agentleFS
M-BajalanM-Bajalan/kibsu-lab/skills/planner/SKILL.md

planner

Skill0 starsChanged 31 days agoMITView on GitHub

How multi-step work gets planned and recorded in this repository before execution starts. Produces a phased plan file that the gate skill can check off, phase by phase.

32 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use executor, reviewer and 5 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.
  • MooseDesign1Skill

    executor

    Main executor agent. Triggered by /executor, or natural language such as: "build this feature", "execute the feature", "start building", "map the codebase", "scan the code", "resume building", "continue the build", "dev status", "where are we on development", "what's built". Do NOT trigger for /planner, /plan:project, /plan:feature, /plan:status, /product-designer, /pd:*, /ds-designer, /ds-*.

    Also in 3 projects that use this

  • MicrosoftSkill

    reviewer

    ASP.NET Core ハンドブックの記事をレビューする。Use when: 記事をレビューする、ドキュメントを校正する、コードレビューする、PRをレビューする。技術ドキュメントのレビュー、品質チェック、校正。

    Also in 5 projects that use this

  • JohnJBorenSkill

    debugger

    Systematic debugging workflows, root cause analysis, and troubleshooting patterns

    Also in 3 projects that use this

  • JetBrainsSkill

    review-plan

    Manually re-run the autonomous plan review (Phase 2 — consistency + structural). The same review runs automatically as the first phase of /execute-tracks; this command is for re-runs after inline replanning or whenever the plan needs explicit re-validation. TRIGGER when: user asks to re-validate the plan after inline replanning; user requests explicit plan review outside /execute-tracks. SKIP: /execute-tracks already running State 0 in this session (autonomous Phase 2 path will fire) — do not double-run.

    Also in 3 projects that use this

  • tesla0225Skill

    orchestrator

    Issue/要件を受けたら分解→担当割当→実装→検証→統合を回す手順。未整備なら /repo-init でbootstrap。

    Also in 4 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Create docs/plans/<YYYY-MM-DD>-<slug>.md with this shape:

    line 21
  2. Distinctive:

    Every phase names its own verify command and expected exit code before the phase starts -- naming the proof after the change is how a wrong …

    line 39
  3. Very specific:

    Do not start Phase 2 until Phase 1's verify command has actually been run and its exit code checked.

    line 45
  4. Distinctive:

    If a phase's done-state cannot be checked by a command (an exit code, a diff, a file that must exist), that is a planning defect: redesign …

    line 51
  5. Very specific:

    When every phase's box is checked and every verify command has actually been run (not assumed), log the change per …

    line 58

“Common” is measured: kept by at least 6 in 10 of the 27 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

planner

When to use this

Any task with 3 or more distinct steps, or any task that touches more than one file under tools/, skills/, or docs/. A one-line fix does not need a plan file -- just make the change, verify it, log it (skills/change-log/SKILL.md).

Step 1 -- write the plan file

Create docs/plans/<YYYY-MM-DD>-<slug>.md with this shape:

# Plan: <name>

**Goal:** <one line -- what "done" looks like>
**Verifier:** <exact command that proves it, e.g. `python tools/check_task.py T1`>

## Phase 1: <name>
- [ ] Task
- [ ] Task
**Verify:** <command> -> expected exit <N>

## Phase 2: <name>
- [ ] Task
**Verify:** <command> -> expected exit <N>

Every phase names its own verify command and expected exit code before the phase starts -- naming the proof after the change is how a wrong fix gets reported as a right one.

Step 2 -- work one phase at a time

Do not start Phase 2 until Phase 1's verify command has actually been run and its exit code checked. Check off each task box (- [ ] -> - [x]) only after its own verify step passed, not when you believe it should pass.

Step 3 -- STOP on ambiguity

If a phase's done-state cannot be checked by a command (an exit code, a diff, a file that must exist), that is a planning defect: redesign the phase into something checkable, or say plainly that this step is not machine-checkable and needs a human read before the plan continues. Never soften a checker to make an unclear phase pass.

Step 4 -- close the plan

When every phase's box is checked and every verify command has actually been run (not assumed), log the change per skills/change-log/SKILL.md and update docs/STATE.md's row for the track this plan touched.

Checklist before you say "planned"

  • Does every phase name an exact verify command and expected exit code?
  • Is there at least one phase, or was a single-file change correctly routed to skills/change-log/SKILL.md instead of a plan file?
  • Is the plan file saved at docs/plans/<date>-<slug>.md?

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.