agentleFS
insapption-projectsinsapption-projects/claude-agent-team-starter/.claude/skills/plan-feature/SKILL.md

plan-feature

Skill1 starsChanged 8 months agoMITView on GitHub

Produces a structured implementation plan for a feature, update, or bug fix after reading reference files. Operates in read-only Plan Mode — no files are written. Requires lead approval before implementation. Step 3 of the dev-workflow.

  • Reads credentials

30 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use explore, review and 4 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.
  • genomewalkerSkill

    explore

    RLM-style recursive memory exploration - dynamically navigate the memory graph

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 5 projects that use this

  • DockerSkill

    review-pr

    Review one or more incoming Docker documentation pull requests as a maintainer. Independently validate technical claims, assess editorial fit and information architecture, choose a verdict, and draft exact inline or PR-wide feedback behind a confirmation gate. Use for requests such as "review PR 123", "is this PR correct?", "does this information belong here?", "validate this PR", or "help review backlog PRs". Do not use to maintain or fix a PR you own; use maintain-pr for that.

    Also in 3 projects that use this

  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 3 projects that use this

  • OpenAISkill

    systematic-debugging

    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

    Also in 3 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

11 rules. 0 are common, 7 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    If reference context is missing, invoke /read-references first

    line 28
  2. Distinctive:

    Read any file on disk

    line 33
  3. Very specific:

    Run grep, find, cat to explore the codebase

    line 34
  4. Distinctive:

    Ask the lead clarifying questions

    line 35
  5. Distinctive:

    Write, edit, or delete any file

    line 38
  6. Distinctive:

    Run migrations, artisan commands, or npm scripts

    line 39
  7. Distinctive:

    If the task is ambiguous, ask ONE clarifying question and wait for the answer before proceeding.

    line 58
  8. Very specific:

    Always include references/{relevant_map}.md as a MODIFY entry

    line 117
  9. Distinctive:

    If a migration is needed, list it FIRST

    line 119
  10. Very specific:

    Never include vendor/, node_modules/, .env files

    line 120
  11. Distinctive:

    Do NOT proceed to implementation until the lead explicitly approves.

    line 164

“Common” is measured: kept by at least 6 in 10 of the 29 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

Skill: /plan-feature

Usage

/plan-feature "{task_description}"

Examples:

/plan-feature "add product filtering by category on the listing page"
/plan-feature "fix cart total not updating when quantity is changed"
/plan-feature "refactor order service to extract coupon logic"

Prerequisites

  • /read-references must have been executed in this session
  • If reference context is missing, invoke /read-references first

Mode: READ-ONLY

In this step you MAY:

  • Read any file on disk
  • Run grep, find, cat to explore the codebase
  • Ask the lead clarifying questions

You MUST NOT:

  • Write, edit, or delete any file
  • Run migrations, artisan commands, or npm scripts
  • Make any git operations

Planning Process

Phase 1: Task Analysis

Restate the task in your own words to confirm understanding:

TASK UNDERSTOOD:
Type        : feature | update | fix
Description : {restatement in 1–2 sentences}
Technology  : laravel | react | react-native | frontend | mixed
Complexity  : low | medium | high (justify in 1 sentence)

If the task is ambiguous, ask ONE clarifying question and wait for the answer before proceeding.


Phase 2: Impact Analysis

Using the reference files and codebase exploration, identify every area affected by this task:

IMPACT ANALYSIS:
─────────────────────────────────────────
Database changes?    : yes / no
  If yes → tables: [list], type: migration / seed / both

Backend changes?     : yes / no
  If yes → routes / controllers / services / repositories / models

Frontend changes?    : yes / no
  If yes → pages / components / hooks / stores / services

Mobile changes?      : yes / no
  If yes → screens / navigators / services

Config/env changes?  : yes / no
  If yes → [specify files and keys — NEVER commit actual values]
─────────────────────────────────────────

Phase 3: Implementation Plan

List every file to be created or modified. For each file:

📝 CREATE  src/services/ProductFilterService.php
   → New service class. Methods: filter(array $criteria): Builder
   → Called by: ProductController@index

✏️  MODIFY  app/Http/Controllers/ProductController.php
   → Inject ProductFilterService. Update index() to accept filter params.
   → No other methods touched.

✏️  MODIFY  references/{relevant_map}.md                 ← ALWAYS include the affected reference map(s)
   → Reflect the implementation so future tasks start from fresh project maps.

Format each entry as:

{icon} {CREATE|MODIFY|DELETE}  {file_path}
   → {what changes and why, 1–2 lines}
   → {dependencies or callers, if relevant}

Icons: 📝 = new file, ✏️ = modify, 🗑️ = delete

Rules for the file list:

  • Always include references/{relevant_map}.md as a MODIFY entry
  • List files in dependency order (models before services before controllers)
  • If a migration is needed, list it FIRST
  • Never include vendor/, node_modules/, .env files

Phase 4: Risk Assessment

RISK ASSESSMENT:
──────────────────────────────────────
Overall risk    : low | medium | high
Breaking change : yes / no
  If yes → describe what breaks and what callers are affected

Database risk   : none | additive | destructive
  If destructive → requires lead sign-off before migration runs

Auth/Security   : affected / not affected
  If affected → flag to security-reviewer

Performance     : no impact | minor impact | significant impact
  If significant → describe expected impact
──────────────────────────────────────

Phase 5: Approval Request

──────────────────────────────────────────────────────────────
  PLAN READY — AWAITING APPROVAL
──────────────────────────────────────────────────────────────
Files to create : {count}
Files to modify : {count}
Files to delete : {count}
Risk level      : {level}

Respond with:
  ✅  approve     — proceed to /implement-plan
  ✏️   revise {N}  — clarify or change item N in the plan
  ❌  reject      — cancel and explain why
──────────────────────────────────────────────────────────────

Do NOT proceed to implementation until the lead explicitly approves.

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.