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 plan-review-tunegit 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/plan-review-tune)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/plan-review-tune"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/plan-review-tune/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/plan-review-tune"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/plan-review-tune.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 | $0.00060 | $0.00696 |
| Opus 5 | $0.00030 | $0.00348 |
| Sonnet 5 | $0.00012 | $0.00139 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
plan-review-tune 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan review tune
Contract
| Field | Bound contract |
|---|---|
| Trigger | Plan-mode enforcement hooks intercept a plan review, or the user runs /plan-review-tune |
| Authority | Reversible local writes to the plan-review question-registry and hook configuration only; no VCS, credential, paid, published, deployed, or remote mutation |
| Side effect | Local question-registry and hook configuration files under the harness config directory |
| Done | The tuned plan-review question flow is persisted |
Inputs
- Tuning request (required): one of (a) a question id plus a preference of
never-ask,always-ask, orask-only-for-one-way; (b) enable or disable question tuning; (c) inspect the current state. - Question-registry (optional): the persisted per-question preference map; treated as empty if absent.
- Developer profile (optional): the dual-track record of declared preferences versus behavior-suggested preferences; treated as empty if absent.
Procedure
- Load the question-registry and developer profile from the local harness config directory; treat absent files as empty maps. Done when: the registry and profile are loaded or treated as empty.
- For an inspect request, render the dual-track profile (declared versus behavior-suggested) and the current per-question preferences, then stop. Done when: the dual-track profile and preference map are rendered.
- For a per-question preference request, validate that the question id is a member of the plan-review question set and that the preference is one of
never-ask,always-ask,ask-only-for-one-way. Reject unknown ids or values before any write. Done when: the question id and preference are validated or rejected. - For an enable or disable request, set the question-tuning flag in the hook configuration. Done when: the flag is set in the hook configuration.
- Persist the registry and hook configuration atomically: write to a temporary file in the config directory, then rename over the target. Leave every field the request did not name unchanged. Done when: the registry and hook configuration are persisted atomically with unnamed fields unchanged.
- Re-read the persisted files and confirm the persisted state matches the request exactly. Done when: the re-read confirms the persisted state matches the request.
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 · 40 lines · 60 tokens per session scan A a93ba58e301f
plan-review-tune is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (36 stars, last pushed 3d ago), licensed Apache-2.0. It adds 60 tokens to every session and 696 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…
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…