agents: fix review findings — thread attribution, races, rescue stall, docs, CI

Fixes from a full repo review: - fetch-thread.sh: attribute every comment to its REAL author (@pm/@qa/… — agents post as their own users now); the old "🤖 @name line at the top" hint pointed at headers we removed, leaving every teammate comment anonymous. Also strip the hidden loop-prevention marker from bodies (prompt noise). - agent.yml: per-issue concurrency group (queued, no cancel) — two quick comments on one issue no longer race the same ai/issue-N branch. - rescue-pr.sh: after opening a rescue PR, hand it back into the flow with an unmarked @pm trigger (the pm→qa choreography previously stalled silently on any rescued run); drop the old "🤖 **@name**" header style; add ops to the token case; mark the status note with the hidden marker. - README: token table said "@qa merges / TOKEN_QA needs write:repository" — inverted since the PM-orchestrated flow (@pm merges, autopilot only; @qa is read-only). Updated the agent table (descs, node1-ssh moved to homelab) and added a "How a task flows" section. - agents.json: pm/qa descs now describe the orchestrator/reviewer roles (these feed the roster prompt agents route by). - NEW ci.yml: bash -n + shellcheck(-S error) on every script, YAML-parse on every workflow, agents.json schema check — the ${x:-{}} brace bug would have been caught here before it shipped. - install-opencode.sh: pin opencode (default 1.17.13, override via OPENCODE_VERSION) — a breaking release no longer takes down every agent. - build-activity-log.sh: ollama/ollama-cloud models are subscription-billed (no $/token exists) — label the footer "subscription" instead of a misleading $0.0000; metered (anthropic) models keep the real dollar cost. - route.sh: document that mention-priority is list-order and load-bearing for the flow's trigger comments. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Merge pull request 'agents: report tokens + $ cost on every agent comment' (#75 ) from feat/comment-cost-report into main
2026-07-06 09:47:34 +03:00 · 2026-07-06 08:22:04 +02:00 · 2026-07-06 09:22:00 +03:00 · 2026-07-05 20:23:44 +02:00 · 2026-07-05 21:23:41 +03:00 · 2026-07-05 20:21:20 +02:00
17 changed files with 769 additions and 249 deletions
@@ -1,24 +1,38 @@
 name: agent
 # Reusable AI-agent workflow, shared across repos. A caller repo triggers on issue_comment/issues
-# and invokes this via:  uses: ffaerber/agents/.gitea/workflows/agent.yml@main  (secrets: inherit).
+# and invokes this via:  uses: gitea/agents/.gitea/workflows/agent.yml@main  (secrets: inherit).
 # The gate + steps run in the caller's event context (github.event.* / github.repository are the caller's).
 on:
  workflow_call:

 jobs:
-  
+
  agent:
+    # One run at a time PER ISSUE: two quick comments on the same issue would otherwise race —
+    # both checking out ai/issue-N, pushing (non-fast-forward loss) and double-posting. Queued
+    # runs wait (no cancel) so every trigger is still processed, just serially.
+    concurrency:
+      group: ai-agent-${{ github.repository }}-${{ github.event.issue.number }}
+      cancel-in-progress: false
    # Trusted author only, and only when a known agent is mentioned. This gate is the main
    # defense against malicious-issue prompt injection — do not loosen it.
    if: >
      (github.event.comment == null && github.event.issue.user.login == 'ffaerber') ||
-      (github.event.comment != null && github.event.comment.user.login == 'ffaerber' &&
+      (github.event.comment != null &&
+       (github.event.comment.user.login == 'ffaerber' ||
+        github.event.comment.user.login == 'pm' ||
+        github.event.comment.user.login == 'junior' ||
+        github.event.comment.user.login == 'senior' ||
+        github.event.comment.user.login == 'lead' ||
+        github.event.comment.user.login == 'qa' ||
+        github.event.comment.user.login == 'ops') &&
       !contains(github.event.comment.body, '🤖') &&
       (contains(github.event.comment.body, '@pm') ||
        contains(github.event.comment.body, '@junior') ||
        contains(github.event.comment.body, '@senior') ||
        contains(github.event.comment.body, '@lead') ||
-        contains(github.event.comment.body, '@qa')))
+        contains(github.event.comment.body, '@qa') ||
+        contains(github.event.comment.body, '@ops')))
    runs-on: ci-runner
    steps:
      - name: Acknowledge with 👀
@@ -54,7 +68,7 @@ jobs:
      - name: Fetch shared agent scripts (this repo)
        uses: actions/checkout@v4
        with:
-          repository: ffaerber/agents
+          repository: gitea/agents
          ref: main
          path: .agents-workflow
          token: ${{ secrets.GITEA_TOKEN }}
@@ -92,6 +106,7 @@ jobs:
          TOKEN_JUNIOR: ${{ secrets.TOKEN_JUNIOR }}
          TOKEN_LEAD: ${{ secrets.TOKEN_LEAD }}
          TOKEN_QA: ${{ secrets.TOKEN_QA }}
+          TOKEN_OPS: ${{ secrets.TOKEN_OPS }}
        run: bash "$SCRIPTS/route.sh"

      - name: Install opencode + provider config (+ Playwright MCP for browser agents)
@@ -103,34 +118,38 @@ jobs:
          SKILLS: ${{ steps.prep.outputs.skills }}   # JSON array of skills this agent may load
        run: bash "$SCRIPTS/install-opencode.sh"

-      - name: Set up read-only SSH alias `node1` (+ opencode skill so the agent actually knows about it)
-        # 1) Writes the deploy key + an SSH config alias so the agent can run
-        #    `ssh node1 <read-only cmd>` (matches the homelab opencode.json allowlist).
-        # 2) Emits a `node1-ssh` opencode Skill file under ~/.config/opencode/skills/ so any
-        #    downstream repo's dev agent discovers this capability via OpenCode's skill registry
-        #    rather than having to trial against the permission allowlist. Only emitted when the
-        #    swarm plumbing is actually wired for that caller (SWARM_HOST/SWARM_USER/SSH_PRIV_KEY).
-        # All three secrets are passed via env and never inlined into shell — this shared workflow
-        # runs in repos that don't have them and must not fail there.
+      - name: Install caller-provided skills (from the caller repo's .gitea/agent-skills/)
+        # Framework skill-plugin hook. A consuming repo can ship its OWN opencode skills under
+        # `.gitea/agent-skills/<name>/` (SKILL.md + skill.json + optional setup.sh) — e.g. homelab's
+        # "ssh into the deploy host" skill. This installs the ones allowed for the running agent, so
+        # deploy-target / infra specifics live in the repo they belong to, not in this framework.
+        # SECRETS_JSON = toJSON(secrets): a caller's setup.sh reads the repo-specific secrets it needs
+        # (whose names this framework can't know) via jq; it never touches disk here in the clear.
        env:
          SCRIPTS: ${{ runner.temp }}/agents-scripts
-          SWARM_HOST: ${{ secrets.SWARM_HOST }}
-          SWARM_USER: ${{ secrets.SWARM_USER }}
-          SSH_PRIV_KEY: ${{ secrets.SSH_PRIV_KEY }}
-        run: bash "$SCRIPTS/skill-node1-ssh.sh"
+          NAME: ${{ steps.prep.outputs.name }}
+          WORKSPACE: ${{ github.workspace }}
+          SECRETS_JSON: ${{ toJSON(secrets) }}
+        run: bash "$SCRIPTS/install-caller-skills.sh"

      - name: Set up `gitea-api` skill (let agents read/write issues, PRs, Actions across repos)
-        # Mirrors the node1-ssh pattern: emit an opencode Skill file under
-        # ~/.config/opencode/skills/ so any dev agent discovers the capability via OpenCode's
-        # skill registry. The credential is the shared AGENT_TOKEN (a PAT whose scopes the
-        # maintainer set at creation time — issue/repository/organization/misc read+write, cross-repo).
-        # Only emitted when AGENT_TOKEN is actually present, so repos without it don't get a
-        # broken skill. The token is passed via env and never inlined into shell.
+        # Emits an opencode Skill file. The skill uses SELF_TOKEN — the running agent's OWN token
+        # (e.g. TOKEN_PM for @pm), injected into the Run-agent step below — so each agent talks to
+        # Gitea as itself. This step only writes the doc; permission.skill scopes who may load it.
        env:
          SCRIPTS: ${{ runner.temp }}/agents-scripts
-          AGENT_TOKEN: ${{ secrets.AGENT_TOKEN }}
        run: bash "$SCRIPTS/skill-gitea-api.sh"

+      - name: Set up `gitea-admin` skill (@ops only — administer the Gitea instance)
+        # Instance administration (orgs/users/repos/labels/secrets/scoped tokens). The SKILL.md is
+        # written ONLY for @ops (skill-gitea-admin.sh gates on NAME) and permission.skill also denies
+        # it to every other agent. It uses SELF_TOKEN (which for @ops is TOKEN_OPS), injected into the
+        # Run-agent step. This step only writes the doc.
+        env:
+          SCRIPTS: ${{ runner.temp }}/agents-scripts
+          NAME: ${{ steps.prep.outputs.name }}
+        run: bash "$SCRIPTS/skill-gitea-admin.sh"
+
      - name: Inspect / fetch image attachments (download only for vision agents)
        id: imgs
        env:
@@ -152,16 +171,19 @@ jobs:
        env:
          SCRIPTS: ${{ runner.temp }}/agents-scripts
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          # AGENT_TOKEN powers the `gitea-api` skill (cross-repo issue/PR/Actions read+write).
-          # It is already a required secret for the delegation step below; exposing it here too
-          # lets the agent process itself call the Gitea API on demand.
-          AGENT_TOKEN: ${{ secrets.AGENT_TOKEN }}
+          # SELF_TOKEN = the RUNNING agent's OWN token (TOKEN_PM for @pm, TOKEN_OPS for @ops, …).
+          # Only this agent's token is placed in its process env, so no agent can act as another.
+          # Powers the gitea-api / gitea-admin skills — each agent calls Gitea as itself. Every
+          # consuming repo now carries the per-agent TOKEN_* secrets (org-level for gitea/*, user-level
+          # for ffaerber/*), so there is no shared-token fallback.
+          SELF_TOKEN: ${{ steps.prep.outputs.name == 'pm' && secrets.TOKEN_PM || steps.prep.outputs.name == 'junior' && secrets.TOKEN_JUNIOR || steps.prep.outputs.name == 'senior' && secrets.TOKEN_SENIOR || steps.prep.outputs.name == 'lead' && secrets.TOKEN_LEAD || steps.prep.outputs.name == 'qa' && secrets.TOKEN_QA || steps.prep.outputs.name == 'ops' && secrets.TOKEN_OPS || '' }}
          NAME: ${{ steps.prep.outputs.name }}
          MODEL: ${{ steps.prep.outputs.model }}
          VISION: ${{ steps.prep.outputs.vision }}
          MODE: ${{ steps.prep.outputs.mode }}
          HAS_IMAGES: ${{ steps.imgs.outputs.has_images }}
          BRANCH: ${{ steps.prep.outputs.branch }}
+          AUTOPILOT: ${{ steps.prep.outputs.autopilot }}   # 'true' when the issue carries the `autopilot` label
          NUM: ${{ github.event.issue.number }}
          TITLE: ${{ github.event.issue.title }}
          IBODY: ${{ github.event.issue.body }}
@@ -169,29 +191,33 @@ jobs:
          FILES: ${{ steps.imgs.outputs.files }}   # opencode -f image flags (vision agents only)
        run: bash "$SCRIPTS/run-agent.sh"

-      - name: Build activity log (tool calls + reasoning) from the event stream
+      - name: Build run report (tool calls + input/output tokens + $ cost) from the event stream
        id: log
        env:
          SCRIPTS: ${{ runner.temp }}/agents-scripts
          MODE: ${{ steps.prep.outputs.mode }}
+          MODEL: ${{ steps.prep.outputs.model }}   # ollama-cloud models are subscription-billed (no $/token)
        run: bash "$SCRIPTS/build-activity-log.sh"

      - name: Publish — PR (dev agents) or comment (pm), always reply in the issue
        env:
          SCRIPTS: ${{ runner.temp }}/agents-scripts
          GT: ${{ secrets.GITEA_TOKEN }}
-          AGENT_TOKEN: ${{ secrets.AGENT_TOKEN }}
          TOKEN_PM: ${{ secrets.TOKEN_PM }}
          TOKEN_SENIOR: ${{ secrets.TOKEN_SENIOR }}
          TOKEN_JUNIOR: ${{ secrets.TOKEN_JUNIOR }}
          TOKEN_LEAD: ${{ secrets.TOKEN_LEAD }}
          TOKEN_QA: ${{ secrets.TOKEN_QA }}
+          TOKEN_OPS: ${{ secrets.TOKEN_OPS }}
          NAME: ${{ steps.prep.outputs.name }}
          MODE: ${{ steps.prep.outputs.mode }}
          NUM: ${{ github.event.issue.number }}
          TITLE: ${{ github.event.issue.title }}
          BRANCH: ${{ steps.prep.outputs.branch }}
          NEW: ${{ steps.prep.outputs.new }}
+          IS_PR: ${{ github.event.issue.pull_request }}   # set when this run is on a PR thread
+          AUTOPILOT: ${{ steps.prep.outputs.autopilot }}   # 'true' when the origin issue carries `autopilot`
+          ISSNUM: ${{ steps.prep.outputs.issnum }}          # origin issue number (resolved from branch on PR threads)
        run: bash "$SCRIPTS/publish.sh"

