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 corveil/crow --skill crow-ci-queuegit clone --depth 1 https://github.com/corveil/crowWrote 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/corveil/crow/crow-ci-queue)<a href="https://agentmods.dev/skills/corveil/crow/crow-ci-queue"><img src="https://agentmods.dev/badge/skills/corveil/crow/crow-ci-queue/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/corveil/crow/crow-ci-queue"><img src="https://agentmods.dev/badge/skills/corveil/crow/crow-ci-queue.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 | $0.00135 | $0.09029 |
| Opus 5.5 | $0.00054 | $0.03612 |
| Sonnet 5.5 | $0.00027 | $0.01806 |
| Haiku 4.5 | $0.00014 | $0.00903 |
Grade B, and why
crow-ci-queue scanned grade B with 1 finding 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 today.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`queue.sh` is pre-approved in `{devRoot}/.claude/settings.local.json` (`Bash(bash .claude/skills/crow-ci-queue/queue.sh *)` and the direct form), as are `crow` and `gh pr view`. That includes the script's writes, which a How it starts
The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crow CI Queue Skill
Purpose
On a repo that follows the CI Gate convention (ADR 0082; today corveil/corveil), the full test.yml suite runs only while a PR carries ci:full, and crow-review-pr adds that label when it approves (CROW-1306). When several session PRs are approved around the same time, they all run the suite at once. Two things go wrong:
- They fight over the small self-hosted runner pool, so every run gets slower.
- The work is thrown away.
mainrequires branches to be up to date (strict_required_status_checks_policy). When one PR merges, every other PR falls behind, gets its branch updated, and runs the suite again.
This skill runs those PRs one at a time, per repo:
- Collect the PRs of every
active/inReviewwork session that carrycrow:merge, in repos that follow the convention. There is one queue per repo. - Normalize: strip
ci:fullfrom every queued PR except one, the holder. - Order the rest: ready PRs, oldest first. PRs that aren't ready are listed with the reason.
- Advance: update the next ready PR from
mainif it's behind, confirm it's still approved, then addci:full. - Watch the holder in a background process that exits only when a decision is needed. You're woken by that exit; you don't poll.
- Report each step to the operator in one line.
- Keep going. A repo whose queue drains keeps an idle watcher, so a session created later joins its queue. Each watcher exit also re-checks for repos that became queueable. The queue runs until the operator stops it.
queue.sh is the deterministic half: reading GitHub and Crow, classifying runs, choosing the holder, and the label and update-branch writes. This file is the other half: what to do with each answer.
Why not GitHub's merge queue? It solves the same "strict up-to-date means N re-runs" problem natively, but it doesn't fit the label gate as it stands. corveil/corveil's main has no merge-queue rule, and test.yml runs only on pull_request and workflow_dispatch, not merge_group. The ADR 0082 gate also keys on the PR's ci:full label, which a merge_group run doesn't carry. Adopting it means redesigning that gate. Whether the org's plan offers a merge queue for this repo hasn't been checked.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 433 lines · 135 tokens per session scan B a6f33739495c
crow-ci-queue is a skill published in the GitHub repository corveil/crow (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 135 tokens to every session and 9,029 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.
Other skills, from other repositories
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
validate-release-green
Run or inspect the local Release-Green observer for an exact base or combined PR candidate, separating hard failures, advisory drift and incomplete evidence. Use for maintainer preflight; full CI acceptance remains a separate requirement.
ship
Pre-release gate. Run the full gate, responsive + render checks, then produce the release checklist (README badge/current/changelog). Use before tagging a release.
verify-and-ship
Choose proportionate validation, fix failures, update the changelog, commit, push, and create/update the pull request or merge request.
ship-workflow
Resumable shipping lifecycle: reconciles current Git and GitHub facts from any entry (dirty default or feature branch, local commits, published branch, open PR, existing manual or native stack, merged work), commits dirty work as lossless logical commits, publishes or reuses the PR, requires current CI and review…
blueprint-refactor-tranche
Take ONE target from the plan and land it without changing behaviour: guard it on the untouched code, move it verbatim, prove the equivalence by running both, mutation-sweep the tests, pass every gate, open a PR and merge it on green CI — or decline it with the cost written down.