use-agent-docs

A project rule for using curated documentation maps stored in .agents/docs/ before searching the web for project topics.

In plain words
What is it for?
Finding the right official documentation page for a project question, checking related subtopics, and deciding when to use normal web research or suggest gathering documentation.
Why use it?
It prevents repeated searching and helps the agent start with the project’s selected upstream documentation. It also highlights when those references may be out of date.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/fmind/agent-docs/use-agent-docs
Any agent
npx skills add fmind/agent-docs --skill use-agent-docs
Clone the repo
git clone --depth 1 https://github.com/fmind/agent-docs

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 894 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00051 $0.00894
Opus 5 $0.00026 $0.00447
Sonnet 5 $0.00010 $0.00179
Haiku 4.5 $0.00005 $0.00089

Measured yesterday against content hash 41a3a52318e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

use-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 yesterday.

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/use-agent-docs/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use Agent Docs

A project may carry a small curated doc set under .agents/docs/, seeded by gather-agent-docs. Each DOC.md is a navigation map — a structured index of upstream URLs grouped by section — plus a brief summary and key concepts. Consult it before doing web research for any topic that's part of the project: you'll land on the right upstream page in one hop instead of N web searches.

Workflow

  1. Check the index. cat .agents/docs/INDEX.md. If missing, this skill is a no-op — fall through to normal research. If the project has several undocumented topics worth covering, propose gather-agent-docs.
  2. Open the matching DOC.md. Read summary + key concepts to orient. The Documentation map is the main body — scan its sections for the entry that matches the question. Read sibling subtopic files (e.g. HOOKS.md) when DOC.md's "Subtopics" points at one that covers your specific question.
  3. Check the verification date. Each file's YAML frontmatter has last_verified; the [YYYY-MM-DD] in INDEX.md is the oldest among that topic's files. If the date is more than ~6 months old, or the file carries a > ⚠ Stale banner just below the frontmatter, treat captured links as hints — confirm against upstream before acting on them, and propose refresh-agent-docs when the gap is large.
  4. Fetch upstream for depth. When the question needs flag-level detail, schema fields, or a paste-ready snippet, fetch the URL directly from the map. If a Patterns section exists and covers your case, use the captured snippet (each carries an inline _Source: …_).
  5. Backfill on use (optional, on user request). After fetching upstream for depth, offer to add the captured detail to DOC.md's Patterns section — progressive enrichment, capped at ~5 entries per topic. The user opts in.
  6. Fall back to web search only when the index has no entry, the upstream link is dead, or the page is too stale to trust. When you find something the local map missed, offer to extend it via gather-agent-docs (or refresh-agent-docs if the entry exists but is stale).

Read the full file on GitHub · 40 lines

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.

  1. yesterday First seen · 40 lines · 51 tokens per session scan A 41a3a52318e1

Subscribe to this mod's changes

use-agent-docs is a skill published in the GitHub repository fmind/agent-docs (3 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 894 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 2026-08-31.

Related

Other skills, from other repositories

html-ppt-zhangzara-coral

OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.

nexu-io/open-design · 55 tokens

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

deepstream-sop

Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…

NVIDIA/skills · 219 tokens

cupynumeric-migration-readiness

Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment…

NVIDIA/skills · 173 tokens