      # Failure-safe: if any step above failed AFTER a dev agent already pushed commits, the normal
@@ -208,6 +234,7 @@ jobs:
          TOKEN_JUNIOR: ${{ secrets.TOKEN_JUNIOR }}
          TOKEN_LEAD: ${{ secrets.TOKEN_LEAD }}
          TOKEN_QA: ${{ secrets.TOKEN_QA }}
+          TOKEN_OPS: ${{ secrets.TOKEN_OPS }}
          NAME: ${{ steps.prep.outputs.name }}
          MODE: ${{ steps.prep.outputs.mode }}
          NUM: ${{ github.event.issue.number }}
@@ -1,5 +1,6 @@
 name: ai-agent
-# Standard caller for the shared AI-agent workflow (ffaerber/agents). Copy this file VERBATIM into
+run-name: "ai-agent · #${{ github.event.issue.number }}"   # quotes required: bare # starts a YAML comment
+# Standard caller for the shared AI-agent workflow (gitea/agents). Copy this file VERBATIM into
 # any repo that should get the agents — it is identical in every repo. All logic + scripts live in
 # agents/.gitea/workflows/; scripts are fetched from @main at run time. The `jobs.agent` wrapper is
 # required: a reusable (workflow_call) workflow can only be invoked from a caller job, not top-level.
@@ -10,5 +11,5 @@ on:
    types: [opened]
 jobs:
  agent:
-    uses: ffaerber/agents/.gitea/workflows/agent.yml@main
+    uses: gitea/agents/.gitea/workflows/agent.yml@main
    secrets: inherit
@@ -0,0 +1,56 @@
+name: ci
+run-name: "ci · ${{ github.event.pull_request.title || github.sha }}"
+# Lint the very scripts every agent run executes. A single unchecked shell bug here breaks ALL
+# agents in ALL repos at once (e.g. the ${VAR:-{}} brace bug shellcheck flags as SC1083/SC2321),
+# so PRs must pass: bash -n + shellcheck on every script, YAML-parse on every workflow, and a
+# schema check on agents.json (the routing registry).
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+jobs:
+  lint:
+    runs-on: ci-runner
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install linters
+        run: |
+          command -v shellcheck >/dev/null || (apt-get update -qq && apt-get install -y -qq shellcheck) || \
+            sudo sh -c 'apt-get update -qq && apt-get install -y -qq shellcheck' || true
+          python3 -c 'import yaml' 2>/dev/null || pip3 install --quiet pyyaml || \
+            (apt-get install -y -qq python3-yaml || sudo apt-get install -y -qq python3-yaml) || true
+
+      - name: bash -n (syntax) — every script
+        run: |
+          set -e
+          for f in .gitea/workflows/scripts/*.sh; do bash -n "$f" && echo "OK $f"; done
+
+      - name: shellcheck — every script
+        run: |
+          set -e
+          if command -v shellcheck >/dev/null; then
+            # error-severity only: the scripts intentionally use unquoted word-splitting in places;
+            # errors (real breakage like the ${x:-{}} brace bug) must fail the build.
+            shellcheck -S error .gitea/workflows/scripts/*.sh && echo "shellcheck clean (severity=error)"
+          else
+            echo "shellcheck unavailable on runner — skipped"
+          fi
+
+      - name: YAML-parse every workflow
+        run: |
+          set -e
+          python3 - <<'EOF'
+          import glob, sys, yaml
+          for f in sorted(glob.glob('.gitea/workflows/*.yml')):
+              yaml.safe_load(open(f))
+              print('OK', f)
+          EOF
+
+      - name: Validate agents.json (registry schema)
+        run: |
+          set -e
+          jq -e 'to_entries | all(.value | (.model|type=="string") and (.mode=="pr" or .mode=="comment")
+                 and (.vision|type=="boolean") and (.skills|type=="array") and (.desc|type=="string"))' \
+            .gitea/workflows/scripts/agents.json >/dev/null && echo "agents.json OK"
@@ -1,7 +1,54 @@
 {
-  "pm":     {"model":"ollama-cloud/gemma4:cloud","vision":true, "mode":"comment","skills":["gitea-api"],"desc":"Product manager — research, plan, ask clarifying questions, and decide which dev should do the work. Comments only; never edits files."},
-  "junior": {"model":"ollama-cloud/kimi-k2.7-code:cloud","vision":false,"mode":"pr",     "skills":[],"desc":"Junior dev — small, low-risk changes (mostly YAML/compose/config). Text-only, cannot read images. Defers complex or image tasks to @senior or @lead."},
-  "senior": {"model":"ollama-cloud/glm-5.2:cloud","vision":false,"mode":"pr",     "skills":["gitea-api","node1-ssh"],"desc":"Senior dev — complex, multi-file implementation (GLM-5.2 via Ollama Cloud, text-only)."},
-  "lead":   {"model":"anthropic/claude-opus-4-8","vision":true, "mode":"pr",     "skills":["gitea-api","node1-ssh"],"desc":"Tech lead — the hardest problems, architecture, and final calls."},
-  "qa":     {"model":"ollama-cloud/minimax-m3:cloud","vision":true, "mode":"comment","skills":["gitea-api"],"desc":"QA — verifies things work. Drives a headless browser (Playwright) to open a URL/web app, click through it, screenshot, and report bugs or confirm behavior. Comments findings; opens no PRs."}
-}
+  "pm": {
+    "model": "ollama-cloud/gemma4:cloud",
+    "vision": true,
+    "mode": "comment",
+    "skills": [
+      "gitea-api"
+    ],
+    "desc": "Product manager & orchestrator — plans and picks the dev, hands each finished PR to @qa for review, and reports back to the issue creator (in autopilot it merges approved PRs itself). Works from the issue thread only — comments only, never edits files, never reads the PR diff."
+  },
+  "junior": {
+    "model": "ollama-cloud/kimi-k2.7-code:cloud",
+    "vision": false,
+    "mode": "pr",
+    "skills": [],
+    "desc": "Junior dev — small, low-risk changes (mostly YAML/compose/config). Text-only, cannot read images. Defers complex or image tasks to @senior or @lead."
+  },
+  "senior": {
+    "model": "ollama-cloud/glm-5.2:cloud",
+    "vision": false,
+    "mode": "pr",
+    "skills": [
+      "gitea-api"
+    ],
+    "desc": "Senior dev — complex, multi-file implementation (GLM-5.2 via Ollama Cloud, text-only)."
+  },
+  "lead": {
+    "model": "anthropic/claude-opus-4-8",
+    "vision": true,
+    "mode": "pr",
+    "skills": [
+      "gitea-api"
+    ],
+    "desc": "Tech lead — the hardest problems, architecture, and final calls."
+  },
+  "qa": {
+    "model": "ollama-cloud/minimax-m3:cloud",
+    "vision": true,
+    "mode": "comment",
+    "skills": [
+      "gitea-api"
+    ],
+    "desc": "QA / reviewer — reviews PRs: reads the diff, drives a headless browser (Playwright) to verify behavior, posts specific recommendations on the PR and the pass/fail verdict on the issue. Never edits code, never merges."
+  },
+  "ops": {
+    "model": "anthropic/claude-opus-4-8",
+    "vision": false,
+    "mode": "comment",
+    "skills": [
+      "gitea-admin"
+    ],
+    "desc": "Gitea operator — administers the Gitea instance itself: create orgs/users/repos, manage labels and secrets, mint scoped per-user tokens, bootstrap new repos with the agent caller. Comments only; never edits code. ALWAYS confirms before any destructive action (delete user/repo/org)."
+  }
+}
@@ -1,26 +1,57 @@
 #!/usr/bin/env bash
-# Build activity log (tool calls + reasoning) from the event stream into /tmp/activity_log.md.
-# Only dev agents (mode=pr) get an activity-log comment — comment-only roles (pm/qa)
-# do no tool calls, so a trail would be empty/noise.
+# Build the RUN REPORT appended to the agent's reply comment: the TOOL CALLS the agent made plus a
+# usage line (input / output tokens + $ cost). Written to /tmp/activity_log.md; the Publish step
+# appends it to the agent's reply. Applies to EVERY agent — @pm/@qa also call tools and cost money.
 #
-# Required env (provided by the workflow step): MODE
+# opencode --format json emits one JSON event per line. `step_finish` events carry, per LLM step,
+# .part.tokens {input, output, reasoning, cache:{read, write}} and .part.cost (USD, already computed
+# by opencode from the model's pricing). We sum them across all steps of the run. Models without
+# pricing (e.g. self-hosted ollama) report cost 0 — shown as $0.0000.
+#
+# Required env (provided by the workflow step): (none needed; reads /tmp/events.jsonl)
 set -u
+E=/tmp/events.jsonl
+: > /tmp/activity_log.md
+[ -s "$E" ] || { echo "no events — empty report"; exit 0; }

