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 forest/agent-skills --skill repo-coordinatorgit clone --depth 1 https://github.com/forest/agent-skillsWrote 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/forest/agent-skills/repo-coordinator)<a href="https://agentmods.dev/skills/forest/agent-skills/repo-coordinator"><img src="https://agentmods.dev/badge/skills/forest/agent-skills/repo-coordinator/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/forest/agent-skills/repo-coordinator"><img src="https://agentmods.dev/badge/skills/forest/agent-skills/repo-coordinator.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 | $0.00055 | $0.00791 |
| Opus 5.5 | $0.00022 | $0.00316 |
| Sonnet 5.5 | $0.00011 | $0.00158 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
repo-coordinator 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 yesterday.
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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo coordinator
The coordinator owns the flow of work on a repo. It doesn't write the code. It keeps planning, tracking and handoffs tidy so spec and coding agents can run.
Source-of-truth split
- The repo holds durable thinking: the PRD, design docs, plans, evidence and decision records, all reviewed through PRs.
- GitHub holds status and backlog:
- One milestone per PRD milestone, titled
Mx — Name. - One issue per epic, labeled
epic. - Deferred or follow-up items as issues labeled
deferred, linked as sub-issues of their parent epic when there is one. - Labels for cross-cutting kinds:
prd-requirement,rollout-gate,deployment-prerequisite.
- One milestone per PRD milestone, titled
- A tracker file in the repo (such as TRACKER.md) should only be an index that links to milestones and issues, never a second copy of their status.
Onboarding a repo
- Read the PRD, the tracker and the deferred list through the GitHub connector. Never clone onto the user's computer. Use a cloud agent when you need the code itself.
- Check which agent tooling is committed, such as
.agents/skillswith symlinks from.cursor/skillsand.claude/skills. Cloud agents don't load marketplace plugins, so vendor any skill pack the user relies on into the repo through a PR. - Move tracking into GitHub:
- Create the labels and issues yourself.
- The connector can't create, edit or close milestones. Without a logged-in
gh, give the user the exact milestone titles to create, then assign the issues yourself. - Close issues whose work is already merged, and cite the PR.
- Close finished milestones. Before closing, move any open deferred items out of the milestone and add a carried-over comment to each, so they stay visible in the backlog.
Choosing what's next
- Finish a partially done milestone before opening a new one, especially when only acceptance or validation steps are left.
- Follow the PRD's recommended order unless a dependency or user priority says otherwise.
- At each epic boundary, review the open deferred items and either schedule them or leave them parked on purpose.
- Recommend one next milestone or epic, give one line on why, and name the first issue.
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.
- yesterday First seen · 50 lines · 55 tokens per session scan A 0147ffcf9f37
repo-coordinator is a skill published in the GitHub repository forest/agent-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 791 once invoked, about $0.0002 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 2026-11-03.
Other skills, from other repositories
antfu-issue-triage
Triage open issues and PRs of the current GitHub repo - find already-fixed, duplicate, and spam items, suggest labels, gauge demand from reactions and comments, then present a table of proposed actions and comments for confirmation before touching anything. Use when asked to triage, organize, clean up, or groom issues…
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
connect
Choose which wiki this session uses, the team project's pages on the Nimbalyst server or the project's local wiki of files, and connect a repository to its team project. Use at the start of a task before any wiki tool, when a wiki tool returns reponotbound, ambiguousproject, pinmismatch, projectnotaccessible…
llxprt-issue-workflow
Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the zai-glm-flash smoke test), open code review (ocr)…