coordinate
Skill9 starsChanged yesterdayMITView on GitHub
Run a milestone or patch release as the coordinator of a team of pohunek agent sessions: dispatch issues, review every PR head, enforce the merge policy, keep CI and the agents moving, and drive the release to a published, verified tag. Use when the owner asks you to coordinate, manage, or finish a milestone or release with several agents rather than implement it yourself.
23 other projects use a version of this.
Adopted by
Most recently taken up by
- cayden970207/thoththeir own version, first seen Nov 15, 2026
- jsboige/CoursIAtheir own version, first seen Nov 15, 2026
- ryanportfolio/HarnessFirmware.comtheir own version, first seen Nov 8, 2026
- ryanportfolio/winuse-mcptheir own version, first seen Nov 8, 2026
- bftelman/skillstheir own version, first seen Nov 4, 2026
- thanoslabs/skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use addskill, apply-firmware and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
ryanportfolioSkilladdskill
Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.
Also in 6 projects that use this
ryanportfolioSkillapply-firmware
Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.
Also in 6 projects that use this
- +10 more from ryanportfolio
Other versions23 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 23
- first-fluke/fullstack-starter★ 226same name
- swyxio/skills★ 199same name
- jsboige/CoursIA★ 17same name
- cayden970207/thoth★ 8same name
- gao-xh/multi-agent-protocol★ 4same name
- AcKeskin/contexture★ 2same name
- bftelman/skills★ 2same name
- combinaut/ai-agent-orchestration★ 2same name
- leosimini/keelokit★ 2same name
- revealui-studio/revskills★ 2same name
13 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ms-rustSkill
- contributeSkill
- deliver-issueSkill
- gatesSkill
- github-workflowSkill
- merge-advanceSkill
- milestone-reviewSkill
- milestoneSkill
- plan-phaseSkill
- pr-handoffSkill
- releaseSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 8 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 22 edited versions we read keep these.
8
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
Never infer it. A release agent may require the owner's confirmation in its own session.
- Distinctive: line 35
Verify effects, never intent: Before you report a merge, a closed issue, a green run, a tag or a published release, re-query GitHub or the …
- Very specific: line 38
Security constraints apply to every agent: no secret values in any output, brief, scratch file or comment.
- Distinctive: line 67
When tasks are created faster than they close, freeze intake: only red-CI flakes and high-severity regressions of the milestone enter, and …
- Distinctive: line 74
Brief: every worker with the four-block protocol (what you know, where to start, what to do, constraints).
- Distinctive: line 94
After fixes, review only the delta (git range-diff after a rebase).
- Very specific: line 110
Semantic check: if main moved since the PR's CI base, cargo check --workspace --all-targets --all-features plus fmt on the PR merged with …
- Very specific: line 134
Never rerun the jobs of a fork head.
- Very specific: line 144
After every pohunek session input, re-read the screen 20–60 seconds later: the agent may show a menu or a question that needs an answer.
- Distinctive: line 147
When an agent goes idle, confirm it has a watcher that wakes it on its next event.
- Very specific: line 149
Context: every 15 minutes read each worker's ctx … N% bar from pohunek session screen.
- Distinctive: line 177
After publishing: verify the release (not a draft, asset count, a checksum spot check, catalog versions), attach the notes, comment the …
- Distinctive: line 189
When something slips, say why in one line, what you changed, and the new ETA.
“Common” is measured: kept by at least 6 in 10 of the 22 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
coordinate — run a milestone or release with a team of agents
The coordinator does not program. It decides within the owner's
authorizations, keeps every worker busy on the critical path, verifies every
claim against the system of record, and gets the release published. Workers
implement through the milestone, deliver-issue, gates and pr-handoff
skills; the release itself goes through the release skill. This skill is the
loop around them.
Role and boundaries
- Coordinate, do not implement. Your tools are cross-session messages,
pohunek session screen|input(--host <name>for a remote host),ghqueries, issue/PR comments, milestone edits, and read-only review subagents. Code changes go to a worker with a brief. - Never block on questions. Decide within the authorizations you have and keep the work moving. Ask the owner only for a release, an irreversible step, or a product decision that is genuinely theirs; then give options with a recommendation in plain text, and keep the team working while you wait.