-if [ "$MODE" != "pr" ]; then
-  echo "skipping activity log for comment-mode agent"; : > /tmp/activity_log.md; exit 0
-fi
+# Tool calls = the ACTIONS taken (not the agent's prose text parts).
 jq -r '
  def trunc(n): if length > n then (.[0:n] + "…") else . end;
-  select(.type=="tool_use" or .type=="text") |
-    if .type=="text" then
-      "💬 " + ((.part.text // "") | trunc(4000))
-    else
-      (.part.tool // "?") as $t |
-      ((.part.state.title // (.part.state.input | tojson | trunc(160)) // "")) as $title |
-      "🔧 **" + $t + "**: `" + ($title | trunc(240)) + "`"
-    end
-' /tmp/events.jsonl > /tmp/activity_log.md 2>/dev/null || true
-n=$(wc -l < /tmp/activity_log.md 2>/dev/null || echo 0)
-echo "activity log: $n entries"
-[ "$n" -eq 0 ] && : > /tmp/activity_log.md
-head -3 /tmp/activity_log.md
+  select(.type=="tool_use") |
+    (.part.tool // "?") as $t |
+    ((.part.state.title // (.part.state.input | tojson | trunc(160)) // "")) as $title |
+    "🔧 **" + $t + "**: `" + ($title | trunc(240)) + "`"
+' "$E" > /tmp/tools.md 2>/dev/null || true
+n=$(wc -l < /tmp/tools.md 2>/dev/null || echo 0); n=${n:-0}
+
+# Usage: sum per-step tokens + cost across every step_finish event (tab-separated for `read`).
+read -r COST INP OUT CR CW RE < <(jq -rs '
+  [ .[] | select(.type=="step_finish") | .part ] as $s
+  | [ ([$s[].cost // 0]|add // 0),
+      ([$s[].tokens.input // 0]|add // 0),
+      ([$s[].tokens.output // 0]|add // 0),
+      ([$s[].tokens.cache.read // 0]|add // 0),
+      ([$s[].tokens.cache.write // 0]|add // 0),
+      ([$s[].tokens.reasoning // 0]|add // 0) ]
+  | @tsv' "$E" 2>/dev/null)
+COST=${COST:-0}; INP=${INP:-0}; OUT=${OUT:-0}; CR=${CR:-0}; CW=${CW:-0}; RE=${RE:-0}
+IN_TOTAL=$(( INP + CR + CW ))                          # total input context processed
+# Cost label: ollama / ollama-cloud models are SUBSCRIPTION-billed (GPU-time against the plan, no
+# $/token price exists), so a "$0.0000" there would be misleading — label it a subscription instead.
+# Metered providers (anthropic/…) get the real dollar cost opencode computed.
+case "${MODEL:-}" in
+  ollama*|*"/ollama"*) COSTF="subscription" ;;
+  *) COSTF=$(awk -v c="$COST" 'BEGIN{printf "$%.4f", c+0}') ;;
+esac
+echo "usage: in=$IN_TOTAL out=$OUT cost=$COSTF (fresh=$INP cache_r=$CR cache_w=$CW reasoning=$RE); tools=$n"
+
+{
+  if [ "$n" -gt 0 ]; then
+    printf '\n\n<details>\n<summary>🔧 %s tool calls · in %s · out %s · %s</summary>\n\n' "$n" "$IN_TOTAL" "$OUT" "$COSTF"
+    cat /tmp/tools.md
+    printf '\n\n<sub>tokens — input %s (fresh %s · cache %sw / %sr) · output %s · reasoning %s · **%s**</sub>\n</details>' \
+      "$IN_TOTAL" "$INP" "$CW" "$CR" "$OUT" "$RE" "$COSTF"
+  else
+    printf '\n\n<sub>💰 **%s** · in %s · out %s tokens (cache %sw / %sr)</sub>' "$COSTF" "$IN_TOTAL" "$OUT" "$CW" "$CR"
+  fi
+} > /tmp/activity_log.md
@@ -1,5 +1,8 @@
 #!/usr/bin/env bash
 # Fetch the full issue thread (shared memory) into /tmp/thread.md.
+# Agents post as their OWN Gitea users, so .user.login IS the agent name — attribute each comment
+# to its real author (@pm/@qa/@junior/…). Strip the hidden `<!-- 🤖 … -->` loop-prevention marker
+# from bodies — it's plumbing, not conversation, and would just waste prompt tokens.
 #
 # Required env (provided by the workflow step): GT NUM GITHUB_SERVER_URL GITHUB_REPOSITORY
 set -eu
@@ -7,9 +10,8 @@ set -eu
 API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
 curl -sS -H "Authorization: token $GT" "$API/issues/$NUM/comments?limit=100" 2>/dev/null \
  | jq -r '.[] |
-      ( if   (.body | test("delegated by"))  then "an automated delegation"
-        elif (.user.login == "ffaerber")     then "ffaerber (the maintainer / you)"
-        else "an AI teammate — the specific one is named in the 🤖 @name line at the top of the comment"
-        end ) as $who |
-      "### comment by \($who):\n\(.body)\n"' > /tmp/thread.md 2>/dev/null || true
+      ( if (.user.login == "ffaerber") then "@ffaerber (the maintainer)"
+        else "@" + .user.login end ) as $who |
+      "### comment by \($who):\n\(.body | gsub("\\s*<!-- 🤖 agent reply — do not trigger -->"; ""))\n"' \
+  > /tmp/thread.md 2>/dev/null || true
 echo "thread comments fetched: $(grep -c '^### comment by ' /tmp/thread.md 2>/dev/null || echo 0)"
@@ -0,0 +1,70 @@
+#!/usr/bin/env bash
+# Install CALLER-PROVIDED opencode skills — the framework's skill-plugin hook.
+#
+# The reusable workflow ships a few built-in skills (gitea-api, gitea-admin). A consuming repo can
+# add its OWN, repo-specific skills (e.g. a homelab "ssh into the deploy host" skill) without any
+# change to this framework: it commits them under `.gitea/agent-skills/<name>/` in its own repo.
+# This step discovers them in the checked-out caller workspace and installs the ones allowed for the
+# running agent. That keeps deploy-target / infra specifics in the repo they belong to, not here.
+#
+# Layout the framework expects, per skill, in the CALLER repo:
+#   .gitea/agent-skills/<name>/
+#     SKILL.md     (required) — the opencode Skill doc; copied verbatim into the skill registry.
+#     skill.json   (required) — {"agents":["senior","lead"]} — which agents may load this skill.
+#     setup.sh     (optional) — runtime setup (e.g. write an SSH alias). Runs ONLY when this agent is
+#                  allowed the skill. Receives $SECRETS_JSON (all inherited secrets, as JSON) and must
+#                  extract what it needs via jq; it must no-op cleanly if its secrets aren't set.
+#
+# Required env (provided by the workflow step): NAME WORKSPACE SECRETS_JSON
+#   (SECRETS_JSON = toJSON(secrets); passed so a caller's setup.sh can read repo-specific secrets
+#    whose names this framework cannot know in advance.)
+#
+# IMPORTANT — caller-skill secrets read from SECRETS_JSON MUST be single-line. The runner masks a
+# secret's value in logs by exact match, but toJSON(secrets) escapes newlines to '\n', so a MULTILINE
+# secret (e.g. a raw PEM key) no longer matches the mask and would print in cleartext in the step's
+# "expression evaluated to …" log line. Store multiline values base64-encoded (single-line) and
+# decode them inside setup.sh. Single-line values mask correctly.
+set -eu
+
+# Safe default for SECRETS_JSON (see note at the setup.sh call below re: the ${x:-{}} brace bug).
+SJ="${SECRETS_JSON:-}"; [ -n "$SJ" ] || SJ='{}'
+DIR="${WORKSPACE:-$GITHUB_WORKSPACE}/.gitea/agent-skills"
+CFG="$HOME/.config/opencode/opencode.json"
+[ -d "$DIR" ] || { echo "no caller skills (.gitea/agent-skills/ absent) — nothing to install"; exit 0; }
+
+allow='{}'   # skills to flip to "allow" in permission.skill for THIS agent
+for skill_dir in "$DIR"/*/; do
+  [ -d "$skill_dir" ] || continue
+  name=$(basename "$skill_dir")
+  md="$skill_dir/SKILL.md"; meta="$skill_dir/skill.json"
+  if [ ! -f "$md" ] || [ ! -f "$meta" ]; then
+    echo "caller skill '$name': missing SKILL.md or skill.json — skipping"; continue
+  fi
+  # Is this agent allowed the skill?
+  if ! jq -e --arg n "$NAME" '(.agents // []) | index($n)' "$meta" >/dev/null 2>&1; then
+    echo "caller skill '$name': not allowed for @$NAME — skipping"; continue
+  fi
+  # Install the doc.
+  dest="$HOME/.config/opencode/skills/$name"
+  mkdir -p "$dest" && chmod 700 "$dest"
+  cp "$md" "$dest/SKILL.md"
+  chmod -R o=rX "$dest"
+  # Optional runtime setup, with all inherited secrets available as JSON (never printed here).
+  # NOTE: pass SECRETS_JSON via a plain variable — do NOT inline ${SECRETS_JSON:-{}} here or in
+  # setup.sh: bash brace-matching appends a stray '}' when the var is set, corrupting the JSON so
+  # the skill's `jq` fails ("Unmatched '}'") and the skill is silently skipped.
+  if [ -f "$skill_dir/setup.sh" ]; then
+    echo "caller skill '$name': running setup.sh for @$NAME"
+    SECRETS_JSON="$SJ" NAME="$NAME" WORKSPACE="${WORKSPACE:-$GITHUB_WORKSPACE}" \
+      bash "$skill_dir/setup.sh" || { echo "caller skill '$name': setup.sh failed — skipping this skill"; continue; }
+  fi
+  allow=$(jq -nc --argjson a "$allow" --arg n "$name" '$a + {($n):"allow"}')
+  echo "caller skill '$name': installed + allowed for @$NAME"
+done
+
+# Merge the allowed caller skills into the permission allow-list opencode already wrote.
+if [ "$allow" != '{}' ] && [ -f "$CFG" ]; then
+  tmp=$(mktemp)
+  jq --argjson add "$allow" '.permission.skill = ((.permission.skill // {}) + $add)' "$CFG" > "$tmp" && mv "$tmp" "$CFG"
+  echo "permission.skill updated with caller skills: $(jq -c '.permission.skill' "$CFG")"
+fi
@@ -5,7 +5,11 @@
 #   GITHUB_PATH HOME
 set -eu

-curl -fsSL https://opencode.ai/install | bash
+# PIN the opencode version: an unpinned `latest` means a breaking release (CLI flags, or the
+# --format json event schema that build-activity-log.sh parses) breaks every agent in every repo
+# at once. Bump deliberately by changing this default (or set OPENCODE_VERSION in the step env).
+OPENCODE_VERSION="${OPENCODE_VERSION:-1.17.13}"
+curl -fsSL https://opencode.ai/install | bash -s -- --version "$OPENCODE_VERSION"
 echo "$HOME/.opencode/bin" >> "$GITHUB_PATH"
 mkdir -p ~/.config/opencode
 # Playwright browser MCP only for agents that need to drive a web app
@@ -2,39 +2,136 @@
 # Publish — PR (dev agents) or comment (pm/qa), always reply in the issue.
 #
 # Required env (provided by the workflow step):
-#   GT AGENT_TOKEN TOKEN_PM TOKEN_SENIOR TOKEN_JUNIOR TOKEN_LEAD TOKEN_QA
+#   GT TOKEN_PM TOKEN_SENIOR TOKEN_JUNIOR TOKEN_LEAD TOKEN_QA
 #   NAME MODE NUM TITLE BRANCH NEW GITHUB_SERVER_URL GITHUB_REPOSITORY
+#   IS_PR AUTOPILOT ISSNUM  (autopilot: @qa label-gated merge/halt + auto-trigger @qa on a fresh PR)
 set +e   # publish is best-effort: a grep-no-match / curl non-zero must NOT kill the step
 # Post/PR as the agent's OWN Gitea user when its token is configured; else the built-in bot.
 case "$NAME" in
  pm) TOK="$TOKEN_PM";; senior) TOK="$TOKEN_SENIOR";; junior) TOK="$TOKEN_JUNIOR";;
-  lead) TOK="$TOKEN_LEAD";; qa) TOK="$TOKEN_QA";; *) TOK="";;
+  lead) TOK="$TOKEN_LEAD";; qa) TOK="$TOKEN_QA";; ops) TOK="$TOKEN_OPS";; *) TOK="";;
 esac
 [ -z "$TOK" ] && TOK="$GT"
+# Trigger token: comments that must FIRE the next workflow (delegation, autopilot) and PR merges
+# cannot use the built-in GITEA_TOKEN (Gitea won't start new runs from it) — they need a real PAT.
+# Every agent now has its own token, so TTOK is just the agent's token. If an agent somehow has none
+# (TOK fell back to the built-in GT), TTOK is left empty so the trigger/merge is skipped rather than
+# silently no-op'ing under the built-in token.
+TTOK="$TOK"
+[ "$TTOK" = "$GT" ] && TTOK=""
 git config user.name  "$NAME"
 git config user.email "$NAME@ffaerber.duckdns.org"
 API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
 hdr=(-H "Authorization: token $TOK" -H "Content-Type: application/json")
+# Hidden loop-prevention marker appended to every agent REPLY/STATUS comment. Gitea already shows
+# who authored a comment, so we don't repeat the agent's name in the body; but the trigger gate keys
+# on the '🤖' character to know "this is an agent's own comment, don't fire a new run". An HTML
+# comment renders as nothing, so the marker is invisible while still tripping the gate's guard.
+# NOTE: trigger comments (delegation / autopilot / bounce) are posted with inline curl, NOT post()/
+# prpost(), so they never get this marker and therefore DO fire the next run — that is intended.
+MARK=$'\n\n<!-- 🤖 agent reply — do not trigger -->'
 post() { curl -sS -w 'comment -> HTTP %{http_code}\n' -X POST "${hdr[@]}" \
-  "$API/issues/$NUM/comments" -d "$(jq -nc --arg b "$1" '{body:$b}')"; }
+  "$API/issues/$NUM/comments" -d "$(jq -nc --arg b "$1$MARK" '{body:$b}')"; }
+# Post a MARKED status/reply comment to an ARBITRARY thread (issue or PR) — never fires a run.
+post_to() { curl -sS -w "comment(#$1) -> HTTP %{http_code}\n" -X POST "${hdr[@]}" \
+  "$API/issues/$1/comments" -d "$(jq -nc --arg b "$2$MARK" '{body:$b}')"; }
+# Post an UNMARKED TRIGGER comment on a thread — fires the mentioned agent's next run. Must use a PAT
+# (TTOK); the built-in GITEA_TOKEN cannot start new runs. No-op (logged) if this agent has no PAT.
+trig() { if [ -z "$TTOK" ]; then echo "no trigger token — cannot fire on #$1"; return; fi
+  curl -sS -w "trigger(#$1) -> HTTP %{http_code}\n" -X POST \
+    -H "Authorization: token $TTOK" -H "Content-Type: application/json" \
+    "$API/issues/$1/comments" -d "$(jq -nc --arg b "$2" '{body:$b}')"; }
+# Origin issue for this run (route.sh resolves it from the branch on PR threads), and a resolver for
+# the open PR built from its branch (ai/issue-<issue>). Lets @pm/@qa cross between the issue and PR.
+ISSN="${ISSNUM:-$NUM}"
+resolve_pr() { curl -sS "${hdr[@]}" "$API/pulls?state=open&limit=50" \
+  | jq -r --arg br "ai/issue-$ISSN" 'if type=="array" then (map(select(.head.ref==$br))|.[0].number // empty) else empty end' 2>/dev/null; }
+# Remove the 'autopilot' label from an issue by resolving its ID first (Gitea's DELETE label
+# endpoint is by ID, not name). Arg $1 = issue number. Used as the autopilot kill switch.
+del_autopilot_label() {
+  local iss="$1" lid
+  lid=$(curl -sS "${hdr[@]}" "$API/issues/$iss/labels" 2>/dev/null \
+        | jq -r 'if type=="array" then ([.[]|select(.name=="autopilot")][0].id // empty) else empty end')
+  if [ -n "$lid" ]; then
+    curl -sS -X DELETE "${hdr[@]}" "$API/issues/$iss/labels/$lid" \
+      -w '\nunlabel -> HTTP %{http_code}\n' || true
+  else
+    echo "no 'autopilot' label found on #$iss to remove"
+  fi
+}

