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 jhoblitt/rook-claude --skill rook-code-reviewgit clone --depth 1 https://github.com/jhoblitt/rook-claudeWrote 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/jhoblitt/rook-claude/rook-code-review)<a href="https://agentmods.dev/skills/jhoblitt/rook-claude/rook-code-review"><img src="https://agentmods.dev/badge/skills/jhoblitt/rook-claude/rook-code-review/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/jhoblitt/rook-claude/rook-code-review"><img src="https://agentmods.dev/badge/skills/jhoblitt/rook-claude/rook-code-review.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 | $0.00116 | $0.05844 |
| Opus 5 | $0.00058 | $0.02922 |
| Sonnet 5 | $0.00023 | $0.01169 |
| Haiku 4.5 | $0.00012 | $0.00584 |
Grade A, and why
rook-code-review 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 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.
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 — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rook code review
Review rook changes the way an expert rook maintainer would: verify claims
independently, judge against the project's own conventions, and report only
findings that survive an attempt to refute them. Findings are REPORTED —
never change code unless the user explicitly asks for fixes, and never post
anything to GitHub unless the user explicitly asked for that post, with
each comment approved in-session. When a post is authorized, follow
references/posting.md.
Edit is denied in frontmatter: nothing here modifies a file in place, and
the reviewed diff is in context arguing for itself. Write is retained for
one purpose only — proposal mode's state dir under ~/.cache (Modes) —
and never lands inside the checkout under review.
Modes
| Mode | Trigger | What it is |
|---|---|---|
| diff (default) | "review this change / branch / PR N" | One target: working tree, current branch vs origin/master (git diff origin/master...HEAD), an explicit range, or a PR (gh pr diff N). Reports; posts only on an explicit request, per references/posting.md. |
| pre-pr | "check this before I open a PR", adversarial review of own work | The review spine PLUS an adversarial attack pass, run in a context-isolated agent. Read references/adversarial.md. |
| proposal | "review this proposal / design doc / design PR N" | Adversarial design review of a document before it is code: decision enumeration, claim verification, hostile-perspective fan-out, per-decision report. Read references/proposal.md. |
Backlog triage — labeling, routing, dedupe, needs-info, cross-linking —
is the rook-triage skill's job. A bulk request ("review the open PRs",
"evaluate contributor X's PRs") decomposes: rook-triage sorts and
filters (author filter for contributor evaluation), then each routed PR
is its own diff-mode target here — parallel rook-reviewer agents at the
user's option. Before any fan-out, show the routed list and its cost —
one full reviewer spine per PR, plus the orchestrating session's
verification layer — and get explicit confirmation.
What ships with it
18 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.
- references/adversarial.md 8.4 KB
- references/architecture.md 13 KB
- references/ceph-ecosystem.md 3.7 KB
- references/ceph-object.md 5.2 KB
- references/ci-triage.md 2.1 KB
- references/cross-references.md 13 KB
- references/docs-sync.md 13 KB
- references/github-actions.md 4.5 KB
- references/go-review.md 8.6 KB
- references/known-flakes.md 4.5 KB
- references/kubernetes-crd.md 7.7 KB
- references/naming-and-comments.md 6.4 KB
- references/posting.md 9.3 KB
- references/proposal.md 11 KB
- references/reuse.md 4.7 KB
- references/security.md 13 KB
- references/testing.md 7.7 KB
- references/verification.md 10 KB
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 Changed · +1 lines 9d0446f94aae
- 5d ago Changed · +22 lines f29e963ce23d
- 9d ago First seen · 390 lines · 116 tokens per session scan A 18f37e920210
rook-code-review is a skill published in the GitHub repository jhoblitt/rook-claude (4 stars, last pushed today), licensed Apache-2.0. It adds 116 tokens to every session and 5,844 once invoked, about $0.0006 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 skills, from other repositories
security-architecture-review
Reviews a design or change for security before it ships — authentication and authorization, data handling, secrets, dependencies, and the secure-development practices around it. Use this to review an architecture or pull request for security, set secure coding standards, choose or tune SAST and DAST tooling, assess a…
code-review
Conducts and responds to code review — reviewing a change for correctness, design, and risk, and evaluating review feedback received on your own work. Use this before merging, when asked to review a diff or pull request, when review feedback has arrived and needs acting on, or when feedback seems wrong and needs a…
ork-review-pr
Review a pull request or branch for correctness, regressions, security, operational risk, and missing evidence. Use when a request asks to review a PR, review a diff, find real bugs, assess merge risk, or provide evidence-backed review findings. Do not use for implementation or style-only cleanup.
ork-assess
Assess a code change, design, architecture, workflow, or competing options against explicit criteria and evidence. Use when a request asks to assess, rate, compare, identify trade-offs, evaluate readiness, or decide whether an approach is good enough. Do not use for a full pull-request review or to implement a chosen…
ork-verify
Verify that existing work is ready to merge, release, or hand off using an explicit evidence contract. Use when a request asks to verify, validate, prove, check readiness, run the relevant tests, or distinguish a claimed result from an observed one. Do not use to write missing tests or fix failures.
review
Multi-agent code review with specialized perspectives (security, performance, patterns, simplification, tests).