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 agentmods add skills/fmind/agent-docs/refresh-agent-docsnpx skills add fmind/agent-docs --skill refresh-agent-docsgit clone --depth 1 https://github.com/fmind/agent-docsWhat 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 | $0.00061 | $0.01447 |
| Opus 5 | $0.00030 | $0.00724 |
| Sonnet 5 | $0.00012 | $0.00289 |
| Haiku 4.5 | $0.00006 | $0.00145 |
Grade A, and why
refresh-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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refresh Agent Docs
Keeps .agents/docs/ honest. Each DOC.md and <SUBTOPIC>.md carries YAML frontmatter (last_verified, optional upstream_commit, sources); this skill re-verifies, applies fixes, and bumps the date.
Pair with gather-agent-docs (seed entries, deepen on request) and use-agent-docs (read them).
Scope
- Default: every entry in
INDEX.md— every*.mdunder each topic's directory. - Topic-targeted: when the user names slugs ("refresh gemini-cli", "refresh cloud-run and firebase"), refresh every
*.mdin those directories. - Subtopic-targeted: when the user names a specific file ("refresh gemini-cli/hooks"), refresh only that file and re-bump the topic's
INDEX.mddate to the new oldest. - No-op if
.agents/docs/INDEX.mddoes not exist — proposegather-agent-docsinstead.
Smart refresh
Before re-fetching upstream content, try the cheap paths in order. The richer the page's frontmatter, the more refreshes short-circuit.
- Commit-pin shortcut. If
upstream_commitis set and matches upstream HEAD (e.g. via the repo URL's HEAD SHA), the page is verified by definition. Bumplast_verified, markunchanged, done. - Changelog shortcut. Fetch
sources.changelog(orsources.release) and filter entries dated afterlast_verified. None matching → bumplast_verified, markunchanged, done. - Link-rot scan. HEAD-check every URL in the Documentation map. All resolve, no nav drift, no T2 snippet sources changed → bump and done.
- Targeted re-verify. Some changelog entries touch surfaces in the map (or some links 404) → re-fetch the topic's nav source to detect renamed/removed/added pages, and re-fetch each affected T2 snippet's
_Source: …_page. - Full re-fetch. No
upstream_commit, no changelog, smart paths inconclusive → re-fetch the topic's nav source and walk every captured T2 snippet.
Per-file workflow
For each *.md in scope (DOC.md plus any subtopic files):
- Read the local page — frontmatter, summary, key concepts, Documentation map, optional Patterns.
- Run smart refresh to pick the path. For dead links (404, moved), search for the current equivalent and substitute it. If no replacement exists, drop the entry and note the gap in the report.
- Diff and fix when re-verifying:
- URL in the map moved → update.
- Page renamed in upstream nav → update title and one-line hook.
- New page in upstream nav covering a meaningful surface → add to map.
- Page removed upstream → drop entry.
- Captured T2 snippet drifted → update or remove. Add a new snippet only on user request (deepen).
- Section restructured upstream → mirror the new grouping.
- Bump the frontmatter
last_verifiedto today and refreshupstream_commitwhen applicable. After all of a topic's files are processed, setINDEX.md's[YYYY-MM-DD]for that topic — andINDEX.md's ownlast_verifiedfrontmatter — to the oldestlast_verifiedamong that topic's files. - Stale banner. When a page can't be re-verified this session (upstream unreachable, login-walled, rate-limited) or its
last_verifiedis more than 6 months old after this run, insert at the top of the body (just below the frontmatter):> ⚠ Stale (verified YYYY-MM-DD). Confirm captured details upstream before acting.Remove the banner automatically on the next successful re-verify. - Record the outcome for the report.
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.
- yesterday First seen · 81 lines · 61 tokens per session scan A 10a1350d1d88
refresh-agent-docs is a skill published in the GitHub repository fmind/agent-docs (3 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 1,447 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.
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.
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".
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.
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).
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…
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…