-# drop machine-readable markers (DELEGATE / CLOSE_ISSUE / the BEGIN_SUBTASKS..END_SUBTASKS block)
+# drop machine-readable markers: DELEGATE / CLOSE_ISSUE / MERGE_PR / APPROVE / HALT / BOUNCE, and the
+# BEGIN_SUBTASKS..END_SUBTASKS and BEGIN_PR_DESCRIPTION..END_PR_DESCRIPTION blocks (the PR
+# description is published separately).
 reply=$(awk '
  /^[[:space:]]*BEGIN_SUBTASKS/{s=1}
+  /^[[:space:]]*BEGIN_PR_DESCRIPTION/{p=1}
  /^[[:space:]]*DELEGATE:[[:space:]]*@/{next}
  /^[[:space:]]*CLOSE_ISSUE[[:space:]]*$/{next}
+  /^[[:space:]]*MERGE_PR[[:space:]]*$/{next}
+  /^[[:space:]]*APPROVE[[:space:]]*$/{next}
+  /^[[:space:]]*HALT([_ ]AUTOPILOT)?[[:space:]]*$/{next}
+  /^[[:space:]]*BOUNCE:[[:space:]]*@/{next}
  s{ if(/^[[:space:]]*END_SUBTASKS/){s=0}; next }
+  p{ if(/^[[:space:]]*END_PR_DESCRIPTION/){p=0}; next }
  {print}
 ' /tmp/agent_out.md 2>/dev/null)
+# Strip a leading self-identification header the model sometimes emits, e.g. "🤖 **@pm**",
+# "🔨 **@senior**", or a heading like "## 🔨 @senior — <title>". Gitea already attributes the comment
+# to its author, so we drop any leading line that references the agent's OWN @handle — or a bare
+# "**@name**" line — together with surrounding blank lines, up to the first real content line.
+reply=$(printf '%s' "$reply" | awk -v me="@$NAME" '
+  BEGIN{s=1}
+  s && /^[[:space:]]*$/ {next}
+  s && index($0, me) {next}
+  s && /^[^A-Za-z0-9]*\*\*@[A-Za-z]+\*\*[[:space:]]*$/ {next}
+  {s=0; print}
+')
 [ -z "$reply" ] && reply="_(Made changes without a text summary — see the diff below.)_"
 # Prefer the agent's clean delimited PR description; fall back to the whole reply.
 prdesc=$(awk '/BEGIN_PR_DESCRIPTION/{f=1;next} /END_PR_DESCRIPTION/{f=0} f' /tmp/agent_out.md)
 [ -z "$prdesc" ] && prdesc="$reply"
+# Run report (tool calls + input/output tokens + $ cost) built by build-activity-log.sh. Appended to
+# every agent's reply comment so each run reports what it did and what it cost.
+activity="$(cat /tmp/activity_log.md 2>/dev/null || true)"

 # comment-only roles (pm/qa): never change files
 if [ "$MODE" != "pr" ]; then
  git checkout -- . 2>/dev/null || true
  git clean -fd  2>/dev/null || true
+
+  # ---------- @qa: reviewer only — never edits, never merges ----------
+  # Recommendations land ON THE PR (onsite the diff); the pass/fail verdict lands ON THE ISSUE so
+  # @pm (who never reads the PR) can act on it. Ends its reply with APPROVE / BOUNCE: @dev / HALT.
+  if [ "$NAME" = "qa" ]; then
+    PRN=$(resolve_pr)
+    if grep -qiE '^[[:space:]]*APPROVE[[:space:]]*$' /tmp/agent_out.md; then
+      post_to "$ISSN" "$(printf '✅ Reviewed PR #%s — looks good.\n\n%s%s' "${PRN:-?}" "$reply" "$activity")"
+      trig    "$ISSN" "@pm — @qa approved PR #${PRN:-?} (issue #$ISSN). Over to you."
+    elif grep -qiE '^[[:space:]]*BOUNCE:[[:space:]]*@(junior|senior|lead)' /tmp/agent_out.md; then
+      dev=$(grep -oiE 'BOUNCE:[[:space:]]*@(junior|senior|lead)' /tmp/agent_out.md | head -1 | grep -oiE '(junior|senior|lead)' | tr '[:upper:]' '[:lower:]')
+      [ -z "$dev" ] && [ -n "$PRN" ] && dev=$(curl -sS "${hdr[@]}" "$API/pulls/$PRN" | jq -r '.user.login // "junior"')
+      dest="${PRN:-$NUM}"
+      post_to "$dest" "$reply$activity"              # recommendations, on the PR
+      # Bounce budget: count prior "fix attempt" markers on the PR thread; stop after 3.
+      prior=$(curl -sS "${hdr[@]}" "$API/issues/$dest/comments?limit=100" | jq -r 'if type=="array" then [.[]|select(.body|test("fix attempt"))]|length else 0 end' 2>/dev/null); prior=${prior:-0}
+      if [ "$prior" -ge 3 ]; then
+        [ "$AUTOPILOT" = "true" ] && del_autopilot_label "$ISSN"
+        post_to "$ISSN" "🛑 Still not right after 3 fix attempts on PR #${PRN:-?} — handing to @ffaerber (details on the PR)."
+      else
+        n=$((prior + 1))
+        trig "$dest" "@${dev:-junior} please address @qa's review above and update PR #${PRN:-?} (fix attempt $n/3)."
+      fi
+    elif grep -qiE '^[[:space:]]*HALT([_ ]AUTOPILOT)?[[:space:]]*$' /tmp/agent_out.md; then
+      [ "$AUTOPILOT" = "true" ] && del_autopilot_label "$ISSN"
+      post_to "$ISSN" "$(printf '🛑 This needs a human decision (not a dev fix) — @ffaerber please take a look.\n\n%s%s' "$reply" "$activity")"
+    else
+      post_to "${PRN:-$NUM}" "$reply$activity"       # no verdict yet (a question) — post where qa works
+    fi
+    exit 0
+  fi
+
+  # ---------- @pm / @ops: issue-thread orchestration ----------
  target=$(grep -oiE 'DELEGATE:[[:space:]]*@(junior|senior|lead|qa)' /tmp/agent_out.md 2>/dev/null | head -1 | grep -oiE '(junior|senior|lead|qa)' | tr '[:upper:]' '[:lower:]')
  # Visible comment: the reply text, or a sensible line if the agent only emitted a marker.
  msg="$reply"
@@ -77,26 +174,52 @@ if [ "$MODE" != "pr" ]; then
      echo "created sub-issue #${n:-?}: $title"
      [ -n "$n" ] && links="$links\n- #$n — $title"
    done < /tmp/subtasks.txt
-    subtext=$(printf '\n\n---\n🤖 **@%s** — created sub-issues%s (mention an agent on each when ready):%b' "$NAME" "${ms:+ under milestone **$ms**}" "$links")
+    subtext=$(printf '\n\n---\nCreated sub-issues%s (mention an agent on each when ready):%b' "${ms:+ under milestone **$ms**}" "$links")
  fi
-  post "$(printf '🤖 **@%s**\n\n%s%s' "$NAME" "$msg" "$subtext")"
-  # Auto-delegate: if the plan names a teammate, trigger them via AGENT_TOKEN (a PAT, so it
-  # fires a new workflow run — the built-in token cannot). Never targets @pm or self, so the
-  # chain always terminates at a dev. The '🤖' guard on the trigger stops status-comment loops.
-  if [ -n "$AGENT_TOKEN" ]; then
-    # Only delegate on an explicit "DELEGATE: @<agent>" line — never on a prose mention,
-    # so an agent that is asking the maintainer a question does not hand off prematurely.
-    target=$(grep -oiE 'DELEGATE:[[:space:]]*@(junior|senior|lead|qa)' /tmp/agent_out.md 2>/dev/null \
-             | head -1 | grep -oiE '(junior|senior|lead|qa)' | tr '[:upper:]' '[:lower:]')
-    if [ -n "$target" ] && [ "$target" != "$NAME" ]; then
-      echo "auto-delegating to @$target"
-      curl -sS -X POST -H "Authorization: token $AGENT_TOKEN" -H "Content-Type: application/json" \
-        "$API/issues/$NUM/comments" \
-        -d "$(jq -nc --arg b "@$target please proceed with issue #$NUM per the plan above (delegated by $NAME)." '{body:$b}')" \
-        -w '\ndelegate -> HTTP %{http_code}\n' || true
+  post "$(printf '%s%s%s' "$msg" "$subtext" "$activity")"
+
+  # --- @pm autopilot merge: @pm is the ONLY agent that merges, and ONLY under the autopilot label ---
+  # (@qa never merges — it approves and hands back here.) Merge with the PAT (TTOK), not the built-in
+  # token, so the push to main fires the deploy. TOKEN_PM must carry write:repository.
+  if [ "$NAME" = "pm" ] && [ "$AUTOPILOT" = "true" ] && grep -qiE '^[[:space:]]*MERGE_PR[[:space:]]*$' /tmp/agent_out.md; then
+    PRN=$(resolve_pr)
+    if [ -z "$PRN" ]; then
+      echo "MERGE_PR but no open PR found for issue #$ISSN"
    else
-      echo "no DELEGATE marker — not delegating (agent is asking or finished)"
+      echo "@pm autopilot: merging PR #$PRN (issue #$ISSN)"
+      mc=$(curl -sS -o /tmp/merge_resp.txt -w '%{http_code}' -X POST \
+            -H "Authorization: token $TTOK" -H "Content-Type: application/json" \
+            "$API/pulls/$PRN/merge" -d '{"Do":"merge"}')
+      echo "merge -> HTTP $mc"; cat /tmp/merge_resp.txt 2>/dev/null || true
+      case "$mc" in
+        200|201|204)
+          curl -sS -X PATCH "${hdr[@]}" "$API/issues/$ISSN" -d '{"state":"closed"}' -w '\nclose -> HTTP %{http_code}\n' || true
+          post_to "$ISSN" "✅ Merged PR #$PRN (autopilot) and closed this issue." ;;
+        *)
+          del_autopilot_label "$ISSN"
+          post_to "$ISSN" "⚠️ Tried to merge PR #$PRN but the API returned HTTP $mc (checks not green, a conflict, or TOKEN_PM lacks merge scope). Removed the autopilot label — @ffaerber please take a look." ;;
+      esac
    fi
+    exit 0
+  fi
+
+  # --- @pm delegation: hand the build to a dev, or hand the finished PR to @qa for review ---
+  # Only an explicit 'DELEGATE: @<agent>' line acts (never a prose mention). Fires via the PAT (TTOK)
+  # so a new run starts; the built-in token cannot. Everything posts on the ISSUE — @pm never touches
+  # the PR. Chain terminates: normal → @pm tells the creator (no marker); autopilot → @pm merges above.
+  if [ -n "$target" ] && [ "$target" != "$NAME" ]; then
+    if [ "$target" = "qa" ]; then
+      PRN=$(resolve_pr)
+      if [ -n "$PRN" ]; then
+        trig "$ISSN" "@qa please review PR #$PRN for issue #$ISSN — put your recommendations on the PR, or approve."
+      else
+        echo "DELEGATE:@qa but no open PR yet for issue #$ISSN — not firing"
+      fi
+    else
+      trig "$ISSN" "@$target please proceed with issue #$ISSN per the plan above (delegated by $NAME)."
+    fi
+  else
+    echo "no DELEGATE marker — not delegating (agent is asking or finished)"
  fi
  exit 0
 fi
@@ -123,19 +246,11 @@ fi
 git push origin "HEAD:$BRANCH" || true
 git fetch -q origin 2>/dev/null || true

-prbody=$(printf '%s\n\n---\nResolves #%s · 🤖 @%s' "$prdesc" "$NUM" "$NAME")
+prbody=$(printf '%s\n\n---\nResolves #%s' "$prdesc" "$NUM")
 owner=${GITHUB_REPOSITORY%%/*}

