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-canvas-htmlgit 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-html)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/pr-review-canvas-html"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/pr-review-canvas-html/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-html"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/pr-review-canvas-html.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 | $0.00058 | $0.01538 |
| Opus 5 | $0.00029 | $0.00769 |
| Sonnet 5 | $0.00012 | $0.00308 |
| Haiku 4.5 | $0.00006 | $0.00154 |
Grade A, and why
pr-review-canvas-html 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR review canvas HTML
Contract
| Field | Bound contract |
|---|---|
| Trigger | Render a GitHub PR as standalone review HTML. |
| Authority | Reversible-local: writes confined to /tmp. No VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | Writes one self-contained HTML file to /tmp and serves it on a fixed localhost port. |
| Done | A self-contained HTML artifact at /tmp/pr-review-.html, served on localhost. |
Inputs
- PR URL or identifier (required): a GitHub PR web URL or
owner/repo#<number>. The model extracts{owner},{repo},{number}. - PR data (fetched):
gh api repos/{owner}/{repo}/pulls/{number}, file list, diff, and comments fetched during step 2.
Procedure
-
Parse the PR identifier. Extract
{owner},{repo},{number}from the provided URL orowner/repo#numberstring. Stop if extraction fails. Done when: owner, repo, and number are extracted. -
Fetch PR data in parallel. Run these
gh apicalls concurrently:gh api repos/{owner}/{repo}/pulls/{number} --jq '{title, body, user: .user.login, state, additions, deletions, changed_files, base: .base.ref, head: .head.ref}' gh api repos/{owner}/{repo}/pulls/{number}/files --paginate --jq '.[] | {filename, status, additions, deletions, patch}' gh api repos/{owner}/{repo}/pulls/{number}/comments --jq '.[] | {user: .user.login, body, path, line}'Stop if any call fails or returns no data. Done when: all three API calls return data.
-
Analyze the PR and write body HTML. Read the diffs, understand the PR, and write the
<body>content directly as HTML. Use any structure that fits the PR: a header with title, PR number, author, and stats; a summary box explaining the PR in plain English; core file sections with annotations and diffs; boilerplate files collapsed by default; a review checklist at the bottom. Include<div data-diff="<target>">placeholders where diffs should render. Add collapsible boilerplate sections, inline code references, and callout boxes for warnings. Done when: the body HTML is written with data-diff placeholders for every diff target.
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 · 99 lines · 58 tokens per session scan A 0548f9bbd2b7
pr-review-canvas-html is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 58 tokens to every session and 1,538 once invoked, about $0.0003 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…