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 pr-review-canvasgit 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/pr-review-canvas)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/pr-review-canvas"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/pr-review-canvas/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/pr-review-canvas"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/pr-review-canvas.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 | $0.00043 | $0.00747 |
| Opus 5 | $0.00022 | $0.00374 |
| Sonnet 5 | $0.00009 | $0.00149 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
pr-review-canvas 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 8d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR review canvas
Contract
| Field | Bound contract |
|---|---|
| Trigger | Render a PR review in Cursor Canvas. |
| Authority | Reversible local write only. Creates one canvas artifact in the working directory. No remote, VCS, credential, paid, published, or deployed mutation. |
| Side effect | Creates a local .canvas artifact file. Overwrites any prior canvas for the same PR. |
| Done | Review canvas artifact exists with risky hunks foregrounded above safe hunks. |
Inputs
- PR diff (required): The unified diff of the pull request to review. Supplied as a file path or piped content.
- PR metadata (optional): PR title, description, and linked issue text. Improves hunk risk classification when available.
Procedure
- Read the PR diff. Parse it into individual hunks grouped by file. Done when: the diff is parsed into file-grouped hunks.
- Classify each hunk as risky or safe. A hunk is risky if it touches control flow, error handling, concurrency, public API boundaries, security-sensitive paths, or data integrity logic. A hunk is safe if it is documentation-only, import reordering, formatting, or trivial renaming with no behavioral change. Done when: every hunk is classified as risky or safe.
- Within each file, place risky hunks before safe hunks while preserving the file order from the diff. This foregrounds the hunks most likely to contain defects. Done when: risky hunks precede safe hunks within each file with file order preserved.
- Create a review block for each hunk containing the file path, hunk line range, diff text, and a risk annotation that explains the classification. Done when: every hunk has a review block with path, range, diff text, and risk annotation.
- Assemble the canvas document with a PR metadata summary, followed by risky hunk blocks and then safe hunk blocks. Make each block a distinct canvas section. Done when: the canvas document is assembled with metadata, risky blocks, then safe blocks.
- Write the canvas document to
<pr-identifier>.canvasin the working directory. Overwrite the file if it exists. Done when: the.canvasfile is written to the working directory.
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.
- 8d ago First seen · 43 lines · 43 tokens per session scan A ccc1f832af42
pr-review-canvas is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (36 stars, last pushed 3d ago), licensed Apache-2.0. It adds 43 tokens to every session and 747 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 2026-09-04.
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…