-# Post the agent's activity trail (tool calls + reasoning) inline in the same comment so
-# each run produces exactly ONE comment (issue #38). Computed once here so every dev-agent
-# exit path (no-changes, PR-open-failed, normal) appends it to the single reply comment.
-activity=""
-if [ -s /tmp/activity_log.md ]; then
-  entries=$(wc -l < /tmp/activity_log.md 2>/dev/null || echo 0)
-  log=$(cat /tmp/activity_log.md)
-  activity=$(printf '\n\n---\n🤖 **@%s** — activity log (%s entries):\n<details>\n<summary>tool calls & reasoning</summary>\n\n%s\n\n</details>' "$NAME" "$entries" "$log")
-fi
-
+# $activity (the run report: tool calls + tokens + $ cost) was built once near the top, so every
+# dev-agent exit path (no-changes, PR-open-failed, normal) appends it to the single reply comment.
 # One PR per run: publish ONLY this run's own branch ($BRANCH), never sibling
 # ai/issue-N-* branches. This removes the multi-PR ambiguity that left the
 # activity log stranded on the triggering issue instead of the PR thread.
@@ -143,7 +258,7 @@ br="$BRANCH"
 ahead=$(git rev-list --count "origin/main..origin/$br" 2>/dev/null || echo 0)
 if [ "${ahead:-0}" -eq 0 ]; then
  # No changes on this branch — a plan / questions / analysis only.
-  post "$(printf '🤖 **@%s**\n\n%s%s' "$NAME" "$reply" "$activity")"
+  post "$(printf '%s%s' "$reply" "$activity")"
  exit 0
 fi

@@ -161,7 +276,7 @@ if [ -z "$url" ]; then
  url=$(printf '%s' "$resp" | jq -r '.html_url // empty' 2>/dev/null)
  prnum=$(printf '%s' "$resp" | jq -r '.number // empty' 2>/dev/null)
 fi
-[ -z "$url" ] && { echo "PR open/lookup failed for $br — posting reply on issue instead"; post "$(printf '🤖 **@%s**\n\n%s%s' "$NAME" "$reply" "$activity")"; exit 0; }
+[ -z "$url" ] && { echo "PR open/lookup failed for $br — posting reply on issue instead"; post "$(printf '%s%s' "$reply" "$activity")"; exit 0; }

 # Posts to the PR thread when we have a PR number, else to the origin issue ($NUM).
 prpost() {
@@ -169,12 +284,19 @@ prpost() {
  [ -n "$n" ] && [ "$n" != "$NUM" ] && t="$n"
  echo "posting to #$t"
  curl -sS -w 'comment -> HTTP %{http_code}\n' -X POST "${hdr[@]}" \
-    "$API/issues/$t/comments" -d "$(jq -nc --arg b "$1" '{body:$b}')"
+    "$API/issues/$t/comments" -d "$(jq -nc --arg b "$1$MARK" '{body:$b}')"
 }

 if [ "$NEW" = "true" ]; then
-  prpost "$prnum" "$(printf '🤖 **@%s** — ✅ PR ready for review — @ffaerber please review & merge:\n- %s%s' "$NAME" "$url" "$activity")"
+  # First PR for this issue: record it on the PR thread, then notify @pm on the ISSUE. @pm never
+  # reads the PR, so the issue gets only this one-line ping — @pm then routes it to @qa for review.
+  prpost "$prnum" "$(printf 'Opened PR #%s for review.%s' "$prnum" "$activity")"
+  trig "$ISSN" "@pm — PR #$prnum is ready for review (issue #$ISSN)."
 else
-  # Resume (comment is on a PR thread): include the write-up here too.
-  prpost "$prnum" "$(printf '🤖 **@%s** — updated branch/PR:\n- %s\n\n%s%s' "$NAME" "$url" "$prdesc" "$activity")"
+  # A fix (usually after a @qa bounce): update the PR and hand straight back to @qa to re-verify,
+  # on the PR thread. The qa↔dev loop is direct — it does NOT go back through @pm each round.
+  prpost "$prnum" "$(printf 'Pushed an update to PR #%s.%s' "$prnum" "$activity")"
+  case "$NAME" in
+    junior|senior|lead) trig "$prnum" "@qa please re-verify PR #$prnum — the dev has pushed an update." ;;
+  esac
 fi
@@ -6,7 +6,7 @@
 # the run. Comment-only roles (pm/qa) push nothing, so they are skipped.
 #
 # Required env (provided by the workflow step):
-#   GT TOKEN_PM TOKEN_SENIOR TOKEN_JUNIOR TOKEN_LEAD TOKEN_QA
+#   GT TOKEN_PM TOKEN_SENIOR TOKEN_JUNIOR TOKEN_LEAD TOKEN_QA TOKEN_OPS
 #   NAME MODE NUM TITLE BRANCH GITHUB_SERVER_URL GITHUB_REPOSITORY
 set +e

@@ -17,9 +17,11 @@ set +e
 # Post/PR as the agent's OWN Gitea user when its token is configured; else the built-in bot.
 case "$NAME" in
  pm) TOK="$TOKEN_PM";; senior) TOK="$TOKEN_SENIOR";; junior) TOK="$TOKEN_JUNIOR";;
-  lead) TOK="$TOKEN_LEAD";; qa) TOK="$TOKEN_QA";; *) TOK="";;
+  lead) TOK="$TOKEN_LEAD";; qa) TOK="$TOKEN_QA";; ops) TOK="$TOKEN_OPS";; *) TOK="";;
 esac
 [ -z "$TOK" ] && TOK="$GT"
+# Trigger token: the @pm hand-back below must FIRE a new run, which the built-in token cannot.
+TTOK="$TOK"; [ "$TTOK" = "$GT" ] && TTOK=""
 API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
 hdr=(-H "Authorization: token $TOK" -H "Content-Type: application/json")

@@ -38,18 +40,30 @@ resp=$(curl -sS "${hdr[@]}" "$API/pulls?state=open&limit=50" \
      | jq -r --arg br "$BRANCH" 'if type=="array" then (map(select(.head.ref==$br)) | .[0] // empty) else empty end' 2>/dev/null)
 url=$(printf '%s' "$resp" | jq -r '.html_url // empty' 2>/dev/null)
 if [ -z "$url" ]; then
-  body=$(printf 'The run failed before it could publish, but pushed work exists on this branch — opening a PR so it is not lost.\n\n---\nResolves #%s · 🤖 @%s (auto-rescued after a failed run)' "$NUM" "$NAME")
+  body=$(printf 'The run failed before it could publish, but pushed work exists on this branch — opening a PR so it is not lost.\n\n---\nResolves #%s (auto-rescued after a failed run)' "$NUM")
  resp=$(curl -sS -X POST "${hdr[@]}" "$API/pulls" \
    -d "$(jq -nc --arg t "@$NAME: $TITLE" --arg h "$BRANCH" --arg b "$body" \
          '{title:$t, head:$h, base:"main", body:$b}')")
  echo "rescue PR create ($BRANCH): $resp"
  url=$(printf '%s' "$resp" | jq -r '.html_url // empty' 2>/dev/null)
+  prnum=$(printf '%s' "$resp" | jq -r '.number // empty' 2>/dev/null)
+else
+  prnum=$(printf '%s' "$resp" | jq -r '.number // empty' 2>/dev/null)
 fi

 if [ -n "$url" ]; then
+  # Status note on the issue (marked — must not trigger)…
  curl -sS -X POST "${hdr[@]}" "$API/issues/$NUM/comments" \
-    -d "$(jq -nc --arg b "$(printf '🤖 **@%s** — ⚠️ the run failed, but your pushed work was not lost — a PR was opened for branch \`%s\`:\n- %s' "$NAME" "$BRANCH" "$url")" '{body:$b}')" \
+    -d "$(jq -nc --arg b "$(printf '⚠️ The run failed, but the pushed work was not lost — a PR was opened for branch \`%s\`:\n- %s\n\n<!-- 🤖 agent reply — do not trigger -->' "$BRANCH" "$url")" '{body:$b}')" \
    -w '\nrescue comment -> HTTP %{http_code}\n' || true
+  # …then hand the rescued PR back into the flow: without this, the pm→qa choreography would stall
+  # here (the normal "PR ready" trigger never fired). Unmarked + PAT so it starts @pm's run.
+  if [ -n "$TTOK" ]; then
+    curl -sS -X POST -H "Authorization: token $TTOK" -H "Content-Type: application/json" \
+      "$API/issues/$NUM/comments" \
+      -d "$(jq -nc --arg b "@pm — PR #${prnum:-?} was auto-rescued after a failed run (issue #$NUM). Please route it for review." '{body:$b}')" \
+      -w '\nrescue trigger @pm -> HTTP %{http_code}\n' || true
+  fi
 else
  echo "rescue: could not open/find a PR for $BRANCH"
 fi
@@ -27,7 +27,11 @@ cp "$AGENTS_JSON" /tmp/agents.json
 # here — see agent.yml: this reusable workflow sees it as 'workflow_call'.)
 if [ -n "$CID" ]; then scan="$BODY"; else scan="$IBODY"; fi
 name=""
-for a in pm junior senior lead qa; do
+# FIRST MATCH IN THIS LIST ORDER WINS when a comment mentions several agents. The order is
+# load-bearing for the flow's trigger comments: "@pm — @qa approved …" must route to @pm (pm is
+# checked first), while "@junior please address @qa's review …" must route to the dev (devs are
+# checked before qa). If you add an agent or reword a trigger in publish.sh, re-check this order.
+for a in pm junior senior lead qa ops; do
  case "$scan" in *"@$a"*) name=$a; break;; esac
 done
 if [ -z "$name" ]; then
@@ -44,18 +48,26 @@ echo "Routing to @$name (model=$model vision=$vision mode=$mode skills=$skills)"
 # Act as the agent's own Gitea user when its token is set; else the built-in bot.
 case "$name" in
  pm) TOK="$TOKEN_PM";; senior) TOK="$TOKEN_SENIOR";; junior) TOK="$TOKEN_JUNIOR";;
-  lead) TOK="$TOKEN_LEAD";; qa) TOK="$TOKEN_QA";; *) TOK="";;
+  lead) TOK="$TOKEN_LEAD";; qa) TOK="$TOKEN_QA";; ops) TOK="$TOKEN_OPS";; *) TOK="";;
 esac
 [ -z "$TOK" ] && TOK="$GT"
 git config user.name "$name"
 git config user.email "$name@ffaerber.duckdns.org"
 API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
 hdr=(-H "Authorization: token $TOK" -H "Content-Type: application/json")
+branch_ref=""
 if [ -n "$IS_PR" ]; then                     # comment on a PR -> resume its branch
  ref=$(curl -s -H "Authorization: token $GT" "$API/pulls/$NUM" | jq -r .head.ref)
+  branch_ref="$ref"
  git fetch origin "$ref" && git checkout "$ref"
  { echo "branch=$ref"; echo "new=false"; } >> "$GITHUB_OUTPUT"
-else                                         # comment on an issue -> new branch
+elif git ls-remote --exit-code --heads origin "ai/issue-$NUM" >/dev/null 2>&1; then
+  # comment on an issue whose branch ALREADY exists (a prior run / open PR) -> RESUME it, so new
+  # commits fast-forward onto the same branch and update its PR. Branching fresh from main here would
+  # be rejected on push as non-fast-forward and the new work would be silently lost (see issue #17).
+  git fetch origin "ai/issue-$NUM" && git checkout "ai/issue-$NUM"
+  { echo "branch=ai/issue-$NUM"; echo "new=false"; } >> "$GITHUB_OUTPUT"
+else                                         # comment on an issue, no branch yet -> new branch
  git checkout -b "ai/issue-$NUM"
  { echo "branch=ai/issue-$NUM"; echo "new=true"; } >> "$GITHUB_OUTPUT"
  # For dev agents, publish the branch immediately and tell the maintainer where to watch.
@@ -63,6 +75,23 @@ else                                         # comment on an issue -> new branch
    git push -u origin "HEAD:ai/issue-$NUM" || true
    url="${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/src/branch/ai/issue-$NUM"
    curl -sS -X POST "${hdr[@]}" "$API/issues/$NUM/comments" \
-      -d "$(jq -nc --arg b "🔨 **@$name** is on it — building on branch [\`ai/issue-$NUM\`]($url). I'll open a PR when it's ready." '{body:$b}')" >/dev/null || true
+      -d "$(jq -nc --arg b "🔨 Building on branch [\`ai/issue-$NUM\`]($url) — I'll open a PR when it's ready.
+
+<!-- 🤖 agent reply — do not trigger -->" '{body:$b}')" >/dev/null || true
  fi
 fi
+
+# --- Autopilot gate: read the `autopilot` label FRESH every run. ---
+# Presence of this label is the opt-in switch (and the kill switch: remove it mid-flight and the
+# next run reverts to normal human-approval behavior). When @qa is triggered on a PR thread, the
+# label lives on the ORIGIN issue (ai/issue-N), so resolve N from the branch name.
+issnum="$NUM"
+case "$IS_PR" in ?*) issnum=$(printf '%s' "$branch_ref" | sed -nE 's,^ai/issue-([0-9]+).*,\1,p');; esac
+[ -z "$issnum" ] && issnum="$NUM"
+autopilot=false
+if curl -sS -H "Authorization: token $GT" "$API/issues/$issnum/labels" 2>/dev/null \
+     | jq -e 'any(.[]?; .name=="autopilot")' >/dev/null 2>&1; then
+  autopilot=true
+fi
+echo "autopilot (autopilot label on #$issnum)=$autopilot"
+{ echo "autopilot=$autopilot"; echo "issnum=$issnum"; } >> "$GITHUB_OUTPUT"
@@ -3,16 +3,19 @@
 # plain-text reply (/tmp/agent_out.md) plus the raw event stream (/tmp/events.jsonl).
 #
 # Required env (provided by the workflow step):
-#   ANTHROPIC_API_KEY AGENT_TOKEN NAME MODEL VISION MODE HAS_IMAGES BRANCH NUM TITLE IBODY CMT
+#   ANTHROPIC_API_KEY SELF_TOKEN NAME MODEL VISION MODE HAS_IMAGES BRANCH AUTOPILOT NUM TITLE
+#   IBODY CMT
 #   FILES   (the opencode -f image flags, from the imgs step output)
+#   AUTOPILOT is 'true' when the issue carries the `autopilot` label (label-gated autopilot mode).
 set -u

