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 Jarroslav/agentic-os --skill repo-audit-guidesgit clone --depth 1 https://github.com/Jarroslav/agentic-osWrote 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/jarroslav/agentic-os/repo-audit-guides)<a href="https://agentmods.dev/skills/jarroslav/agentic-os/repo-audit-guides"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/repo-audit-guides/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/jarroslav/agentic-os/repo-audit-guides"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/repo-audit-guides.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00153 | $0.02845 |
| Opus 5 | $0.00077 | $0.01422 |
| Sonnet 5 | $0.00031 | $0.00569 |
| Haiku 4.5 | $0.00015 | $0.00284 |
Grade A, and why
repo-audit-guides 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 11d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Audit Guides
Survey what a repository already tells its coding agents, then hand the next step a per-surface plan. This is the audit that runs before knowledge planting — the later repo-guides foundation step that installs factory-owned guidance under .agentic/guides/. You look, you reason, you report. You do not touch anything.
This is a readiness analysis, not a report card. Abstract quality scoring is banned: no letter grades, no 1-10, no "documentation health: 72%". Every claim rides on cited evidence and resolves to one concrete foundation action.
When to use
Trigger on requests to survey / audit / inspect / assess / review:
- repo documentation, README, CONTRIBUTING,
docs/, ADRs, runbooks, architecture or onboarding material; - assistant instructions and entrypoints —
AGENTS.md,CLAUDE.md,GEMINI.md,.github/copilot-instructions.md; - Claude Code / Codex / Gemini / GitHub Copilot / Cursor setup;
- assistant assets — commands, skills, subagents, hooks, settings, prompts, memory files;
- whether the repo is ready for knowledge planting / foundation.
Blast radius
R0 — read-only. You inventory and report; you never write run artifacts, repo files, or external side-effects. Nothing you do requires a gate because nothing you do mutates state.
Read-only contract
Strictly non-mutating. You MUST NOT:
- write, create, or edit guides, entrypoints, configs, hooks, settings, or any file;
- install, publish, push, open PRs, or run migrations / formatters / test suites / package installs;
- mutate caches or lockfiles;
- run any destructive command.
Allowed shell is inspection only: pwd, find, rg, ls, sed -n, wc -l, and read-only git (git status, git branch --show-current, git log, git diff --name-only). Narrow noisy commands before running them; adapt every path to what actually exists in the tree.
Scoping rules
.agentic/ is ignored by default. Pre-existing .agentic/ and .agentic/guides/ state is NOT inventoried and NOT rated — unless one of these holds:
What ships with it
8 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.
- 11d ago First seen · 231 lines · 0 tokens per session scan A 5099fabcb2c5
repo-audit-guides is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 153 tokens to every session and 2,845 once invoked, about $0.0008 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 2026-08-31.
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…