Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add jhoblitt/rook-claude/plugin install rook-maintainerWrote 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-conventions)<a href="https://agentmods.dev/skills/jhoblitt/rook-claude/rook-conventions"><img src="https://agentmods.dev/badge/skills/jhoblitt/rook-claude/rook-conventions/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-conventions"><img src="https://agentmods.dev/badge/skills/jhoblitt/rook-claude/rook-conventions.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 | $0.00085 | $0.02489 |
| Opus 5 | $0.00043 | $0.01244 |
| Sonnet 5 | $0.00017 | $0.00498 |
| Haiku 4.5 | $0.00009 | $0.00249 |
Grade A, and why
rook-conventions 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 3d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rook house conventions
The operating rules the rest of this plugin's skills share: the authoring
canon in full, plus the cross-cutting rules review and triage both depend on
(GitHub write authorization, attribution, untrusted content, review-authority
weighting, backport eligibility). Mode-specific canon stays with its skill —
review in rook-code-review, triage in rook-triage.
Precedence: in-repo docs (Documentation/Contributing/*) outrank this skill;
the user's own global CLAUDE.md outranks it too — on conflict, follow
theirs and note the divergence.
"The operating maintainer" below means whoever is running the session:
resolve their GitHub login with gh api user --jq .login when a rule needs
it. Never hardcode a username.
Reference routing
Read a reference when the work touches its trigger; skip the rest. The rules below this table apply to every trigger.
| Doing this | Read |
|---|---|
| writing or fixing a commit message, amending, reworking a branch's history, or diagnosing a commitlint failure | references/commits.md |
| opening or updating a PR, writing its description, filling its template checklist, writing the AI-assistance disclosure, requesting reviewers | references/pull-requests.md |
| deciding whether a change is backport-eligible, or writing one headed for a backport | references/backporting.md |
| applying or maintaining backport labels, or fixing a mergify backport PR | references/backport-labels.md |
| weighing review feedback on a PR — conflicting opinions, or a technical claim from outside CODE-OWNERS | references/review-feedback.md |
| building, testing, or linting rook; regenerating CRDs or generated code; writing rook tests | references/building-and-testing.md |
changing .github/workflows/**, .mergify.yml, or a pinned CI Kubernetes version |
references/workflows-and-ci.md |
| watching CI after a push, retrying flakes, or burning in a flake fix | references/watching-ci.md |
| fanning out subagents | references/fan-out.md |
running one of this plugin's own tools through run.sh, or changing one |
references/plugin-tools.md |
What ships with it
10 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/backport-labels.md 8.4 KB
- references/backporting.md 2.3 KB
- references/building-and-testing.md 3.6 KB
- references/commits.md 4.0 KB
- references/fan-out.md 1002 B
- references/plugin-tools.md 1.4 KB
- references/pull-requests.md 5.5 KB
- references/review-feedback.md 2.3 KB
- references/watching-ci.md 2.0 KB
- references/workflows-and-ci.md 1.9 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.
- 3d ago Changed · +9 lines 26c6da0c3076
- 8d ago Changed · -8 lines 49ae0bac7d38
- 12d ago First seen · 189 lines · 85 tokens per session scan A 30dbffa95581
rook-conventions is a skill published in the GitHub repository jhoblitt/rook-claude (4 stars, last pushed 3d ago), licensed Apache-2.0. It adds 85 tokens to every session and 2,489 once invoked, about $0.0004 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
branch-and-worktree-workflow
Isolates feature work in its own branch or worktree and integrates it cleanly when done. Use this when starting work that should not disturb the current workspace, when several efforts must proceed in parallel on one repository, or when implementation is finished and the change needs merging, rebasing, or splitting…
swarm-migrate
Cross-repo migration swarm — one coordinator + N parallel subagents (one per target repo) that apply the same transformation, open PRs, wait for CI, and report back to a shared JSON ledger. Coordinator handles topology, conflict auto-rebase, and stop-on-novel-failure. Use when bumping a shared dependency, rolling out…
dev
One-command dev loop boot. Spins up portless (named HTTPS subdomain), emulate (stateful API mocks), the project's dev server, and an agent-browser session, all keyed to the current git branch. Use when starting a feature branch, switching worktrees, or returning to a project after a break. Skips silently with install…
github-operations
GitHub CLI operations for issues, PRs, milestones, and Projects v2. Covers gh commands, REST API patterns, and automation scripts. Use when managing GitHub issues, PRs, milestones, or Projects with gh.
release-sync
Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.
personal-guide-start
A starter workflow that creates a private GitHub repository for a personal development guide and fills it with six starter files.