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 OutlineDriven/odin-claude-plugin --skill gh-review-requestsgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/gh-review-requests)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/gh-review-requests"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/gh-review-requests/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/outlinedriven/odin-claude-plugin/gh-review-requests"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/gh-review-requests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00038 | $0.00836 |
| Opus 5 | $0.00019 | $0.00418 |
| Sonnet 5 | $0.00008 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
gh-review-requests 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 6d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gh review requests
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks to find PRs to review, show review requests, or check the team review queue. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | Fetches unread GitHub review-request notifications and filters by team; emits chat output only. |
| Done | A table of open PRs needing review with URLs and reasons, or a no-results report, is returned. |
Not for
- Summarizing feedback on a specific PR: use resolve-pr-feedback.
- Resolving review feedback, use resolve-pr-feedback.
- Source or remote mutation: this skill is read-only.
Inputs
- GitHub authentication via the authenticated
ghCLI (verified withgh auth status) or aGITHUB_TOKENavailable togh. Required. - Optional team filter: a team slug or name. When supplied, keep only review requests targeting that team or its members.
- Optional repository scope: one or more
owner/repostrings. When supplied, restrict results to those repositories.
Procedure
- Verify
ghis authenticated by runninggh auth status. If it is not, stop and report the auth failure class; do not attempt to write credentials. Done when:ghis authenticated or the auth failure is reported. - Fetch unread notifications with reason
review_requested: rungh api --paginate /notificationsand keep entries wherereason == "review_requested"andunread == true. Done when: unread review-requested notifications are fetched. - For each retained notification, resolve the subject URL into the PR record with
gh pr view <number> --repo <owner/repo> --json number,title,author,url,reviewRequeststo obtain title, author, URL, and the review request teams. Done when: every retained notification is resolved into a PR record. - If a team filter is supplied, keep only PRs whose
reviewRequestsinclude that team slug or one of its members; resolve members withgh api /orgs/<org>/teams/<slug>/memberswhen the filter is a team slug. Done when: the team filter is applied or confirmed absent. - If a repository scope is supplied, drop any PR whose repository is not in the supplied set. Done when: the repository filter is applied or confirmed absent.
- Build a table with columns: Repository, PR (title and number), Author, URL, Reason (e.g., "review requested", "team: "). Done when: the table is built with all five columns.
- If the table is empty, return a no-results report stating that no unread review requests matched the filters. Done when: the table or no-results report is returned.
What ships with it
1 file 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.
- 6d ago First seen · 49 lines · 38 tokens per session scan A 30679bbe5c99
gh-review-requests is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (36 stars, last pushed 3d ago), licensed Apache-2.0. It adds 38 tokens to every session and 836 once invoked, about $0.0002 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 2026-09-06.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…