A coordinator for planning and managing feature work across separate coding workers. It records acceptance criteria, assigns independent tasks, checks their results, and verifies the finished changes.

Use it to split a feature into independent tasks, dispatch workers, wait for their completion, review their files and commands, run verification, and send follow-up work when needed.

It helps prevent overlapping edits, unclear completion claims, and unverified work when several coding agents work on one project. It also provides a tracked process for correcting failed checks.

coordinate — Skill for Claude Code by ch1kim0n1

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.

Any agent

npx skills add ch1kim0n1/claude-pm-mcp --skill coordinate

Clone the repo

git clone --depth 1 https://github.com/ch1kim0n1/claude-pm-mcp

Made for: Claude Code.

Or install claude-pm-mcp, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ch1kim0n1/claude-pm-mcp/coordinate/github.svg)](https://agentmods.dev/skills/ch1kim0n1/claude-pm-mcp/coordinate)

Your own site

<a href="https://agentmods.dev/skills/ch1kim0n1/claude-pm-mcp/coordinate"><img src="https://agentmods.dev/badge/skills/ch1kim0n1/claude-pm-mcp/coordinate/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ch1kim0n1/claude-pm-mcp/coordinate"><img src="https://agentmods.dev/badge/skills/ch1kim0n1/claude-pm-mcp/coordinate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 537 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00047	$0.00537
Opus 5	$0.00023	$0.00269
Sonnet 5	$0.00009	$0.00107
Haiku 4.5	$0.00005	$0.00054

Measured 12d ago against content hash f617155ea5b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

coordinate 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 12d 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/coordinate/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude PM MCP orchestration

Use the Claude PM MCP tools as the system of record. Do not treat a worker's natural-language terminal output as completion evidence.

Start a run

Inspect the target repository and confirm it is clean enough for Git worktrees.
State measurable acceptance criteria. Every required criterion needs an evidence type.
Call coordify_run_create with a stable idempotency key.
Call coordify_workers_list; start/restart workers through the local CLI only if they are not ready.

Dispatch work

Split only independent tasks into the same coordify_batch_dispatch call.
Give every task a non-overlapping owned_paths scope, explicit prohibited paths, required commands, and criterion IDs.
Use a fresh idempotency key for each logical dispatch or follow-up.
Poll coordify_batch_await with a short bounded wait. Do not review a batch until every task is in a terminal state or worker_completed.

Verify and iterate

Read each coordify_task_result; compare the claimed files and commands to the task scope.
Call coordify_verify. Passing worker claims never override failed independent verification.
If verification fails, send one narrowly scoped coordify_task_follow_up that includes the failing evidence. Respect the configured iteration limit.
Call coordify_run_status after every verification round.

Completion and integration

Do not complete a run until every required criterion has passing evidence or an explicit waiver.
Call coordify_integration_prepare and present its commit plan to the user.
Only call coordify_integration_apply with approved: true after the user has explicitly approved the merge.
Call coordify_run_stop with reason completed only after all required criteria pass. Its summary is the final evidence report.

Recovery and safety

If the MCP process or Claude session restarts, call coordify_recover before dispatching more work.
Never broaden a task's path scope or approve destructive commands without user confirmation.
Use the built-in fake workers only for local protocol tests. Configure tmux-interactive-cli workers for persistent interactive Claude/GLM sessions, or process-json workers for deterministic noninteractive CLIs.

Read the full file on GitHub · 43 lines

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.

12d ago First seen · 43 lines · 47 tokens per session scan A f617155ea5b8

Subscribe to this mod's changes

coordinate is a skill published in the GitHub repository ch1kim0n1/claude-pm-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 537 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.

Building agents Project management

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

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…

specstoryai/getspecstory · 126 tokens

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…

Donchitos/Claude-Code-Game-Studios · 77 tokens

projects

List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.

me2resh/apexyard · 24 tokens

magpie-security-issue-import-from-md

Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.

apache/magpie · 73 tokens