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 review-plugin-submissiongit 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/review-plugin-submission)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/review-plugin-submission"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/review-plugin-submission/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/review-plugin-submission"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/review-plugin-submission.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 | $0.00051 | $0.00859 |
| Opus 5 | $0.00026 | $0.00430 |
| Sonnet 5 | $0.00010 | $0.00172 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
review-plugin-submission 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review plugin submission
Contract
| Field | Bound contract |
|---|---|
| Trigger | Final marketplace-readiness review of an agent plugin. |
| Authority | No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | Chat output only; no file writes, no credential use, no remote calls beyond reads needed for the audit. |
| Done | Sectioned pass/fail report and submission recommendation returned in chat. |
Inputs
- plugin_root (required): Absolute path to the plugin directory to audit.
- gate_rules_path (optional): Absolute path to a gate rules file that defines the named gates, each gate's pass condition, and the exact failure message for its fail path. When it is omitted, the audit runs the built-in default gates defined in step 1.
Procedure
- Read the gate rules file at
gate_rules_path. When it is omitted, audit with the built-in default gates instead: manifest-present (step 2), manifest-complete (step 3), and file-valid (step 4a); these defaults define no allowlist entries. Parse every named gate (check, rule, or criterion block). Record each gate's pass condition and the exact failure message for its fail path. Also parse the rules file's allowlist section when present: each entry is a path prefix, and a file is allowlisted when its path relative toplugin_rootstarts with that prefix. - Reject with a failure report if
plugin_root/plugin.jsondoes not exist. - Reject with a failure report if
plugin_root/plugin.jsonlacksname,version, anddescriptionfields. - Read every file under
plugin_rootthat is reachable by traversing directories and following symlinks that resolve insideplugin_root, excluding binary blobs, node_modules, and hidden paths. Skip any symlink whose resolved target is outsideplugin_root. For each file: a. Verify the file is syntactically valid for its declared format. b. Apply each applicable gate to the file's contents. - Evaluate each named gate across all examined files. A gate fails if any file violates its condition; a gate passes only when every file that is in-scope for that gate satisfies it.
- Assemble a report with:
- Summary: one line naming every failing gate and the overall recommendation (APPROVE, APPROVE WITH WARNINGS, or REJECT).
- Gate results: for each named gate, the status (PASS / FAIL) and a one-line evidence summary.
- Warnings: for each file that violates a gate condition but whose path matches an allowlist entry parsed in step 1, the file path and the matched allowlist entry; an allowlisted violation is a warning and does not fail the gate.
- Recommendation: APPROVE (all gates pass), APPROVE WITH WARNINGS (all gates pass and allowlist triggered), or REJECT (one or more gates fail).
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 · 47 lines · 51 tokens per session scan A 65adfb0081a4
review-plugin-submission is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (36 stars, last pushed 3d ago), licensed Apache-2.0. It adds 51 tokens to every session and 859 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…