agentleFS
NoaiRoxNoaiRox/specialist-agent/skills/plan/SKILL.md

plan

Skill2 starsChanged 9 months agoMITView on GitHub

Use when starting a new feature, refactor, or multi-step task - before writing any code. Use especially when scope is unclear or multiple files are involved.

184 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use heartmula, webhook-subscriptions and 10 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.
  • math-incSkill

    heartmula

    Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.

    Also in 9 projects that use this

  • Tommy-ywSkill

    webhook-subscriptions

    Create and manage webhook subscriptions for event-driven agent activation, or for direct push notifications (zero LLM cost). Use when the user wants external services to trigger agent runs OR push notifications to chats.

    Also in 5 projects that use this

  • math-incSkill

    minecraft-modpack-server

    Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.

    Also in 5 projects that use this

  • john-data-chenSkill

    touchdesigner-mcp

    Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

    Also in 6 projects that use this

  • gaebalaiSkill

    codex-system

    PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".

    Also in 3 projects that use this

  • ibahgatSkill

    context-optimize

    Improve context efficiency and cache stability for long or complex sessions.

    Also in 3 projects that use this

  • +3 more from math-inc

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 167 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create an implementation plan that matches the complexity of the task.

    line 11
  2. Distinctive:

    Search the codebase to understand scope:

    line 19
  3. Distinctive:

    Ask user: "Approve plan and begin execution?"

    line 109
  4. Distinctive:

    If approved, delegate to @executor with the plan.

    line 111
  5. Distinctive:

    Never force heavy planning for simple tasks

    line 138
  6. Distinctive:

    Always estimate token costs

    line 139
  7. Distinctive:

    Ask clarifying questions if needed

    line 140
  8. Distinctive:

    Read existing architecture before planning

    line 141

“Common” is measured: kept by at least 6 in 10 of the 167 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

/plan - Adaptive Planning

Create an implementation plan that matches the complexity of the task.

Target: $ARGUMENTS

Workflow

Step 1: Assess Complexity

Search the codebase to understand scope:

# Find affected files
# Estimate lines of code
# Identify dependencies

Classify as:

  • TRIVIAL (1-2 files, <50 lines) → Skip planning
  • SIMPLE (3-5 files, <200 lines) → Mini-plan
  • MEDIUM (6-15 files, complete module) → Standard plan
  • COMPLEX (15+ files, multiple modules) → Full design doc

Step 2: Generate Plan

For TRIVIAL:

✓ Task is trivial. Delegating to @builder.

For SIMPLE:

## Quick Plan: [Feature]

1. [Step 1] - `file.ts`
2. [Step 2] - `file.ts`
3. [Step 3] - `file.ts`
4. Test: Run `npm test`
5. Verify: Check [criteria]

Estimated: ~X tokens

For MEDIUM:

## Implementation Plan: [Feature]

### Overview
[2-3 sentences]

### Task Breakdown
- [ ] Task 1: [description] - `file.ts` (~N lines)
- [ ] Task 2: [description] - `file.ts` (~N lines)
- [ ] Task 3: [description] - `file.ts` (~N lines)

### Dependencies
- Task 2 depends on Task 1
- Tasks 3-4 can run in parallel

### Checkpoints
- After Task 2: Verify [condition]
- After Task 4: Run all tests

### Estimated Cost
~X tokens total

For COMPLEX:

## Design Document: [Feature]

### Problem Statement
[What problem are we solving?]

### Requirements
- [ ] Requirement 1
- [ ] Requirement 2

### Current State
[How does the system work today?]

### Proposed Solution
[High-level architecture]

### Alternatives Considered
1. [Alternative] - Rejected: [reason]

### Task Breakdown
[Detailed tasks with estimates]

### Risks
- Risk 1: [mitigation]

### Estimated Cost
~X tokens total

Step 3: Confirm

Ask user: "Approve plan and begin execution?"

If approved, delegate to @executor with the plan.

Output

──── /plan ────
Feature: [name]
Complexity: [TRIVIAL | SIMPLE | MEDIUM | COMPLEX]
Files affected: ~N
Estimated tokens: ~N

[Plan content]

Next: Awaiting approval

Anti-Rationalization

ExcuseReality
"It's simple enough to just start coding"That's what every developer says before a 3-day rabbit hole. 10 minutes of planning saves hours.
"I already know the architecture"Plans aren't just for you - they create alignment and a checkpoint to rollback to.
"Planning is waterfall"Adaptive planning IS agile. Skipping planning is chaos, not agility.
"I'll refactor later if the approach is wrong"Refactoring costs 10x more than planning. Get it right first.

Rules

  • Never force heavy planning for simple tasks
  • Always estimate token costs
  • Ask clarifying questions if needed
  • Read existing architecture before planning

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.