A workflow for creating or updating `AGENTS.md` files, which give coding agents instructions about a codebase. It can generate documentation from scratch or detect and fix documentation that no longer matches the code.

It helps inspect a repository, discover project-specific rules, design a documentation hierarchy, generate agent instructions, and refresh them when the code changes.

Agents work less reliably when repository guidance is missing or outdated. This workflow checks the documentation against the current project and brings it back into alignment.

agent-docs — Skill for Claude Code by SteveVitali

Install

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.

Any agent

npx skills add SteveVitali/agent-skills --skill agent-docs

Clone the repo

git clone --depth 1 https://github.com/SteveVitali/agent-skills

Made for: Claude Code.

Or install agent-skills, the plugin that ships this one along with the rest of its 8 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/stevevitali/agent-skills/agent-docs.svg)](https://agentmods.dev/skills/stevevitali/agent-skills/agent-docs)

Your own site

<a href="https://agentmods.dev/skills/stevevitali/agent-skills/agent-docs"><img src="https://agentmods.dev/badge/skills/stevevitali/agent-skills/agent-docs.svg" alt="Measured on agentmods" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,791 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00033	$0.01791
Opus 5	$0.00016	$0.00896
Sonnet 5	$0.00007	$0.00358
Haiku 4.5	$0.00003	$0.00179

Measured 8d ago against content hash b54f1f7fa01a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agent-docs 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check-agent-docs-freshness.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/agent-docs/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Docs

One workflow with two modes, both converging docs and code onto the same target state: an accurate, AGENTS.md-standard doc hierarchy that an agent can trust cold.

bootstrap — no docs exist yet. Generate them from scratch: reconnaissance → gotcha mining → hierarchy design → generation.
refresh — docs exist but may have drifted. Detect → triage → surgical fixes → (optionally) deep semantic verification.

The modes are the same convergence loop entered at different states: a refresh that finds a severely drifted doc regenerates it with bootstrap's machinery; a refresh that finds an uncovered package bootstraps a doc for it; a bootstrap validates its output with refresh's drift detector. Both modes finish through the same shared tail below.

All docs produced in either mode MUST conform to the Doc Authoring Guidelines — read that file before generating or editing any doc.

Phase 0 — Resolve scope and mode

Use the user-provided scope, or default to . (the entire repo). Then run the drift detector once:

// turbo

bash scripts/check-agent-docs-freshness.sh <scope>

(The script lives in this skill's scripts/ directory; run it from the repo root. It writes a structured report to /tmp/agent-docs-freshness.json.)

Mode resolution:

User said	Detector found	Mode
nothing	`docsScanned: 0`	`bootstrap`
nothing	docs exist	`refresh`
`bootstrap`	docs exist	Confirm intent. Then: fill gaps only — generate docs for uncovered areas via bootstrap; existing docs are never clobbered, they're refresh candidates.
`refresh`	`docsScanned: 0`	Report "nothing to refresh" and suggest bootstrap. Stop.

Phase 1 — Execute the mode core

bootstrap → follow modes/bootstrap.md (reconnaissance, gotcha & convention discovery, hierarchy design, generation, optional --cross-repo integration surface).
refresh → follow modes/refresh.md (triage the detector report, fix critical/moderate issues, fill coverage gaps, rewrite severely drifted docs, optional --deep semantic verification). The report from Phase 0 is the input — don't re-run the detector to start.

Read the full file on GitHub · 182 lines

Files

What ships with it

4 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.

Changes

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 · 182 lines · 33 tokens per session scan A b54f1f7fa01a

Subscribe to this mod's changes

agent-docs is a skill published in the GitHub repository SteveVitali/agent-skills (9 stars, last pushed 6d ago), licensed MIT. It adds 33 tokens to every session and 1,791 once invoked, about $0.0002 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.

Building agents Claude Code Writing and docs agent-skills ai-agents developer-tools

haiku

When writing a haiku for this bot, follow these conventions.

agno-agi/agno · 0 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

printing-press-import

Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…

mvanhorn/cli-printing-press · 104 tokens

agent-docs