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.
git clone --depth 1 https://github.com/PenguinMiaou/claude-hiveWrote 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/commands/penguinmiaou/claude-hive/coordination-init)<a href="https://agentmods.dev/commands/penguinmiaou/claude-hive/coordination-init"><img src="https://agentmods.dev/badge/commands/penguinmiaou/claude-hive/coordination-init.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.00984 |
| Opus 5 | $0.00014 | $0.00492 |
| Sonnet 5 | $0.00005 | $0.00197 |
| Haiku 4.5 | $0.00003 | $0.00098 |
Grade A, and why
coordination-init 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Current git remote: !
git remote -v 2>/dev/null | head -2 - gh auth status: !
gh auth status 2>&1 | head -3 - COORDINATION.md exists: !
[ -f COORDINATION.md ] && echo "YES — already initialized" || echo "NO — needs creation" - CLAUDE.md exists: !
[ -f CLAUDE.md ] && echo "YES — already exists" || echo "NO — needs creation" - Current branch: !
git branch --show-current - Open PRs: !
gh pr list --state open 2>/dev/null | head -10
Your Task
Initialize multi-agent collaboration mode for this project. Follow these steps:
1. Prerequisites Check
Verify ALL of these. If any fail, report the issue and provide the fix command:
- GitHub remote:
git remote -vmust show a GitHub remote. If not: "Rungit remote add origin <url>first." - gh CLI authenticated:
gh auth statusmust succeed. If not: "Rungh auth loginfirst." - On main branch: Should be on main. If not, note it.
2. Create project workflow docs (if not exists)
If COORDINATION.md does not exist, create it:
# Multi-Agent Coordination
## Branch Registry
## Conflict Map
## Merge Queue
## Audit Trail
## Review Policy
If CLAUDE.md does not exist, create it. If it already exists, append the claude-hive section instead of overwriting the file:
## Multi-Agent Worktree Coordination
When multi-window collaboration mode is active (both `COORDINATION.md` and this `CLAUDE.md` section exist):
### Branch Protection
- main branch: ONLY the merger window may commit/merge to main
- Work windows: ALL changes go to worktree branches (`feat/xxx`, `fix/xxx`)
### Default Review Workflow
- Contributors create/update PRs and expect remote automatic review on every push
- Merger must run a final local review against latest `main` before merge
- Local review provider defaults to `codex`, but another local CLI reviewer may be used
- Blocking final-review findings require human decision before merge
### Coordination And Audit
- Treat `COORDINATION.md` as the source of truth for branch registry, merge queue, audit trail, and review policy
- Run `/coordination-audit` before merger proceeds with a local merge
### Auto-Reminder
- When `COORDINATION.md` exists and the agent is on `main` and about to write code:
prompt user "Multi-agent mode detected. Invoke /worktree-contributor first."
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.
- 7d ago First seen · 104 lines · 27 tokens per session scan A 73d3dd081f7b
coordination-init is a command published in the GitHub repository PenguinMiaou/claude-hive (1 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 984 once invoked, about $0.0001 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 commands, from other repositories
resolve-todos
Resolve approved TODOs in parallel using worker agents — one agent per TODO.
delivery
Executes an approved plan by orchestrating subagents in parallel batches. Use after /fractal:planning produces an approved plan.md.
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
discover
Run a full product discovery cycle — from outcome definition through opportunity mapping, prioritisation, and experiment design. Use when the team isn't sure what to build next, or before writing a PRD for a complex feature space.
update-counts
Update all hardcoded counts (skills, agents, marketplace repos/skills) across documentation from filesystem.
plan-start
5-phase planning command: PRD analysis, design review, technical decisions, dynamic research team, metrics. Produces a complete implementation plan + ADRs before any code is written.