What is coordination-audit?

A read-only checklist for checking whether coordinated coding work is ready to merge. A merge combines changes from one Git branch into another, usually through a pull request.

Use it before merging work from multiple agents to inspect repository coordination, pull-request readiness, review status, branches, and worktrees.

It reveals missing coordination files, stale worktree or queue information, unresolved reviews, draft pull requests, and branches that may be behind the main branch.

coordination-audit — Command for Claude Code by PenguinMiaou

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.

Clone the repo

git clone --depth 1 https://github.com/PenguinMiaou/claude-hive

Made for: Claude Code.

Or install claude-hive, the plugin that ships this one along with the rest of its 2 skills, 3 commands.

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/commands/penguinmiaou/claude-hive/coordination-audit/github.svg)](https://agentmods.dev/commands/penguinmiaou/claude-hive/coordination-audit)

Your own site

<a href="https://agentmods.dev/commands/penguinmiaou/claude-hive/coordination-audit"><img src="https://agentmods.dev/badge/commands/penguinmiaou/claude-hive/coordination-audit/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/commands/penguinmiaou/claude-hive/coordination-audit"><img src="https://agentmods.dev/badge/commands/penguinmiaou/claude-hive/coordination-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 705 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	$0.00026	$0.00705
Opus 5.5	$0.00010	$0.00282
Sonnet 5.5	$0.00005	$0.00141
Haiku 4.5	$0.00003	$0.00071

Measured 1mo ago against content hash 2c63aaca59bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

coordination-audit 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 1mo 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.

commands/coordination-audit.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

COORDINATION.md: !cat COORDINATION.md 2>/dev/null || echo "NOT FOUND — run /coordination-init first"
CLAUDE.md: !cat CLAUDE.md 2>/dev/null || echo "NOT FOUND — run /coordination-init first"
Open PRs: !gh pr list --state open --json number,title,headRefName,isDraft,reviewDecision 2>/dev/null || echo "gh CLI not available"
Current branch: !git branch --show-current
Worktrees: !git worktree list 2>/dev/null

Your Task

Run a read-only pre-merge audit for claude-hive. This command is the merger's situational audit step before any local merge or verification work starts.

Audit Checklist

Check and report:

Coordination hygiene
- COORDINATION.md exists
- CLAUDE.md exists
- Branch Registry, Conflict Map, Merge Queue, and Audit Trail sections exist
- CLAUDE.md contains the Multi-Agent Worktree Coordination section
- Queue entries and branch registry entries are not obviously stale
PR readiness
- Which PRs are draft vs ready
- Whether a branch in Merge Queue still has an open PR
- Whether any queued PR appears to be behind main
Review state
- Flag PRs with unresolved or blocking review state where visible from gh pr list
- Treat CHANGES_REQUESTED or equivalent blocking state as not ready to merge
- If exact thread resolution is unavailable, say so explicitly and tell the merger to verify before merge
Local final review policy
- Remind that merger should run one local final review against the latest main
- Local review is provider-driven and advisory by default
- Supported provider examples: codex (default), claude, gemini, or another local CLI
- Severity policy:
  - info: continue
  - warning: continue and report
  - blocking: stop and ask the user

Output Format

🐝 Claude Hive Audit
════════════════════

Queue health:
  - feat/table-v2 #12 — ready
  - feat/chart-export #13 — ready but review decision is CHANGES_REQUESTED

Remote review:
  - #12 clean
  - #13 blocking review state detected

Local final review policy:
  - Provider: codex (default) / configurable
  - Mode: advisory
  - Blocking findings require human decision

Next action:
  - Merge can proceed for: #12
  - Merge must pause for: #13

Read the full file on GitHub · 78 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.

1mo ago First seen · 78 lines · 26 tokens per session scan A 2c63aaca59bd

Subscribe to this mod's changes

coordination-audit is a command published in the GitHub repository PenguinMiaou/claude-hive (1 stars, last pushed 7mo ago), licensed MIT. It adds 26 tokens to every session and 705 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude Code Code review Git and workflow Multi-Agent anthropic git-worktree plugin

resolve-pr

Resolve PR review feedback — fetch unresolved threads, triage, dispatch resolver agents, reply + resolve via GraphQL.

gmickel/flow-next · 26 tokens

release

Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync.

avelikiy/great_cto · 34 tokens

create-pr

Context-aware GitHub Pull Request creation and update assistant.

joaquimscosta/arkhe-claude-plugins · 10 tokens

align

Context-aware alignment. In plan mode it audits the active plan and folds the amendments in. Otherwise it reviews the branch, a named branch, or a pull request against Ion's principles, authors a fix plan, and after approval implements and commits the fixes.

dsswift/ion · 51 tokens

resolve-dependabot-prs

Triage open Dependabot PRs, return a quick risk/action summary table, then enter planning mode with an ordered rebase→merge→follow-up→resume resolution plan.

dsswift/ion · 35 tokens

review

Unified review orchestrator — detect changes, dispatch reviewers, validate findings, optionally post GitHub inline comments.

RaNDoM6913/claude-code-superkit · 20 tokens