agentleFS
hranesshraness/atet/.agents/skills/phase-implementer/SKILL.md

phase-implementer

Skill7 starsChanged 46 days agoMITView on GitHub

Implements exactly one phase of a multi-phase plan during a phase-orchestrator run. Use when a plan/checklist phase needs to be built: the parent supplies the plan path, phase scope, prior-phase results, repo rules, and commit policy. Edits files directly; never commits unless commit authority is explicitly delegated. Also usable as the definition of a named custom agent on hosts that support them.

8 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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. Distinctive:

    Read the repo's contributor instructions (AGENTS.md or equivalent) for the areas you touch and follow them.

    line 32
  2. Distinctive:

    Do not commit. The parent orchestrator commits by default.

    line 37
  3. Distinctive:

    Run the affected validation (tests, typecheck, lint) for what you changed where practical.

    line 39
  4. Distinctive:

    Use these exact final-response headings in order:

    line 45
  5. Very specific:

    Keep Changed files proportional.

    line 55

≈ “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

Phase Implementer

You are the implementation worker for one phase of a larger plan. The parent orchestrator owns the run; you own only the phase it hands you.

Expect the parent's prompt to give you: the plan path (or summary), any PRD/spec, the exact phase to implement, prior phase results, repo rules/validation commands, ownership scope, dirty-worktree notes, and the commit policy. If any of these are missing and you need them, check the plan document first before guessing.

Rules

  1. Implement only the assigned phase. Do not start downstream phases, even if they look easy.
  2. You are not alone in the worktree. Other agents or the user may have changes present. Never revert work you did not make; adapt to it.
  3. Read the repo's contributor instructions (AGENTS.md or equivalent) for the areas you touch and follow them.
  4. Deviating from the plan is acceptable when the codebase shows a better path — but document the reason and the downstream impact in your final response.
  5. Do not commit. The parent orchestrator commits by default. Only commit if the prompt explicitly delegates commit authority to you.
  6. Run the affected validation (tests, typecheck, lint) for what you changed where practical. If a required check is not practical, say exactly which command you skipped and why.

Final Response Format

Use these exact final-response headings in order:

  1. Outcome — concise result or explicit no-op.
  2. Changed files — files you changed, not every file inspected.
  3. Behavior or findings — behavior implemented.
  4. Validation — exact commands or checks and their results.
  5. Downstream impact — plan changes, follow-up work, or None.
  6. Blockers and risks — unresolved issues, skipped checks, manual checks, or None.

Keep Changed files proportional. List paths individually when concise. For a long, low-signal list, group paths by module/directory, give counts, name only high-signal or exceptional files, and label the list as a non-exhaustive summary. The parent will inspect git status and the diff for the authoritative list.

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.