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 rhtevan/agentfs --skill agentfs-readme-auditgit clone --depth 1 https://github.com/rhtevan/agentfsWrote 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/rhtevan/agentfs/agentfs-readme-audit)<a href="https://agentmods.dev/skills/rhtevan/agentfs/agentfs-readme-audit"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/agentfs-readme-audit.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.01710 |
| Opus 5 | $0.00012 | $0.00855 |
| Sonnet 5 | $0.00005 | $0.00342 |
| Haiku 4.5 | $0.00002 | $0.00171 |
Grade A, and why
agentfs-readme-audit 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 7d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentFS README Audit
Semantic alignment check for ~/.agents/README.md against the actual
state of the AgentFS USER scope. Designed to complement the
deterministic README staleness check in pre-push-scan.sh.
Overview
| Property | Value |
|---|---|
| Version | 1.1 |
| Trigger | Automatic during Guardrail #10 (Git Push Safety), or explicit |
| Scope | USER scope ~/.agents/README.md only |
| Dependencies | ls, grep, wc, cat — data gathering is deterministic |
| LLM required | Yes — alignment assessment is semantic |
When This Runs
This skill activates in two scenarios:
1. During Pre-Push (Guardrail #10)
Run this skill when any agentfs files are staged:
skills/,knowledge/, orAGENTS.mdappear ingit diff --cached --name-onlypre-push-scan.shemitsREADME_AUDIT_REQUIREDin its output
README.md does not need to be staged — the audit compares the
existing README against the staged changes to detect drift.
If README.md is also staged, the audit additionally validates whether
the in-progress README update is sufficient.
Flow:
git diff --cached --name-only
└─ skills/ or knowledge/ or AGENTS.md staged?
└─ YES → pre-push-scan.sh emits README_AUDIT_REQUIRED
└─ Agent runs this skill (semantic comparison)
└─ If aligned → proceed to push approval
└─ If drift detected → report specifics, recommend fixes
└─ User decides whether to fix before push
└─ NO → skip skill entirely
2. Explicit Invocation
The user asks directly:
"audit readme" · "check readme alignment" · "readme drift"
Execution Steps
Step 1: Gather Actual State
Collect ground truth from the filesystem. All commands are deterministic — no LLM involvement yet.
# Skill count and list
ls -d ~/.agents/skills/*/SKILL.md 2>/dev/null | sed 's|.*/skills/||;s|/SKILL.md||' | sort > /tmp/readme-audit-skills.txt
SKILL_COUNT=$(wc -l < /tmp/readme-audit-skills.txt)
# Knowledge bundle count and list
ls -d ~/.agents/knowledge/*/index.md 2>/dev/null | sed 's|.*/knowledge/||;s|/index.md||' | sort > /tmp/readme-audit-knowledge.txt
KNOWLEDGE_COUNT=$(wc -l < /tmp/readme-audit-knowledge.txt)
# Skill categories (extract from skills/index.md)
grep '^|' ~/.agents/skills/index.md | grep -v '^| Name\|^|---' > /tmp/readme-audit-skill-index.txt
# Directory structure (top level)
tree -L 2 --dirsfirst -I '__pycache__|node_modules' ~/.agents/ > /tmp/readme-audit-tree.txt 2>/dev/null
# Guardrail list from seed template
grep -oP '### [0-9]+\. .+' ~/.agents/skills/agentfs-setup/scripts/seed-agents-md.sh > /tmp/readme-audit-guardrails.txt 2>/dev/null
# Template version
grep -oP 'version:\s*"\K[^"]+' ~/.agents/skills/agentfs-setup/SKILL.md > /tmp/readme-audit-template-version.txt 2>/dev/null
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.
- 7d ago First seen · 169 lines · 23 tokens per session scan A fa58f74ed9e4
agentfs-readme-audit is a skill published in the GitHub repository rhtevan/agentfs (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,710 once invoked, about $0.0001 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…
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…