agentleFS
ek33450505ek33450505/claude-agent-team/skills/plan/SKILL.md

plan

Skill8 starsChanged 32 days agoMITView on GitHub

Activate the heavy planner→/orchestrate chain — write a structured plan file with Agent Dispatch Manifest, then invoke the /orchestrate skill to execute it in waves. Reserve for genuinely multi-file / multi-hour / multi-agent work (large refactors, migrations, features spanning many files). For single-session-sized work (one or a few files), use built-in plan mode (shift-tab) instead — not this skill.

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

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

  • 0

    Common

    Most of the 167 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Write a plan file under ~/.claude/plans/ using the Write tool:

    line 14
  2. Very specific:

    Use "subagent_type": "main" for tasks the orchestrator handles inline.

    line 41
  3. Distinctive:

    After writing the plan file, display a concise summary:

    line 45
  4. Distinctive:

    Wait for explicit confirmation before proceeding.

    line 52

“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 Mode

This is the /plan skill — the heavy planner→/orchestrate chain, reserved for genuinely multi-file / multi-hour / multi-agent work. For single-session-sized tasks (one or a few files, finishable in one session), use built-in plan mode (shift-tab) with a single agent instead of this skill. You are entering plan mode to write a structured implementation plan.

Step 1 — Write the plan file

Write a plan file under ~/.claude/plans/ using the Write tool:

  • Filename: ~/.claude/plans/<YYYY-MM-DD>-<slug>.md where slug is a short kebab-case description
  • Include all of these sections:
    • Title and context
    • Fix strategy / implementation approach (one subsection per logical change)
    • Files to modify table
    • Implementation order
    • Verification steps
    • ## Agent Dispatch Manifest — mandatory — a json dispatch code block with batches, agent types, prompts, and parallel flags

The ADM block must follow this schema:

{
  "batches": [
    {
      "id": 1,
      "description": "short description",
      "parallel": true,
      "agents": [
        { "subagent_type": "agent-name", "prompt": "specific task prompt" }
      ]
    }
  ]
}

Use "subagent_type": "main" for tasks the orchestrator handles inline. Use named agents (e.g. "code-reviewer", "commit") for delegated tasks. Group independent tasks into parallel batches.

Step 2 — Show plan summary and ask for approval

After writing the plan file, display a concise summary:

  • Plan file path
  • Number of batches and agents
  • A table: Batch | Mode | What it does

Then ask the user: "Execute this plan with /orchestrate? [yes/no]"

Wait for explicit confirmation before proceeding.

Step 3 — Execute via /orchestrate skill

Once the user confirms, invoke the /orchestrate skill with the plan file path:

/orchestrate [ABSOLUTE_PLAN_PATH]

The /orchestrate skill reads the plan's Agent Dispatch Manifest and executes all batches directly from the main session — presenting the batch queue, running the interrupt window, then dispatching agents in order.

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.