pm-stop

pm-stop is a skill for Claude Code, Codex from hunterg325/claude-code-pm. It costs 41 tokens per session (326 once invoked), scanned A, original, MIT.

A skill for stopping a project-manager orchestration loop and optionally shutting down its workers. It reads the orchestration state, notifies active workers, waits for acknowledgements, and records the shutdown state.

In plain words
What is it for?
Use it for `/pm:stop`, stopping project-manager orchestration, aborting active workers, recording shutdown details, and optionally reviewing unmerged worktrees for cleanup.
Why use it?
It provides a controlled way to halt coordinated agent work and preserve information about tasks that were still running. It can also identify orphaned worktrees before optional cleanup.

Skill for Claude CodeCodex

Part of the claude-code-pm plugin — 3 skills, 1 agent shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/hunterg325/claude-code-pm/pm-stop
Any agent
npx skills add hunterg325/claude-code-pm --skill pm-stop
Clone the repo
git clone --depth 1 https://github.com/hunterg325/claude-code-pm

Made for: Claude Code, Codex.

Or install claude-code-pm, the plugin that ships this one along with the rest of its 3 skills, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pm-stop

README.md
[![agentmods](https://agentmods.dev/badge/skills/hunterg325/claude-code-pm/pm-stop.svg)](https://agentmods.dev/skills/hunterg325/claude-code-pm/pm-stop)
Your own site
<a href="https://agentmods.dev/skills/hunterg325/claude-code-pm/pm-stop"><img src="https://agentmods.dev/badge/skills/hunterg325/claude-code-pm/pm-stop.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 326 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00041 $0.00326
Opus 5 $0.00020 $0.00163
Sonnet 5 $0.00008 $0.00065
Haiku 4.5 $0.00004 $0.00033

Measured 4d ago against content hash 496a16c4dced, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pm-stop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/pm-stop/SKILL.md · 38 lines

What it actually says

/pm:stop — Graceful Shutdown

Shutdown Sequence

  1. Read .claude/pm-state.json for active state
  2. For each active worker:
    • Send abort message via claude-peers: { "type": "abort", "task_id": "{id}", "reason": "PM shutting down" }
    • Log the abort
  3. For each active VO agent:
    • Send abort message
  4. Wait up to 30 seconds for workers to acknowledge (responses arrive as events)
  5. Update pm-state.json:
    • Move active workers to a shutdown_pending state
    • Record shutdown timestamp
  6. Report summary:
    • Workers notified: N
    • Workers acknowledged: N
    • Tasks that were in progress (may need re-queue on next /pm:start)

Optional Cleanup

Ask user: "Would you like to clean up orphaned worktrees? This removes worktrees for tasks that haven't been merged."

If yes:

  • Run git worktree list
  • Cross-reference with merged branches
  • Remove unmerged worktrees with confirmation for each
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 38 lines · 41 tokens per session scan A 496a16c4dced

Subscribe to this mod's changes

pm-stop is a skill published in the GitHub repository hunterg325/claude-code-pm (2 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 326 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

run

Conduct a task end to end, from a one-line fix to a multi-day programme - a short interview, then autonomous execution to the finish. Classifies the task S/M/L/XL, configures itself to the repo, routes each role to a cost tier, drives the agent team from the kanban board, and stops only at genuine decisions. Use for…

jjanczur/tyran · 97 tokens

status

Where is the work right now. Regenerates the projections and the kanban board from the journal and answers with the progress line, the agents still running, the open gates and the resume steps. Read-only. Use for /tyran:status or when asked what is going on.

jjanczur/tyran · 58 tokens

heartbeat

This skill should be used when the user asks to "run a heartbeat", "run the agent loop", "process GitHub issues", "check for work", or runs the /heartbeat command. Executes the WoterClip heartbeat — picks up GitHub issues, resolves personas, does work, and reports back.

wotai-dev/woterclip · 64 tokens

woterclip-init

This skill should be used when the user asks to "initialize woterclip", "set up woterclip", "woterclip init", "configure woterclip for this repo", or runs the /woterclip-init command. Scaffolds a repo with WoterClip config, persona directories, and GitHub labels.

wotai-dev/woterclip · 72 tokens

unleash

Run as a named worker draining the task queue in my private coordination repo, where each task is a GitHub Issue — claim one task at a time, check blocked-by dependencies, plan with explicit assumptions, execute, validate against acceptance criteria, and record results as comments; then stay in ambush behind a…

rafael-adcp/kraken · 94 tokens

status

Read-only console of a kraken queue — everything the operator reads in one place. Runs kraken.py status, which computes the review queue (awaiting-merge, with PR links), the decision queue (needs-decision), what is still in flight (every live claim ref — worker name + lease age, flagging expired leases), a…

rafael-adcp/kraken · 103 tokens