agentleFS
Sign inStart free
hunterg325hunterg325/claude-code-pm/skills/pm-start/SKILL.md

pm-start

Skill2 starsChanged 8 months agoMITView on GitHub

Launch the PM orchestration loop. Use when: user runs /pm:start, wants to start autonomous task execution from Linear, or says 'start the PM'.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. naderelewa/Product-to-Prod★ 43same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 3 are distinctive, and 8 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 8

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run these checks before starting.

    line 28
  2. Very specific:

    claude-peers broker: Call list_peers — if it fails, tell user to start the claude-peers broker (cd ~/claude-peers && bun run src/index.ts)

    line 30
  3. Very specific:

    Linear MCP: Call list_issues with a limit of 1 — if it fails, tell user to configure Linear MCP and link to …

    line 31
  4. Very specific:

    gh CLI: Run gh auth status — if it fails, tell user to run gh auth login

    line 32
  5. Very specific:

    pm-config.yaml: Read .claude/pm-config.yaml — if missing, offer to create it from ${CLAUDE_PLUGIN_ROOT}/templates/pm-config.example.yaml

    line 33
  6. Distinctive:

    If any check fails, stop and report all failures at once.

    line 36
  7. Very specific:

    Read .claude/pm-config.yaml and validate required fields (target_repo, linear.project)

    line 40
  8. Very specific:

    Check for .claude/pm-state.json — if exists, enter crash recovery mode:

    line 42
  9. Very specific:

    If --dry-run argument provided: fetch tasks, show what would be assigned, then stop

    line 45
  10. Distinctive:

    Run the spawn script:

    line 52
  11. Very specific:

    After spawning, wait ~15 seconds for workers to register, then verify with list_peers.

    line 63

≈ “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

/pm:start — Launch PM Orchestration

Pre-flight Checks

Run these checks before starting. Surface clear errors for any failures:

  1. claude-peers broker: Call list_peers — if it fails, tell user to start the claude-peers broker (cd ~/claude-peers && bun run src/index.ts)
  2. Linear MCP: Call list_issues with a limit of 1 — if it fails, tell user to configure Linear MCP and link to https://docs.claude.ai/integrations/linear
  3. gh CLI: Run gh auth status — if it fails, tell user to run gh auth login
  4. pm-config.yaml: Read .claude/pm-config.yaml — if missing, offer to create it from ${CLAUDE_PLUGIN_ROOT}/templates/pm-config.example.yaml
  5. target_repo: Validate that target_repo is set in pm-config.yaml and the path exists and is a git repo

If any check fails, stop and report all failures at once. Do not proceed.

Startup Sequence

  1. Read .claude/pm-config.yaml and validate required fields (target_repo, linear.project)
  2. Set your peer summary via set_summary: "PM Orchestrator — managing {project_name}"
  3. Check for .claude/pm-state.json — if exists, enter crash recovery mode:
    • Reconcile against list_peers, git worktree list, Linear statuses
    • Report recovered state to user
  4. If --dry-run argument provided: fetch tasks, show what would be assigned, then stop

Spawn Worker Pool

The PM does NOT spawn workers itself. Workers are interactive Claude Code sessions running in visible Terminal.app tabs so the user can observe them.

Run the spawn script:

bash ${CLAUDE_PLUGIN_ROOT}/scripts/spawn-workers.sh "{target_repo}" {max_concurrent}

This opens max_concurrent Terminal tabs, each running:

cd {target_repo} && claude --dangerously-skip-permissions --dangerously-load-development-channels server:claude-peers

Workers start idle and wait for task assignments via claude-peers messages. After spawning, wait ~15 seconds for workers to register, then verify with list_peers.

Enter Orchestration Loop

Load and follow the PM system prompt at ${CLAUDE_PLUGIN_ROOT}/templates/pm-system-prompt.md.

The PM assigns tasks to workers by sending task_assignment messages via claude-peers. Workers are already running in the target repo — the PM just routes work to them.

Orchestration loop: fetch tasks → pick unblocked → send assignment to idle worker → monitor messages → on completion delegate to VO → repeat.

The PM session should run continuously until stopped with /pm:stop or interrupted.

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.

Check your setup, free