 [ -z "$CMT" ] && CMT="(a new issue was just opened — assess it)"
 THREAD=$(cat /tmp/thread.md 2>/dev/null); [ -z "$THREAD" ] && THREAD="(no prior comments)"
 DESC=$(jq -r --arg a "$NAME" '.[$a].desc' /tmp/agents.json)
-# Include each teammate's skills so an agent (esp. @pm) can route by capability — e.g. only
-# @senior/@lead hold node1-ssh, so a node1 task must not go to @junior. Skill *names* only; the
-# scoped how-to detail stays hidden per the permission.skill allow-list.
+# Include each teammate's registry skills so an agent (esp. @pm) can route by capability — e.g. only
+# skill-holders should get a task that needs that skill. Skill *names* only; the scoped how-to detail
+# stays hidden per the permission.skill allow-list. (Caller-provided skills from a repo's
+# .gitea/agent-skills/ are not in this roster — document that routing in the caller's AGENTS.md.)
 ROSTER=$(jq -r 'to_entries | map("- @\(.key): \(.value.desc) (vision: \(.value.vision); skills: \(.value.skills | if length>0 then join(", ") else "none" end))") | join("\n")' /tmp/agents.json)
 if [ "$VISION" = "true" ]; then CAP="You CAN read images attached to the issue."; else CAP="You CANNOT read images — you are a text-only model."; fi
 NOTE=""
@@ -32,25 +35,63 @@ if [ "$MODE" = "comment" ]; then
   obviously not needed; when in doubt, ask instead."
  if [ "$NAME" = "pm" ]; then
    ACTION="$ACTION
-   As PM you work in two phases and NEVER skip the approval gate:
-   PLAN — when the task is clear, present a SHORT plan naming which teammate should build it
-   (@junior for small/low-risk, @senior/@lead for complex, @qa to verify), then END by asking
-   '@ffaerber ready to start building? reply yes to proceed.' Do NOT include a DELEGATE line yet.
-   DELEGATE — ONLY after the maintainer has explicitly approved starting in the thread (a clear
-   'yes' / 'go' / 'proceed' / 'start building' answering your ready-to-build question) do you end
-   your reply with a 'DELEGATE: @<agent>' line to hand off.
-   Never present a plan and delegate on the same turn. If anything is unclear or needs a decision,
-   START your reply with '@ffaerber', ask specific questions, and do NOT delegate.
-   BREAKDOWN (for a feature too big for one PR): first PLAN — propose a milestone name and the list
-   of sub-tasks (title + one line each), then ask '@ffaerber create these N sub-issues? reply yes.'
-   Do NOT emit the block yet. ONLY after the maintainer approves, end your reply with EXACTLY:
+   As PM you ORCHESTRATE this issue from the ISSUE THREAD ONLY — you never read or comment on the PR
+   (keep your context on the issue). Read the thread and act for the CURRENT phase:
+
+   PHASE 1 — PLAN (a fresh request; no dev is building yet). Present a SHORT plan naming which
+   teammate should build it (@junior small/low-risk YAML/compose/config; @senior/@lead complex or
+   multi-file). Then END by asking '@ffaerber ready to start building? reply yes to proceed.' — do
+   NOT delegate yet. ONLY after an explicit 'yes'/'go'/'proceed' do you end a reply with a
+   'DELEGATE: @<dev>' line to hand off. Never plan and delegate in the same reply.
+
+   PHASE 2 — REVIEW (a dev has reported 'PR #<n> is ready'). Do NOT re-plan. Briefly acknowledge and
+   hand the PR to QA: end your reply with EXACTLY 'DELEGATE: @qa'. (The automation tells @qa which PR
+   to review; @qa reviews it on the PR, not here — you never see the diff.)
+
+   PHASE 3 — FINALIZE (@qa has reported the PR is approved / 'code OK'). Tell the issue creator it is
+   ready: e.g. 'PR #<n> is reviewed and ready to merge, @ffaerber.' Do NOT delegate and do NOT merge —
+   the human merges.
+
+   If anything is unclear or needs a decision at any phase, START your reply with '@ffaerber', ask
+   specific questions, and do NOT emit a marker. Mentioning a teammate in prose does NOT act — only a
+   DELEGATE line does.
+   BREAKDOWN (a feature too big for one PR): in PHASE 1, propose a milestone name and the sub-task
+   list, then ask '@ffaerber create these N sub-issues? reply yes.' ONLY after approval, end with:
   BEGIN_SUBTASKS
   milestone: <feature name>
   - <task title> :: <one-line description>
   - <task title> :: <one-line description>
   END_SUBTASKS
-   The automation creates the milestone + one sub-issue per line (each linked to this issue). It
-   does NOT auto-start any dev — the maintainer @mentions an agent on each sub-issue when ready."
+   The automation creates the milestone + one sub-issue per line (each linked here); it does NOT
+   auto-start any dev — the maintainer @mentions an agent on each sub-issue when ready."
+    if [ "$AUTOPILOT" = "true" ]; then
+      ACTION="$ACTION
+   AUTOPILOT MODE IS ACTIVE (this issue carries the 'autopilot' label) — it changes exactly TWO
+   things for you; everything else above is unchanged:
+   - PHASE 1: do NOT ask '@ffaerber ready to build?'. Present your SHORT plan AND end with a
+     'DELEGATE: @<dev>' line in the SAME reply. Only skip delegating (and ask @ffaerber) if the task
+     is genuinely ambiguous or unsafe.
+   - PHASE 3: do NOT ask the human to merge. When @qa has approved, end your reply with EXACTLY
+     'MERGE_PR' — the automation merges the PR and closes this issue. You are the ONLY agent that
+     merges, and only here."
+    fi
+  fi
+  if [ "$NAME" = "qa" ]; then
+    ACTION="$ACTION
+   As QA you are the REVIEWER — you NEVER edit code and NEVER merge. @pm points you at a PR; review
+   it: read the diff, drive the web app with your headless browser if there is a URL, and put your
+   detailed, specific recommendations ON THE PR (the automation posts your reply to the PR thread).
+   After actually verifying, end your reply with EXACTLY one of:
+   - 'APPROVE' — the change is correct and any CI is green. The automation records your verdict on the
+     issue and hands back to @pm (who tells the creator, or in autopilot merges). You do NOT merge.
+   - 'BOUNCE: @<dev>' — something needs changing. FIRST spell out, specifically and actionably, exactly
+     what to change (file, label, value, hostname, …), THEN end with the BOUNCE line naming who fixes
+     it (@junior / @senior / @lead — usually whoever built it). The automation sends the PR back and
+     re-verifies with you. After 3 rounds it stops and hands to @ffaerber — so list ALL problems at
+     once, not one at a time.
+   - 'HALT' — the problem is NOT something a dev can fix (the request is ambiguous / needs a human
+     decision). Hands back to @ffaerber.
+   Emit AT MOST one marker, and only after you have actually verified."
  fi
 else
  ACTION="You start on git branch '${BRANCH}', with git and push credentials already configured.
@@ -66,6 +107,10 @@ PROMPT="You are @${NAME}, a member of an AI dev team working on this Gitea repos
   YOUR CAPABILITIES: model ${MODEL}. ${CAP}
   ${NOTE}

+   Your reply is posted as a comment already attributed to you (@${NAME}) — your name and avatar are
+   shown by Gitea. Do NOT begin your reply with your own name, an '@${NAME}' header, or a '🤖/🔨 @you'
+   line; just write the content directly.
+
   TEAM ROSTER (who does what — hand off if a task isn't yours):
   ${ROSTER}

