agentleFS
Sign inStart free
blauwtjeblauwtje/exo/skills/gate/SKILL.md

gate

Skill1 starsChanged 53 days agoMITView on GitHub

Use when a plan's tasks are landed and its branch needs the gate before a pull request: the scripted checks, the branch review and its repairs. Not for landing a task (build) or a change with no plan.

32 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use new, checkpoint and 8 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.
  • codebycoreySkill

    new

    Start a new change with a proposal. Use when starting a feature, creating a proposal, or beginning planned work.

    Also in 3 projects that use this

  • genomewalkerSkill

    checkpoint

    Save a checkpoint of task status, decisions, active files, and next steps

    Also in 3 projects that use this

  • VercelSkill

    investigate

    Investigate an issue report, or analyze the constraints of a proposed change, with strict, evidence-driven diagnosis.

    Also in 3 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 4 projects that use this

  • GitHubSkill

    refactor

    Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 6 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 30 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    No plan file → end the turn: ask for its path and name build's no-plan route.

    line 17

“Common” is measured: kept by at least 6 in 10 of the 30 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Gate

The gate readies a branch for a pull request.

The loop

  1. Run the gate. node "${CLAUDE_SKILL_DIR}/scripts/gate-step.mjs" --plan <plan path> --root <checkout> --base <base> first. Read only its STEP, LOG, NEXT, DECIDE lines, no log file.
    • Then in one message: the full run in the background and step 2's dispatch; end the turn, no ScheduleWakeup, Monitor or sleep. A dispatched agent runs it in the foreground, timeout 600000.
    • No plan file → end the turn: ask for its path and name build's no-plan route; hand-run no check or ship.
    • SKIP, WARN, FIX-ONLY, SESSION, SELF-HOSTED → references/gate-lines.md.
    • On FAIL or UNPLANNED, end the turn with its report, rerunning nothing.
  2. Review the branch. Reviewer none: skip the dispatch, still merge.
    • Dispatch exo:review-branch per DISPATCH Branch in one message, starting exo-kind: review-deep unless the line has none, its fields and Read: changed files.
    • For a branch with many changed files, print the tree from changedFileTree in lib/draw.mjs first, so the reviewer sees the shape before reading.
    • Then run gate-step.mjs --after review with those flags and a --report <path> per report; follow its NEXT lines.
    • On a CODEX offer line, ask once for a codex exec review of plan and diff, into findings.
    • --land → skip.
  3. Repair the findings. FINDINGS with fix=1 or more, or concern=1 or more, goes to the exo:build-task agent with exo-kind: fix-review, no model override, the dispatch line and ../build/review-fixer-prompt.md by path.
    • One exo:build-task per CLUSTER line, in parallel, each with only its findings, concern ones too.
    • With fix=0 and concern=0, go to step 4: no fixer dispatch, rerun or fix commit.
    • Else read references/repair.md.
  4. Offer the finish. End on ship, unless a request or plan rules out a push; then say nothing left the machine.
    • --land → pass --land to ship.

References

FileRead it when
references/review-rules.mdBLOCKED return or resume.
references/triage.mdStep 2.
references/repair.mdStep 3.
references/gate-lines.mdStep 1.
references/plan-checks.mdNever.
../../lib/references/closing.mdFinal message.
references/review.mdMode review.

Report: REPORT gets Changed, chores, report, note findings. Message: the report rule, three lines: REPORT path, question findings, one decision: FAIL, else question, else ship.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free