fulcra-agent-forge
Skill10 starsChanged 2 months agoMITView on GitHub
Bridge GitHub into a fulcra-agent-teams review flow: mirror PR state onto the team store as evidence, and auto-approve a review when its PR merges — so review status reflects the forge even when no human files a verdict.
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- coordinator-disciplineSkill
- fulcra-agent-atcSkill
- fulcra-agent-automationSkill
- fulcra-agent-cloud-coordinatorSkill
- fulcra-agent-continuitySkill
- fulcra-agent-directivesSkill
- fulcra-agent-durable-stateSkill
- fulcra-agent-healthSkill
- fulcra-agent-operatorSkill
- fulcra-agent-presenceSkill
- fulcra-agent-reconcileSkill
- fulcra-agent-reviewSkill
- fulcra-agent-rolesSkill
- fulcra-agent-tasksSkill
- fulcra-content-reviewSkill
- fulcra-fdeSkill
- fulcra-lab-resultsSkill
- map-our-teamSkill
- sealed-secretsSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Auto-verdict: when the PR merges, a verdicts/forge.md approval is written (reviewer forge) — the review tally then folds it like any …
- Very specific: line 35
All probes clean → run one mirror pass to fold current PR state into review evidence and sweep feedback (see Usage).
- Very specific: line 42
Run it ad hoc, or on the heartbeat alongside reconcile.
- Very specific: line 80
Only github.com/<owner>/<repo>/pull/<n> artifacts are mirrored.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Fulcra Agent Forge
Enhances fulcra-agent-review. When a review's artifact: is a
GitHub PR URL, the forge is the ground truth — this skill mirrors it onto the team store so
coord-engine review status reflects reality:
- Evidence: one idempotent shard per PR state transition
(
_coord/evidence/<slug>/state-<OPEN|MERGED|CLOSED>.md). - Auto-verdict: when the PR merges, a
verdicts/forge.mdapproval is written (reviewerforge) — the review tally then folds it like any reviewer.
Where to start — the re-entrancy probes
The forge is stateless — forge mirror is a full idempotent pass, so there is no mid-journey
resume; the probes are a preflight confirming you can mirror. Enter at the first probe that
fails (per docs/skill-quality-pattern.md); both probes are non-mutating (the mirror pass itself
is the only write, and it's idempotent):
| Probe (run in order) | Command | Passes when | If it fails, enter at |
| Engine + auth usable? | coord-engine doctor <team> | exits 0 and the last line is exactly doctor: healthy | fix engine/auth first (see fulcra-agent-reconcile) — do NOT mirror against a broken engine |
| GitHub reachable? | gh auth status | exits 0 (an authenticated gh is installed) | authenticate the GitHub CLI: gh auth login — without it forge mirror is a clean no-op (exit 0) and no evidence is written, so review status stays stale |
| Watching my authored PRs? | coord-engine needs-me <team> --agent <me> | a PR you authored or requested review on surfaces as a [FORGE] item (feedback is reaching you) | it isn't a swept target — register it: forge watch <team> <pr-url> --agent <me>, then sweep (see PR feedback lives on three surfaces) |
| Feedback swept? | coord-engine forge feedback <team> | exits 0 — a sweep pass over all three surfaces completed (new shards, if any, written) | authenticate gh first (the row above); an unauthenticated sweep is a clean no-op |
All probes clean → run one mirror pass to fold current PR state into review evidence and sweep feedback (see
Usage); re-run on your heartbeat alongside reconcile.
Usage
coord-engine forge mirror <team> # one pass over all PR-backed reviewsRun it ad hoc, or on the heartbeat alongside reconcile. Requires the GitHub CLI (gh) authenticated;
without it the command is a clear no-op (exit 0) — the skill degrades, nothing breaks. A gh that is not the
GitHub CLI (its gh --version does not begin gh version, e.g. a built-in client that answers only gh api)
counts as no CLI: forge mirror and forge feedback take the same no-op and say why on stderr.
PR feedback lives on three surfaces
A PR's feedback is scattered across three GitHub API surfaces, and a poll that reads only one misses the rest:
- Formal reviews —
gh pr view <url> --json reviews(APPROVE / CHANGES / COMMENTED verdicts). - Inline review comments —
gh api repos/<owner>/<repo>/pulls/<n>/comments(diff-anchored threads; a distinct REST shape). - Conversation comments —
gh pr view <url> --json comments(the PR timeline).
The motivating failure mode: a watch prompt that polled conversation comments alone saw an empty timeline
and reported "no feedback" while a formal CHANGES review and inline comments sat unread — a real review
went unseen this way. forge feedback <team> (sweep-only) and forge mirror <team> (which now sweeps too)
hit all three surfaces every pass, mirroring each item to an idempotent shard keyed by its GitHub node
id, so a re-run converges rather than duplicating. Items authored by the PR author are skipped as
self-comments — and when the PR author can't be resolved (the reviews call failed), self-skip can't apply,
so the sweep notes it on stderr.
Watch PRs the review flow doesn't already cover. A PR that backs a review artifact is swept automatically; an authored or upstream PR with no review doc is not, until you register it:
coord-engine forge watch <team> <pr-url> [--agent <responsible>] # register; default responsible = caller
coord-engine forge unwatch <team> <pr-url> # deregister
coord-engine forge feedback <team> # sweep all three surfaces nowDiscovery reads the review doc's of: first, falling back to artifact:; a watched PR joins that same
target set.
The needs-me guarantee. Swept feedback on a PR you're responsible for surfaces as a [FORGE] item in
needs-me and briefing for that agent, and persists until you ack it — it does not age out. Acking is
two steps (non-obvious, so spell it out):
coord-engine needs-me <team> --agent <me> --json— eachforge-feedbackrow carries anitemsarray; those stems are the ack ids.coord-engine inbox <team> --ack <item-id> --agent <me>— ack each stem. A later sweep that finds a new node id writes a new shard, which re-surfaces — you silence only what you've already seen.
Notes
- Only
github.com/<owner>/<repo>/pull/<n>artifacts are mirrored; other artifacts are skipped silently. - A failing
ghcall leaves the review untouched (never fabricates state). - The forge approval doesn't override human verdicts — a human
changesstill blocks (CHANGES dominates).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

