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 audit-projectgit 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/audit-project)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/audit-project"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/audit-project.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.03244 |
| Opus 5 | $0.00025 | $0.01622 |
| Sonnet 5 | $0.00010 | $0.00649 |
| Haiku 4.5 | $0.00005 | $0.00324 |
Grade A, and why
audit-project 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Project: correct-op multi-agent audit loop
audit-project restores the invariant: no open critical/high findings remain in the selected scope. This is not a one-pass critique; it selects reviewers from evidence, applies fixes in verified batches, re-reviews only changed files, and stops only at zero critical/high, a user decision gate, or the iteration cap.
Bulk reviewer prompts live in references/review-roster.md. Consolidation, dismissal, blocked-ratio, decision-gate, and priority-routing rules live in references/false-positive-contract.md.
Sync lineage: the diff-scoped
review-fix-grill-loopskill carries adapted copies of both reference files. The reviewer prompts, common schema, false-positive clause, blocked-ratio, stall-hash, and routing rules share an ancestor; a canonical edit here must be hand-propagated toskills/review-fix-grill-loop/references/(no CI enforces it).
When to Apply / NOT
Apply when the user asks for a deep code audit, an iterative review until clean, release-readiness review, security/performance/test-quality review, post-refactor risk sweep, or a bug-hunting pass across a scope.
NOT when the user wants a read-only opinion, a single known test failure fixed, a narrow symbol explanation, dependency CVE remediation only, or a pure formatting/lint cleanup. Use the smaller direct operation instead; this loop is intentionally heavyweight.
Inputs and State
Inputs:
scope: path, glob, package, PR/diff, or.. Default..--recent: audit files touched in the last five commits plus unstaged/staged changes.--domain <reviewer>: run one reviewer domain only; still apply the same consolidation contract.--quick: single review pass; no fixes, no iteration.--resume: load.outline/audit/queue.jsonif present.--max-iterations N: default5.
State:
.outline/audit/queue.json: current scope, selected reviewers, raw reviewer output, consolidated findings, low-debt extraction, verification results, decisions, hash history..outline/audit/iterations/<n>.json: per-iteration changed files, batches, verification command/output summary, re-review result hash.
What ships with it
3 files 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 · 198 lines · 50 tokens per session scan A 9e8bbf593a21
audit-project is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 50 tokens to every session and 3,244 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 2026-08-30.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…