@@ -0,0 +1,118 @@
+#!/usr/bin/env bash
+# Set up the `gitea-admin` skill — instance administration for the @ops agent ONLY.
+# Emits an opencode Skill file under ~/.config/opencode/skills/ documenting how to create
+# orgs/users/repos, manage labels & secrets, and mint scoped per-user tokens via the Gitea API.
+#
+# The credential is SELF_TOKEN (BOOTSTRAP: currently an admin PAT — temporary). This skill doc is
+# written ONLY for @ops (gated on NAME) so the how-to never reaches other agents. NOTE: while
+# SELF_TOKEN is admin, every agent's process technically holds an admin credential in its env —
+# that is the bootstrap trade-off. Once @ops is minting scoped per-user tokens, SELF_TOKEN should be
+# narrowed and a dedicated admin token injected only for @ops.
+#
+# Required env (provided by the workflow step): NAME SELF_TOKEN
+set -eu
+
+[ "${NAME:-}" = "ops" ] || { echo "not @ops — skipping gitea-admin skill"; exit 0; }
+# The doc references $SELF_TOKEN (@ops's own admin token, present in the Run-agent step). This step
+# only writes the doc for @ops; permission.skill also denies the skill to every other agent.
+mkdir -p ~/.config/opencode/skills/gitea-admin && chmod 700 ~/.config/opencode/skills/gitea-admin
+cat > ~/.config/opencode/skills/gitea-admin/SKILL.md <<'SKILLET'
+---
+name: gitea-admin
+description: Administer this Gitea instance — create orgs, users, repos; manage labels & Actions secrets; mint scoped per-user access tokens; bootstrap a new repo with the agent caller workflow. Use for "create org X", "create repo Y", "add user Z", "give user W a token scoped to …", "set label set on …".
+domains: [gitea, admin, orgs, users, repos, secrets, tokens]
+tags: [gitea, admin, api, curl, bootstrap]
+---
+
+# `gitea-admin` Skill (operator / @ops only)
+
+Administer the Gitea instance via its REST API at `${GITHUB_SERVER_URL}/api/v1`, authenticated with
+`Authorization: token ${SELF_TOKEN}` (a site-admin token during bootstrap). Both env vars are
+already set. Work from the issue instructions; report what you did.
+
+## Golden rules
+- **NEVER print, echo, or paste a token, password, or secret value** — not in comments, not in logs.
+  Capture into a shell variable and immediately store it as a secret; report only that it was stored.
+- **ALWAYS confirm before anything destructive** (delete user/repo/org, remove a member). Post a
+  clear "reply `yes` to confirm deleting X" and stop; only act after the maintainer confirms.
+- Prefer the **least privilege** that satisfies the request when minting tokens.
+- Be idempotent where you can (check if the org/repo/label already exists before creating).
+
+## Create an organisation
+```
+curl -sS -X POST -H "Authorization: token $SELF_TOKEN" -H "Content-Type: application/json" \
+  "$API/orgs" -d '{"username":"acme","visibility":"private"}'
+```
+
+## Create a user, then mint a TAILORED token for them (least privilege)
+Admin creates the user with a password you generate; you then basic-auth AS that user (with the
+password you just set) to mint a scoped token, and store the token straight into a secret.
+```
+API="${GITHUB_SERVER_URL}/api/v1"
+PW=$(head -c 24 /dev/urandom | base64 | tr -d '/+=' | head -c 24)   # generated, never printed
+# 1) create the user
+curl -sS -X POST -H "Authorization: token $SELF_TOKEN" -H "Content-Type: application/json" \
+  "$API/admin/users" -d "$(jq -nc --arg u inter --arg e inter@ffaerber.duckdns.org --arg p "$PW" \
+     '{username:$u,email:$e,password:$p,must_change_password:false,source_id:0,visibility:"private"}')"
+# 2) mint a scoped token AS that user (pick the narrowest scopes needed)
+tok=$(curl -sS -u "inter:$PW" -H "Content-Type: application/json" -X POST "$API/users/inter/tokens" \
+      -d '{"name":"inter","scopes":["read:repository","write:issue"]}' | jq -r '.sha1')
+# 3) store the value in BOTH places (see "Secret storage" below) — never print $tok
+curl -sS -X PUT -H "Authorization: token $SELF_TOKEN" -H "Content-Type: application/json" \
+  "$API/orgs/gitea/actions/secrets/TOKEN_INTER" -d "$(jq -nc --arg d "$tok" '{data:$d}')"
+```
+Token **scopes** are groups of `read:`/`write:` on: `repository`, `issue`, `organization`, `user`,
+`package`, `notification`, `misc`, and (only for a privileged token) `admin`.
+
+## Secret storage — `gitea/secrets/.env` is the SOURCE OF TRUTH
+Every token/secret value MUST live in **`gitea/secrets/.env`** (private, readable only by @ffaerber and
+@ops) as a `KEY=value` line. That file is the master; the workflows only get a secret because `.env` is
+mirrored into the org Actions secrets. So whenever you mint, rotate, or re-scope a token you MUST do
+BOTH, in sync:
+  1. **`.env`**: `GET /repos/gitea/secrets/contents/.env` for its `sha`, add or replace the `KEY=value`
+     line, then `PUT` the updated base64 content with that `sha`.
+  2. **Actions secret**: `PUT /orgs/gitea/actions/secrets/{KEY}` with the same value (what runs use).
+When you DELETE a token, remove it from BOTH. Keep `gitea/secrets/README.md` (the table describing what
+each KEY is) up to date. Do NOT use `tokens.md` — the values live in `.env`. NEVER paste a token value
+into any issue/PR/comment/log; it only ever goes into `.env` and the Actions secret.
+
+## Change a user's token scope (the "update my token" flow)
+Tokens are immutable — you can't edit scopes. Re-mint: delete the old token and create a new one,
+then overwrite the stored secret.
+```
+curl -sS -u "inter:$PW" -X DELETE "$API/users/inter/tokens/<name-or-id>"     # needs the password again
+tok=$(curl -sS -u "inter:$PW" -X POST "$API/users/inter/tokens" -d '{"name":"inter","scopes":[…new…]}' | jq -r '.sha1')
+curl -sS -X PUT -H "Authorization: token $SELF_TOKEN" "$API/orgs/gitea/actions/secrets/TOKEN_INTER" -d "$(jq -nc --arg d "$tok" '{data:$d}')"
+```
+(If you no longer hold the user's password, reset it first via `PATCH /admin/users/{username}` with a
+new generated password, then re-mint.)
+
+## Actions secrets & variables
+```
+curl -sS -X PUT  -H "Authorization: token $SELF_TOKEN" "$API/orgs/{org}/actions/secrets/{NAME}"  -d '{"data":"<value>"}'
+curl -sS -X PUT  -H "Authorization: token $SELF_TOKEN" "$API/repos/{owner}/{repo}/actions/secrets/{NAME}" -d '{"data":"<value>"}'
+curl -sS -X PUT  -H "Authorization: token $SELF_TOKEN" "$API/user/actions/secrets/{NAME}" -d '{"data":"<value>"}'   # user-level
+```
+
+## Labels (repo or org-wide). Scoped labels (name `scope/value`) are mutually exclusive if `exclusive:true`.
+```
+curl -sS -X POST -H "Authorization: token $SELF_TOKEN" "$API/repos/{owner}/{repo}/labels" \
+  -d '{"name":"status/review","color":"1d76db","description":"…","exclusive":true}'
+curl -sS -X POST -H "Authorization: token $SELF_TOKEN" "$API/orgs/{org}/labels" -d '{…}'
+```
+
+## Bootstrap a new repo (create + wire it up for the agents)
+1. Create: `POST /orgs/{org}/repos` or `POST /admin/users/{user}/repos` (e.g. `{"name":"homepage","auto_init":true,"private":true}`).
+2. Add the standard label set (loop the labels above).
+3. Commit the standard caller so it gets the agents — `PUT /repos/{owner}/{repo}/contents/.gitea/workflows/ai-agent.yml`
+   with base64 `content`, `message`, `branch:"main"` (copy the exact caller from the `agents` repo README).
+4. Add the agent bot users as collaborators: `PUT /repos/{owner}/{repo}/collaborators/{username}` (`{"permission":"write"}`).
+5. Ensure the repo can run agents — the org must hold the runtime secrets (ANTHROPIC_API_KEY, SELF_TOKEN,
+   TOKEN_* , OLLAMA_URL, OLLAMA_CLOUD_API_KEY); set any missing via the secrets calls above.
+
+## Admin user management
+- Create: `POST /admin/users`. Edit: `PATCH /admin/users/{username}`. Delete: `DELETE /admin/users/{username}` (**confirm first**).
+- List: `GET /admin/users`.
+SKILLET
+chmod -R o=rX ~/.config/opencode/skills/gitea-admin
+echo "gitea-admin skill installed for @ops ($(wc -l < ~/.config/opencode/skills/gitea-admin/SKILL.md) lines)"
@@ -1,19 +1,13 @@
 #!/usr/bin/env bash
 # Set up `gitea-api` skill (let agents read/write issues, PRs, Actions across repos).
-# Mirrors the node1-ssh pattern: emit an opencode Skill file under
-# ~/.config/opencode/skills/ so any dev agent discovers the capability via OpenCode's
-# skill registry. The credential is the shared AGENT_TOKEN (a PAT whose scopes the
-# maintainer set at creation time — issue/repository/organization/misc read+write, cross-repo).
-# Only emitted when AGENT_TOKEN is actually present, so repos without it don't get a
-# broken skill. The token is passed via env and never inlined into shell.
+# Emits an opencode Skill file under ~/.config/opencode/skills/. The credential is SELF_TOKEN — the
+# RUNNING agent's OWN token (e.g. TOKEN_PM for @pm), present in the Run-agent step's env. So each
+# agent talks to Gitea as itself, with its own scopes. This step only writes the doc, so it always
+# emits; permission.skill decides which agents may actually load it.
 #
-# Required env (provided by the workflow step): AGENT_TOKEN
+# Required env (provided by the workflow step): (none — the token is in the Run-agent step)
 set -eu

-if [ -z "$AGENT_TOKEN" ]; then
-  echo "AGENT_TOKEN not set — skipping gitea-api skill"
-  exit 0
-fi
 mkdir -p ~/.config/opencode/skills/gitea-api && chmod 700 ~/.config/opencode/skills/gitea-api
 cat > ~/.config/opencode/skills/gitea-api/SKILL.md <<'SKILLET'
 ---
@@ -33,14 +27,14 @@ Use this skill to talk to the **Gitea REST API** (`${GITHUB_SERVER_URL}/api/v1`)

 ## How it works

-Calls go via `curl` with the header `Authorization: token ${AGENT_TOKEN}`. Both
+Calls go via `curl` with the header `Authorization: token ${SELF_TOKEN}`. Both
 `${GITHUB_SERVER_URL}` (the instance root, e.g. `https://git.example.com`) and
-`${AGENT_TOKEN}` are present in your environment. The API root is
+`${SELF_TOKEN}` are present in your environment. The API root is
 `${GITHUB_SERVER_URL}/api/v1`.

 ## What you're actually allowed to do — the token's scopes are the source of truth

-The shared `AGENT_TOKEN` was granted **read and write** on the `issue`,
+The shared `SELF_TOKEN` was granted **read and write** on the `issue`,
 `repository`, `organization`, and `misc` scope groups, **cross-repo** (any repo the
 token's account can see). That covers:
 - issues, PRs, comments, labels, milestones, reviewers (read + write)
@@ -64,9 +58,9 @@ in `agent.yml` exists to enforce.

 ## Never echo the token

-**Never print, log, or exfiltrate `AGENT_TOKEN`.** Do not pass it to `echo`, do not
+**Never print, log, or exfiltrate `SELF_TOKEN`.** Do not pass it to `echo`, do not
 include it in a comment, do not write it to a file. If you need to show a curl command,
-redact the header as `Authorization: token $AGENT_TOKEN`.
+redact the header as `Authorization: token $SELF_TOKEN`.

 ## Examples

@@ -77,9 +71,9 @@ All examples assume `API="${GITHUB_SERVER_URL}/api/v1"`.
 ```bash
 API="${GITHUB_SERVER_URL}/api/v1"
 # Get issue/PR #12 on repo owner/repo (a PR if the number is a pull; issues/PRs share one number space)
-curl -sS -H "Authorization: token $AGENT_TOKEN" "$API/repos/owner/repo/issues/12" | jq '{title,state,body,user:.user.login}'
+curl -sS -H "Authorization: token $SELF_TOKEN" "$API/repos/owner/repo/issues/12" | jq '{title,state,body,user:.user.login}'
 # Its comment thread
-curl -sS -H "Authorization: token $AGENT_TOKEN" "$API/repos/owner/repo/issues/12/comments?limit=100" \
+curl -sS -H "Authorization: token $SELF_TOKEN" "$API/repos/owner/repo/issues/12/comments?limit=100" \
  | jq -r '.[] | "### @\(.user.login):\n\(.body)\n"'
 ```

@@ -91,27 +85,27 @@ find the owner/repo for a `#N` in *this* repo, just use `${GITHUB_REPOSITORY}`.
 ```bash
 API="${GITHUB_SERVER_URL}/api/v1"
 # Recent runs on a repo
-curl -sS -H "Authorization: token $AGENT_TOKEN" "$API/repos/owner/repo/actions/runs?limit=10" | jq '.[] | {id,status,conclusion,head_branch,event}'
+curl -sS -H "Authorization: token $SELF_TOKEN" "$API/repos/owner/repo/actions/runs?limit=10" | jq '.[] | {id,status,conclusion,head_branch,event}'
 # Jobs for a run
-curl -sS -H "Authorization: token $AGENT_TOKEN" "$API/repos/owner/repo/actions/runs/$RUN_ID/jobs" | jq '.[] | {name,status,conclusion}'
+curl -sS -H "Authorization: token $SELF_TOKEN" "$API/repos/owner/repo/actions/runs/$RUN_ID/jobs" | jq '.[] | {name,status,conclusion}'
 # Logs for a job (returns a text/plain stream)
-curl -sS -H "Authorization: token $AGENT_TOKEN" "$API/repos/owner/repo/actions/jobs/$JOB_ID/logs"
+curl -sS -H "Authorization: token $SELF_TOKEN" "$API/repos/owner/repo/actions/jobs/$JOB_ID/logs"
 ```

 ### List repos across an org

 ```bash
-curl -sS -H "Authorization: token $AGENT_TOKEN" "$API/orgs/$ORG/repos?limit=50" | jq '.[] | .full_name'
+curl -sS -H "Authorization: token $SELF_TOKEN" "$API/orgs/$ORG/repos?limit=50" | jq '.[] | .full_name'
 ```

 ### Write: comment / label / close on another repo's issue (only when your task requires it)

 ```bash
-curl -sS -X POST -H "Authorization: token $AGENT_TOKEN" -H "Content-Type: application/json" \
+curl -sS -X POST -H "Authorization: token $SELF_TOKEN" -H "Content-Type: application/json" \
  "$API/repos/owner/repo/issues/12/comments" -d '{"body":"related to #N"}'
-curl -sS -X POST -H "Authorization: token $AGENT_TOKEN" -H "Content-Type: application/json" \
+curl -sS -X POST -H "Authorization: token $SELF_TOKEN" -H "Content-Type: application/json" \
  "$API/repos/owner/repo/issues/12/labels" -d '{"labels":["related"]}'
-curl -sS -X PATCH -H "Authorization: token $AGENT_TOKEN" -H "Content-Type: application/json" \
+curl -sS -X PATCH -H "Authorization: token $SELF_TOKEN" -H "Content-Type: application/json" \
  "$API/repos/owner/repo/issues/12" -d '{"state":"closed"}'
 ```

