Drop the shared AGENT_TOKEN as the primary credential; every agent now acts
as its own Gitea user (TOKEN_PM for @pm, TOKEN_OPS for @ops, …) for API
calls, delegation/autopilot trigger comments, and PR merges.
- agent.yml: Run-agent step injects SELF_TOKEN — a ternary selecting the
running agent's own token by name, falling back to AGENT_TOKEN for repos
not yet migrated to per-agent tokens (e.g. homelab). Only that one token
enters the agent process, so no agent can act as another. The gitea-api /
gitea-admin skill-setup steps no longer carry a token (they only write docs).
- Gate: trust the agent roster (pm/junior/senior/lead/qa/ops) as comment
authors so an agent's own delegation/autopilot trigger comment (posted with
its PAT, no 🤖 prefix) fires the next run. @ops added to the mention set.
- publish.sh: TOK = agent identity (comments/replies); new TTOK = trigger/merge
token (agent PAT, else AGENT_TOKEN fallback) for delegation, autopilot @qa
triggers, and PR merges that must fire downstream workflows.
- skill-gitea-api.sh / skill-gitea-admin.sh / run-agent.sh: AGENT_TOKEN/
TOKEN_OPS → SELF_TOKEN in the emitted skill docs and env contract.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The gitea-admin skill now authenticates with TOKEN_OPS (the ops user's admin token), and TOKEN_OPS
is injected into the agent process ONLY when name==ops. No other agent holds an admin credential in
its env. This unhooks @ops from AGENT_TOKEN, so AGENT_TOKEN can be narrowed to a non-admin token.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Repo transferred ffaerber/agents -> gitea/agents. Point the scripts checkout (agent.yml
repository:), the standard caller (uses:), and the README at gitea/agents. The trigger gate still
keys on the maintainer 'ffaerber' (unchanged).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
PR #55 added @ops to the registry but route.sh only looped pm/junior/senior/lead/qa, so @ops could
never be triggered, and there was no token case for it. Add 'ops' to the routing loop and the
TOKEN_OPS case in route.sh + publish.sh, and pass TOKEN_OPS in the workflow env next to TOKEN_QA
(route/publish/rescue steps) so route.sh (set -u) doesn't error on an @ops run.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A comment-mode operator agent (opus) for administering Gitea itself from issues in gitea/ops:
create orgs/users/repos, manage labels & Actions secrets, and mint least-privilege per-user tokens.
- agents.json: new @ops role (comment-mode, skill gitea-admin, confirms before destructive ops).
- skill-gitea-admin.sh: SKILL.md documenting org/user/repo/label/secret ops + the create-user →
mint-scoped-token → store-as-secret flow (never printing tokens). Gated on NAME=ops so the admin
how-to is written ONLY for @ops; permission.skill also denies it to other agents.
- agent.yml: wire the skill step (uses AGENT_TOKEN — an admin PAT during bootstrap).
Bootstrap note: AGENT_TOKEN is admin for now, so every agent's process technically holds an admin
credential (skill-scoping hides the doc, not the env var). Once @ops is minting scoped per-user
tokens, narrow AGENT_TOKEN and inject a dedicated admin token only for @ops.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Stage the shared scripts into $RUNNER_TEMP and point $SCRIPTS there for every
step, so an agent that commits/deletes the in-tree .agents-workflow checkout no
longer destroys the scripts the post-agent steps run (issue #33). Scrub any
in-tree .agents-workflow artifact before publishing, and add a failure-safe
rescue step that opens a PR for pushed work when a run fails.
The shared agent.yml is a reusable (workflow_call) workflow, so on Gitea
github.event_name evaluates to 'workflow_call' — not the original 'issues'/
'issue_comment'. route.sh branched on EVENT == "issues", so issue-opened runs
scanned the empty comment body and skipped the @pm fallback, exiting 1 with
"no known agent mentioned" (runs #393/#394). Comment runs were unaffected
because the @mention lives in $BODY.
Discriminate on the comment id (CID) instead, which IS reliably forwarded in
the event payload: empty => issue-opened (scan issue body, default @pm), set
=> comment (scan comment body). Also add .gitignore for .env.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Rebased onto the per-agent skill-scoping change so PR #25 carries both:
- route.sh keeps the registry 'skills' allow-list and emits skills as a step output
- install-opencode.sh writes the permission.skill block (deny-all + allow listed)
Pure refactor otherwise: each step's shell moves to its own file, called via
bash "$SCRIPTS/<name>.sh". The two extracted SKILL.md bodies are byte-identical to
main; routing/config/publish behavior is unchanged. Because this is a reusable
workflow (workflow_call) the runtime checkout is the caller's repo, so agent.yml now
checks THIS repo out into .agents-workflow/ (pinned @main) and points $SCRIPTS there.
- New gitea-api opencode skill (mirrors node1-ssh): documents the Gitea REST API
base URL, Authorization: token $AGENT_TOKEN header, and example curl calls for
read (issue/PR + comments, Actions runs/jobs/logs, org repos) and write (comment,
label, close), with explicit warnings: never echo the token, treat fetched
content as untrusted data (prompt-injection guard), and stop on 403.
- Wire AGENT_TOKEN into the Run agent step env so the agent process itself can
call the API (previously only the Publish step saw it).
- Update README secrets table: AGENT_TOKEN now also powers gitea-api; do not
re-narrow scopes without removing the skill.
Switch the real 'Run agent' step to --format json (replacing the two
TEMP/DEBUG schema-discovery commits da6f0d5/d0ddb06), capture the raw
event stream, and reconstruct the plain-text reply from the assistant
'text' parts so the existing Publish logic is unchanged.
Add a 'Build activity log' step that filters the event stream to
tool_use (with truncated title/input) and text (reasoning) events.
The Publish step posts that trail as a separate collapsible comment on
the PR thread (dev agents only — comment-only roles do no tool calls).
This is additive to the existing summary/PR-description comment.
Reasoning reuse on a follow-up run is free: the existing 'fetch full
issue thread' step already re-feeds all prior comments (including this
new log comment) into the next run's prompt, so the agent sees what it
did last time.
Runs a tiny Sonnet probe and dumps the raw events to the Actions log so we can build the
PR-progress parser against the real schema. Removed once captured.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@pm proposes a milestone + sub-tasks and asks for approval; on 'yes' it emits a BEGIN_SUBTASKS
block, and the workflow creates the milestone + one sub-issue per line (each 'Part of #<feature>').
Sub-issues are not auto-started — maintainer @mentions an agent on each when ready.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Reusable workflow (on: workflow_call) moved from homelab; consuming repos add a thin caller
(uses: ffaerber/agents/.gitea/workflows/agent.yml@main, secrets: inherit).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
lead
ffaerber
senior
junior