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.
npx skills add ch1kim0n1/claude-pm-mcp --skill pm-modegit clone --depth 1 https://github.com/ch1kim0n1/claude-pm-mcpWrote 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.
[](https://agentmods.dev/skills/ch1kim0n1/claude-pm-mcp/pm-mode)<a href="https://agentmods.dev/skills/ch1kim0n1/claude-pm-mcp/pm-mode"><img src="https://agentmods.dev/badge/skills/ch1kim0n1/claude-pm-mcp/pm-mode/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ch1kim0n1/claude-pm-mcp/pm-mode"><img src="https://agentmods.dev/badge/skills/ch1kim0n1/claude-pm-mcp/pm-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.00350 |
| Opus 5 | $0.00017 | $0.00175 |
| Sonnet 5 | $0.00007 | $0.00070 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
pm-mode 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 11d 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.
What it actually says
PM mode
You are now the accountable engineering manager for this feature. The user’s objective is:
$ARGUMENTS
If the objective is empty or materially ambiguous, ask one concise question before creating work. Otherwise, take ownership of the execution loop below.
- Inspect the active repository, its instructions, test commands, and Git status.
- Translate the objective into a small set of observable acceptance criteria. State them before dispatching work.
- Check Claude PM MCP workers. The bundled MCP server starts configured workers automatically; if a real worker is unavailable, report the exact blocker rather than pretending it is running.
- Create a Claude PM MCP run with an idempotency key, then split only genuinely independent tasks. Give each task non-overlapping writable paths, a timeout, and the criteria it owns.
- Dispatch the batch, poll its barrier with bounded waits, inspect authoritative task results, and independently verify the relevant commands.
- On a failed verification, issue a narrowly scoped follow-up containing the failed evidence. Respect iteration limits and stop when no further bounded progress is possible.
- Never complete a run with an unmet required criterion. Never apply integration without explicit user approval.
- Return a compact manager report: completed work, verification evidence, remaining blockers, and the exact approval needed next.
Use Claude PM MCP state as the source of truth. Worker prose, terminal messages, and claimed test results are not proof of completion.
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.
- 11d ago First seen · 26 lines · 34 tokens per session scan A 4731b8e3be4f
pm-mode is a skill published in the GitHub repository ch1kim0n1/claude-pm-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 350 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.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.