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 visual-diff-reviewgit 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/visual-diff-review)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/visual-diff-review"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/visual-diff-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/outlinedriven/odin-claude-plugin/visual-diff-review"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/visual-diff-review.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 | $0.00057 | $0.00677 |
| Opus 5.5 | $0.00023 | $0.00271 |
| Sonnet 5.5 | $0.00011 | $0.00135 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
visual-diff-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 1mo 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual diff review
Contract
| Field | Bound contract |
|---|---|
| Trigger | Diff review of a branch, commit, range, PR, or working tree against main or master by default |
| Authority | Write only named local artifacts; rollback path stated before mutation |
| Side effect | Writes the 7-section review page to the diagrams directory; opens it |
| Done | Scope, before/after behavior, risk, coupling, and a merge recommendation all cited from evidence |
Inputs
The diff target must be supplied: a branch name, commit hash or range, PR identifier, or working tree. The comparison base defaults to main; supply a named base only when it differs. The source is the live git diff of the named target against the named or default base.
Procedure
- Collect. Resolve the diff target to the named comparison base. Extract the full diff. Done when: the full diff is extracted against the named base.
- Scope. Enumerate every file and component affected. Classify the change surface. Done when: every affected file and component is enumerated and classified.
- Before/After. Describe the behavior before and after each hunk. Capture the delta in concrete terms. Done when: every hunk has a before/after behavioral description.
- Risk. Assess each risk dimension: correctness, performance, security, and compatibility. Cite evidence from the diff. Done when: every risk dimension is assessed with cited evidence.
- Coupling. Identify cross-component dependencies and side-effect surfaces within the diff. Done when: every cross-component dependency and side-effect surface is identified.
- Merge recommendation. State merge, defer, or reject with the specific evidence from steps 2–5. Done when: a merge recommendation is stated with cited evidence.
- Render. Write the 7-section review page to
diagrams/visual-diff-review.html. Open it. Done when: the page is written and opened, or the path is reported.
Failure and recovery
- Unresolvable diff target. Report the exact name that failed and stop. Do not widen scope.
- Empty diff. Report that no changes were found and stop. The done predicate does not hold.
- Unavailable external reference. Mark the affected section as
INSUFFICIENT EVIDENCEand continue. Do not fabricate citations. - Filesystem error on write. Report the error and stop. Roll back any partial file. Do not proceed to open.
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.
- 1mo ago First seen · 41 lines · 57 tokens per session scan A cbf3b6650d25
visual-diff-review is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (37 stars, last pushed 21d ago), licensed Apache-2.0. It adds 57 tokens to every session and 677 once invoked, about $0.0002 per session on Opus 5.5. 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
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…