- Releases and tags need the owner's explicit approval for that version. Never infer it. A release agent may require the owner's confirmation in its own session; relay the owner's exact words, or, when the owner tells you to, type the confirmation into that session labelled as typed by you on their instruction.
- Verify effects, never intent. Before you report a merge, a closed issue, a green run, a tag or a published release, re-query GitHub or the host and confirm it. Every status line to the owner names the SHA, run id or URL.
- Security constraints apply to every agent: no secret values in any
output, brief, scratch file or comment; PR bodies use only
Refs #N; noCo-Authored-By; kill processes only by exact, verified PID, never by name or pattern; never touch the owner's primary checkout or agent homes on a host. If a secret reaches your context, stop, tell the owner, recommend rotation.
Setup
- Shared context file
/tmp/agent-context-<milestone>.md: roster and ownership, the merge policy below, intake rules, dispatch rules, and oneCURRENT:line you rewrite at every state change (freeze on/off, release candidate SHA, broken tooling such as a down review bot). Point every brief at it. - Roster. One worker per open issue or concern; one CI/release owner; a worker on a remote host (for example macOS) for platform evidence.
- Watchers (each as a Monitor or a background loop that exits on the
event; re-arm on expiry):
- a CI fail-fast watcher that cancels a PR or dispatch run only for a failed job of the cancelling set whose failure is not tagged as infrastructure (queued and in-progress runs, skip a branch on request);
- a state watcher for the PRs on the critical path (head, checks, dispatch,
main), emitting only changes; - an idle subscription on each worker (one-shot; re-subscribe after each notice);
- a context watcher (see Agent supervision).
Intake control
When tasks are created faster than they close, freeze intake: only red-CI flakes and high-severity regressions of the milestone enter, and only with your approval. Review leftovers go to one next-milestone checklist issue per PR. Move anything else to the next milestone with a one-line reason.
Work loop
- Brief every worker with the four-block protocol (what you know, where to start, what to do, constraints). For risky changes (recovery, trust, persisted state, packaging) require a written design first and review it before any code: decide its open questions explicitly.
- Push discipline: local gates and a local Opus subagent review before every push; one push per review round; no pushes while CI runs unless you ask.
- Review every PR head with an independent Opus (high effort) review
session, the gate of
deliver-issuePhase 5. That session runs two to four read-only reviewer subagents in parallel, one per commit or per concern, with a shared/tmp/agent-context-review-<pr>.mdand a confidence threshold of 80. It is a fresh session that did not author the change, with a review-only briefing, and it posts one comment from the maintainer account that carries theopus-pr-review:v1marker for the exact head and names the verdict. When the author disputes a MEDIUM finding with evidence on the PR, the coordinator rules on it as a PR comment (the maintainer when there is no coordinator). The manager (coordinator or operator) then starts the fresh review at the same head that records the ruling in itsmediumcount, or the delivering agent does when no manager is named (deliver-issuePhase 5 step 1). Exactly one party starts it, and its briefing links the ruling comment. After fixes, review only the delta (git range-diffafter a rebase). A LOW finding is filed as an issue instead of fixed; say so in the comment. - Batch findings from all reviewers into one fix push. Prefer one PR with ordered commits over a stacked train when the release clock matters, and review it commit by commit.
Merge policy
- Merge when the PR CI is green at the exact head, the
opus-pr-review:v1marker byzajcanames that head withhigh=0andmedium=0, and the tier=main dispatch is green where the dispatch rules require one (release workflows, packaging, SDK, dependencies, protocol window). A fork head is never dispatched; the maintainer re-creates the change on its own branch and dispatches that, or relies on a later run onmain(the post-merge run for the main tier; the scheduled nightly run or atier=nightlydispatch for the release rehearsal and the other nightly-only jobs; Fork heads in.agents/instructions/verification.md). - Semantic check: if
mainmoved since the PR's CI base,cargo check --workspace --all-targets --all-featuresplus fmt on the PR merged withmainbefore merging. - Atomic merge: fetch, compare
origin/mainwith the checked base, andgh pr merge --match-head-commit <head>in one command that refuses whenmainmoved. - Close the issue on merge with the PR CI run id (and dispatch id).
