agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/FixLab/.github/skills/fixlab-job-scoped-post-approval/SKILL.md

fixlab-job-scoped-post-approval

Skill0 starsChanged 59 days agoMITView on GitHub

Preserve explicit, revision-bound write consent when changing scoped POST or broad DEV approval, native tools, or job lifecycle.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    Use when changing POST consent, executor configuration, recovery, or snapshots.

    line 8
  2. Distinctive:

    Stop job-scoped approval after failed or ambiguous attempts.

    line 30
  3. Distinctive:

    Verify actual HTTP, SDK, worker, and browser behavior, not prompt text alone:

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

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

Job-scoped POST approval

Use when changing POST consent, executor configuration, recovery, or snapshots. Work from the FixLab repository root.

  • A saved capability preference is not write approval. Only fresh explicit checkbox confirmation creates the memory-only job/environment/revision grant.
  • Validate consent independently of toolApprovalMode. Enforce exact loopback Host and Origin for both ordinary and Allow-all jobs.
  • Bind the reviewed profile and authentication-helper revision before queueing. Configuration added later must not enlarge an earlier approval.
  • Preserve the grant through the native worker protocol. Never persist it in snapshots or inherit it on hold, recovery, restart, or another job.
  • Scoped POST approval retains endpoint/test-record checks. Separate broad DEV or PPE consent selects mode: dev-origin or ppe-origin on the same memory-only grant and worker protocol; it permits POST/PUT/PATCH/DELETE on exact reviewed dataSafety.devWrite or dataSafety.ppeWrite HTTPS origins without a record marker. Require fresh explicit consent for that environment; never inherit origins or grants across environments. Require its explicit hostname label and reject conflicting labels. Require separate consent, never generic Allow all tools or a recovered capability preference.
  • Both scopes retain existing authentication. Never disable browser guards or substitute a browser write. API-only/unit-only and explicit read-only contracts cannot be overridden.
  • Stop job-scoped approval after failed or ambiguous attempts. Approval is not evidence that a scenario passed.

Implementation: dashboard/dev-post.js, dashboard/copilot-session.js, dashboard/server.js, and dashboard/public/app.js.

Verify actual HTTP, SDK, worker, and browser behavior, not prompt text alone:

node --test test\dashboard-dev-post.test.js
node --test --test-name-pattern="POST checkbox write consent|DEV write checkbox|native executor forwards" test\dashboard-server.test.js
npm run test:e2e -- dashboard-readiness --grep "POST checkbox|DEV write checkbox"

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