Install
$ agentstack add skill-fmind-agent-docs-use-agent-docs ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
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
- 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, proposegather-agent-docs. - 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) whenDOC.md's "Subtopics" points at one that covers your specific question. - Check the verification date. Each file's YAML frontmatter has
last_verified; the[YYYY-MM-DD]inINDEX.mdis the oldest among that topic's files. If the date is more than ~6 months old, or the file carries a> ⚠ Stalebanner just below the frontmatter, treat captured links as hints — confirm against upstream before acting on them, and proposerefresh-agent-docswhen the gap is large. - 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: …_). - 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. - 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(orrefresh-agent-docsif the entry exists but is stale).
Failure modes
INDEX.mdlists a topic but/DOC.mdis missing → fall through to web research; flag the broken entry for the user and proposegather-agent-docsto repair.DOC.mdhas no frontmatter → treat as undated. Proposerefresh-agent-docsso the verification metadata gets reinstated.- A subtopic file is referenced from
DOC.mdbut absent on disk → fall through to web research and flag for repair. - A URL in the documentation map is dead (404, moved) → web-search for the current equivalent, use that upstream, and propose
refresh-agent-docsto repair the map. last_verifiedis in the future → likely a manual edit error; treat as undated and surface to the user.
When not to use local docs
- Questions about the user's own code or recent changes — read the source or
git loginstead. - Genuinely fresh information (today's release notes, a breaking change in the last week) — go to upstream directly.
- Topics the project does not actually use — local docs scope to project topics.
Pairing
gather-agent-docs— seeds and extends.agents/docs/; deepens with captured snippets on request.refresh-agent-docs— re-verifies the documentation map against upstream and bumpslast_verifieddates.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: fmind
- Source: fmind/agent-docs
- License: MIT
- Homepage: https://fmind.github.io/agent-docs/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.