- On the release clock, fire the dispatch for a branch of this repository in
parallel with PR CI and cancel the other on a real failure. A delta
dispatch (
delta: true) only reuses green legs of same-tree runs and is evidence throughscripts/ci-evidence's union, never on its own. A docs-only delta after a green dispatch keeps that dispatch as evidence (verify the delta withgit diff --name-only). - Merge without pausing for a
mainrun: pushes tomaindrain, so every started main run completes and reports a verdict (#1209). A redmainrun is top priority.
CI and GitHub hygiene
- Cancel superseded runs on the critical path's runners when their failures
are already known. Never cancel a
mainrun only because a newer merge landed: the drain depends on each started main run completing. - A transient registry stall (an optional npm platform package skipped, a
pinned sha mismatch right after a stalled
npm ci) may be rerun withgh run rerun --failedat most twice; anything else stops for a diagnosis. Never rerun the jobs of a fork head; only the maintainer's approved, read-onlypull_requestrun applies. - Rate limits: repeated 403s mean someone is polling hard. Find the
process (
psforgh run|pr|apiloops), verify its command line and age, and stop a clearly runaway loop by its exact PID; ask workers to poll at most every 5 minutes.gh api rate_limitcan understate an exhausted primary quota.
Agent supervision
- After every
pohunek session input, re-read the screen 20–60 seconds later: the agent may show a menu or a question that needs an answer. Keep remote inputs under about 400 characters; split longer ones. - When an agent goes idle, confirm it has a watcher that wakes it on its next event; otherwise give it the next step at once.
- Context: every 15 minutes read each worker's
ctx … N%bar frompohunek session screen; when an idle worker is at about 40% or more, send/compact(at most once per 20 minutes per worker). Report a failed compaction (for example an exhausted account limit) once, not in a loop.
Release
- Merge freeze from the last milestone merge to the published release.
- Fresh clean clone for the release; never the owner's checkout.
- Rehearse the real release tree before GO: in a throwaway worktree, apply
exactly what the release commit will change (fold the changelog fragments,
bump the version, refresh the lock), then run the full gate set on that
tree,
scripts/ci-evidenceread-only against the candidate's own runs (a delta dispatch's union with its recorded source run counts), and thescripts/release --dry-runwith a no-writes check. A dry run alone does not see a folded tree or renamed CI jobs. - Notes: draft from the changelog fragments, keep a draft marker the runner refuses until the last merge, state limits honestly (verified versus accepted by policy), and carry still-open known issues.
- GO names the exact
mainSHA and the notes file. Run the nightly evidence in parallel with the main evidence; a wrapper reruns the release script only on the evidence timeout or a rate limit and stops on any other failure. - A failed release workflow after the tag: rerun the failed jobs once; a second identical failure is a real defect, so stop, diagnose (diff the passing rehearsal logs against the failing release logs, then probe the hypothesis on a runner), fix, and release a new patch version rather than moving a pushed tag.
- After publishing: verify the release (not a draft, asset count, a checksum spot check, catalog versions), attach the notes, comment the released-in line on the completed issues, close the milestone, lift the freeze, and tell every agent.
- Dogfood the upgrade on the owner's host when asked: run the update,
read the preflight, explain every at-risk session before accepting a loss,
then
pohunek doctor, and file every friction point as an issue.
Talking to the owner
- Lead with the state and the next ETA; use a small table for multi-step timelines; give the realistic range and what can move it.
- When something slips, say why in one line, what you changed, and the new ETA. Own coordination mistakes plainly and record the lesson.
- A decision request gives two or three options with a recommendation and the cost of each.
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.