@@ -1,83 +0,0 @@
-#!/usr/bin/env bash
-# Set up read-only SSH alias `node1` (+ opencode skill so the agent actually knows about it).
-# 1) Writes the deploy key + an SSH config alias so the agent can run
-#    `ssh node1 <read-only cmd>` (matches the homelab opencode.json allowlist).
-# 2) Emits a `node1-ssh` opencode Skill file under ~/.config/opencode/skills/ so any
-#    downstream repo's dev agent discovers this capability via OpenCode's skill registry
-#    rather than having to trial against the permission allowlist. Only emitted when the
-#    swarm plumbing is actually wired for that caller (SWARM_HOST/SWARM_USER/SSH_PRIV_KEY).
-# All three secrets are passed via env and never inlined into shell — this shared workflow
-# runs in repos that don't have them and must not fail there.
-#
-# Required env (provided by the workflow step): SWARM_HOST SWARM_USER SSH_PRIV_KEY
-set -eu
-
-if [ -z "$SWARM_HOST" ] || [ -z "$SWARM_USER" ] || [ -z "$SSH_PRIV_KEY" ]; then
-  echo "swarm secrets not set in this repo — skipping node1 SSH alias + skill"
-  exit 0
-fi
-mkdir -p ~/.ssh ~/.config/opencode/skills/node1-ssh && chmod 700 ~/.ssh ~/.config/opencode/skills/node1-ssh
-# Write the private key with 600 perms; never echo its contents.
-printf '%s\n' "$SSH_PRIV_KEY" > ~/.ssh/agent_node1
-chmod 600 ~/.ssh/agent_node1
-# SSH config alias `node1` — last-match-wins in the homelab opencode allowlist
-# (`deny ssh *` + specific `allow ssh node1 …`), so the alias name is fixed.
-cat > ~/.ssh/config <<EOF
-Host node1
-    HostName $SWARM_HOST
-    User $SWARM_USER
-    IdentityFile ~/.ssh/agent_node1
-    IdentitiesOnly yes
-    StrictHostKeyChecking accept-new
-    ConnectTimeout 10
-EOF
-chmod 600 ~/.ssh/config
-echo "node1 SSH alias configured (host=$SWARM_HOST user=$SWARM_USER)"
-
-# Emit a reusable opencode Skill that surfaces the capability to downstream agents.
-# OpenCode's skill tool registers it via the <available_skills> block, so any dev agent
-# can discover "I am allowed to ssh node1" without trial-and-error against the allowlist.
-cat > ~/.config/opencode/skills/node1-ssh/SKILL.md <<'SKILLET'
---
-name: node1-ssh
-description: Read-only diagnostics on the swarm host via `ssh node1 …` — use when debugging a deploy or checking a running service.
-domains: [swarm]
-tags: [ssh, swarm, diagnostics, docker]
---
-
-# `node1-ssh` Skill
-
-Use this skill to run **read-only** commands against **node1** (the Docker Swarm host) when:
- A deploy failed and you need to inspect running services.
- You need to see a service's logs for debugging.
- You want to check the state of the stack on the swarm.
-
-## How it works
-
-Commands run via `ssh node1 <cmd>`. The SSH alias is configured in `${HOME}/.ssh/config`
-during this workflow (only when swarm secrets are configured for the caller repo).
-
-## What you're actually allowed to run — the allowlist is the source of truth
-
-This skill does **not** define which commands are permitted, and you must not assume a fixed
-list here. The single source of truth for exactly which `ssh node1 …` commands are allowed is
-the **caller repo's own OpenCode permission config** (e.g. `opencode.json` in the homelab repo:
-a `deny "ssh *"` with specific `allow "ssh node1 …"` entries, last-match-wins).
-
- Only read-only diagnostics are permitted; any write/mutating command on node1 is denied.
- The permission layer enforces this — if a command is not on the caller's allowlist it will be
-  blocked, regardless of what this skill or any other allowlist says.
- So: reach for `ssh node1 …` for read-only diagnostics, and treat the caller's `opencode.json`
-  `ssh node1` allow-entries as the authoritative list of what will actually run.
-
-## Example
-
-> The frontend returned a 5xx after a deploy.
->
-> Action (a read-only log inspection, subject to the caller's allowlist):
-> ```
-> ssh node1 "docker service logs --tail 100 --timestamps homelab_frontend"
-> ```
-SKILLET
-chmod -R o=rX ~/.config/opencode/skills/node1-ssh
-echo "opencode skill node1-ssh installed ($(wc -l < ~/.config/opencode/skills/node1-ssh/SKILL.md) lines)"
@@ -11,10 +11,26 @@ the loop guards.
 ## Golden rules
 - You may edit **any file**. **NEVER push to `main`, NEVER merge a PR** — all work goes on a branch
  and becomes a PR a human reviews and merges.
+  - **Narrow exception — `@qa` autopilot merge:** `@qa` (and only `@qa`) MAY merge a single PR **only**
+    when the linked issue carries the `autopilot` label, the PR is clearly correct, and any CI
+    checks are green. `@qa` triggers the merge by ending its reply with the `MERGE_PR` marker (the
+    workflow performs the merge + closes the issue). On **any** doubt or bug, `@qa` must NOT merge:
+    it ends with `HALT_AUTOPILOT` instead, which removes the `autopilot` label and returns the
+    issue to human control. No other agent may merge, and `@qa` may not merge without the label.
 - **Never print, exfiltrate, or invent secret values.**
 - Keep changes **minimal** and match the conventions already in the file you're editing.
 - Do the work on a **branch** — never paste code or diffs into the issue thread.

+## Autopilot (`autopilot` label)
+An issue labeled **`autopilot`** runs without the usual human checkpoints:
+- `@pm` plans **and** delegates in the same turn (skips the "ready to build? reply yes" gate).
+- After the dev's PR is opened, `@qa` is auto-triggered to verify it, and merges + closes on success
+  (see the QA merge exception above).
+- **Kill switch:** remove the `autopilot` label at any time. The label is re-read fresh at the
+  start of every run, so the next agent turn reverts to normal human-approval behavior. `@qa` also
+  removes the label itself whenever it halts on a bug or a failed merge.
+No label (the default) = today's behavior, unchanged.
+
 ## Branches & pull requests
 Start on `ai/issue-<N>`. Split independent changes into separate branches (one PR each). Commit and
 push incrementally. Do NOT open PRs yourself (automated). End your reply with the PR description
@@ -7,14 +7,33 @@ Shared **AI dev-team** workflow for Gitea Actions, reusable across repos. It giv

 | Agent | Model | Vision | Mode | Skills | Role |
 |-------|-------|:------:|------|--------|------|
-| `@pm` | `ollama-cloud/gemma4:cloud` | yes | comment | `gitea-api` | Product manager — research, plan, ask clarifying questions, and decide which dev should do the work. Comments only; never edits files. |
+| `@pm` | `ollama-cloud/gemma4:cloud` | yes | comment | `gitea-api` | Product manager & orchestrator — plans, picks the dev, hands finished PRs to `@qa`, reports back to the issue creator (autopilot: merges approved PRs itself). Issue thread only; never edits files, never reads the PR diff. |
 | `@junior` | `ollama-cloud/kimi-k2.7-code:cloud` | no | pr | — | Junior dev — small, low-risk changes (mostly YAML/compose/config). Text-only, cannot read images. Defers complex or image tasks to `@senior` or `@lead`. |
-| `@senior` | `ollama-cloud/glm-5.2:cloud` | no | pr | `gitea-api`, `node1-ssh` | Senior dev — complex, multi-file implementation (GLM-5.2 via Ollama Cloud, text-only). |
-| `@lead` | `anthropic/claude-opus-4-8` | yes | pr | `gitea-api`, `node1-ssh` | Tech lead — the hardest problems, architecture, and final calls. |
-| `@qa` | `ollama-cloud/minimax-m3:cloud` | yes | comment | `gitea-api` | QA — verifies things work. Drives a headless browser (Playwright) to open a URL/web app, click through it, screenshot, and report bugs or confirm behavior. Comments findings; opens no PRs. |
+| `@senior` | `ollama-cloud/glm-5.2:cloud` | no | pr | `gitea-api` | Senior dev — complex, multi-file implementation (GLM-5.2 via Ollama Cloud, text-only). |
+| `@lead` | `anthropic/claude-opus-4-8` | yes | pr | `gitea-api` | Tech lead — the hardest problems, architecture, and final calls. |
+| `@qa` | `ollama-cloud/minimax-m3:cloud` | yes | comment | `gitea-api` | QA / reviewer — reads the PR diff, drives a headless browser (Playwright) to verify behavior; recommendations on the PR, pass/fail verdict on the issue. Never edits code, never merges. |
+| `@ops` | `anthropic/claude-opus-4-8` | no | comment | `gitea-admin` | Gitea operator — administers the instance itself (create orgs/users/repos, labels, secrets, scoped per-user tokens, bootstrap repos). Comments only; never edits code. Confirms before destructive actions. |

-`agent.yml`'s agent registry is the source of truth for this mapping — if you change a model
-or an agent's skills there, update this table too.
+The registry `.gitea/workflows/scripts/agents.json` is the source of truth for this mapping — if you
+change a model or an agent's skills there, update this table too. (Repo-specific skills, e.g. a
+deploy-host SSH skill, live in the consuming repo under `.gitea/agent-skills/` — not in this table.)
+
+## How a task flows
+
+`@pm` orchestrates from the **issue thread**; the review happens on the **PR**; `@pm` never reads the PR
+(keeps its context small) and `@qa` never merges.
+
+1. **Issue opened** → `@pm` plans and names a dev, then asks the creator *"ready? reply yes"*
+   (with the `autopilot` label it skips the question and delegates immediately).
+2. **Dev builds** on `ai/issue-N`, a PR opens automatically, and the dev pings `@pm` on the issue.
+3. `@pm` hands the PR to **`@qa`**.
+4. `@qa` reviews **on the PR** — either recommendations + `BOUNCE: @dev` (dev fixes → `@qa`
+   re-verifies, direct loop, max 3 rounds) or `APPROVE`.
+5. On approval `@qa` posts the verdict **on the issue** → `@pm` tells the creator *"ready to merge"*
+   and a **human merges** — or, with the `autopilot` label, `@pm` merges and closes the issue itself.
+
+`@pm` is the only agent that ever merges, and only under the `autopilot` label (its kill switch:
+remove the label mid-flight and the next step reverts to human control).

 ### Per-agent skill scoping

@@ -35,10 +54,12 @@ it is the source of truth, and `agents` itself uses the same file:

 ```yaml
 name: ai-agent
-# Standard caller for the shared AI-agent workflow (ffaerber/agents). Copy this file VERBATIM into
+run-name: "ai-agent · #${{ github.event.issue.number }}"   # quotes required: bare # starts a YAML comment
+# Standard caller for the shared AI-agent workflow (gitea/agents). Copy this file VERBATIM into
 # any repo that should get the agents — it is identical in every repo. All logic + scripts live in
 # agents/.gitea/workflows/; scripts are fetched from @main at run time. The `jobs.agent` wrapper is
 # required: a reusable (workflow_call) workflow can only be invoked from a caller job, not top-level.
+# `run-name` titles each run by the triggering issue (e.g. "ai-agent · #42") in the Actions list.
 on:
  issue_comment:
    types: [created]
@@ -46,7 +67,7 @@ on:
    types: [opened]
 jobs:
  agent:
-    uses: ffaerber/agents/.gitea/workflows/agent.yml@main
+    uses: gitea/agents/.gitea/workflows/agent.yml@main
    secrets: inherit
 ```

@@ -73,11 +94,17 @@ points `$SCRIPTS` at it. Keep the workflow and its scripts moving together on `m
 |--------|-----|
 | `ANTHROPIC_API_KEY` | `@lead` (and `@pm`/`@senior`/`@qa` if on Claude) |
 | `OLLAMA_URL`, `OLLAMA_CLOUD_API_KEY` | local ornith / Ollama Cloud (gemma4, kimi-k2.7-code, glm-5.2, minimax-m3) |
-| `AGENT_TOKEN` | PAT (issue/repository/organization/misc read+write, cross-repo) — posts the delegation comment that fires the next agent **and** powers the `gitea-api` skill (read/write issues, PRs, comments, labels, and Actions runs/logs across any repo). Do not re-narrow its scopes without also removing the `gitea-api` skill. |
-| `TOKEN_PM`,`TOKEN_SENIOR`,`TOKEN_JUNIOR`,`TOKEN_LEAD`,`TOKEN_QA` | optional — post/commit as each agent's own Gitea user (falls back to the bot) |
+| `TOKEN_PM`,`TOKEN_SENIOR`,`TOKEN_JUNIOR`,`TOKEN_LEAD`,`TOKEN_QA` | **primary** — each agent's own Gitea-user PAT. The running agent gets *only its own* token (as `SELF_TOKEN`) so it posts, commits and comments as itself, and its `gitea-api` skill acts with its own scopes. Scopes: devs + `TOKEN_PM` carry `write:repository` (`@pm` is the only agent that merges, autopilot only); `TOKEN_QA` is `read:repository` + `write:issue` (reviews, never merges). |
+| `TOKEN_OPS` | `@ops` only — the admin PAT behind the `gitea-admin` skill (create orgs/users/repos, manage labels & secrets, mint scoped tokens). Injected into the agent process only when the agent is `@ops`. |

-`GITEA_TOKEN` is auto-provided. Tip: set these once at the **org** level so every repo inherits
-them via `secrets: inherit`.
+Each agent authenticates as **itself**: the Run-agent step selects that agent's `TOKEN_*` into
+`SELF_TOKEN` (never another agent's), and `publish.sh` uses the same token for the trigger comments
+that drive the flow (delegation, `@qa` hand-offs, bounces) and for `@pm`'s autopilot merge — the two
+things the built-in `GITEA_TOKEN` can't do (it won't start
+new runs, and a merge under it won't fire downstream deploys). So **every consuming repo must carry the
+per-agent `TOKEN_*` secrets** (org-level for `gitea/*`, user-level for `ffaerber/*`); there is no shared
+fallback token. `GITEA_TOKEN` is auto-provided (used for reads). Tip: set the `TOKEN_*` once at the
+**org / user** level so every repo inherits them via `secrets: inherit`.

 ## Also add to each consuming repo