docs-lookup

A tool for fetching clean, current documentation for a software tool or SDK into a searchable folder. It uses a site’s llms.txt index and retrieves individual pages when needed instead of copying an entire documentation site.

In plain words
What is it for?
Use it to save a documentation index, fetch specific pages on demand, or maintain a small set of verbatim reference copies.
Why use it?
It keeps documentation focused and current while avoiding a large, outdated mirror of pages you may never use.

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/hamchowderr/braynee/docs-lookup
Any agent
npx skills add hamchowderr/braynee --skill docs-lookup
Clone the repo
git clone --depth 1 https://github.com/hamchowderr/braynee

Made for: Claude Code, Codex.

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 863 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 $0.00102 $0.00863
Opus 5 $0.00051 $0.00432
Sonnet 5 $0.00020 $0.00173
Haiku 4.5 $0.00010 $0.00086

Measured 2d ago against content hash 9a6c8924af2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-lookup 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 2d 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.

skills/docs-lookup/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

docs-lookup — clean docs on demand (llms.txt model)

Put a tool/SDK's docs where you can search them, without crawling the whole site. Backed by ${CLAUDE_PLUGIN_ROOT}/scripts/mirror-llms-docs.mjs (Node built-in fetch, zero deps, cross-platform).

The model — three layers, in order

  1. Index (always). A site's root llms.txt is a curated link-map of its docs. Save it once as a navigable index note. This is the map, not the territory.
  2. On-demand (default). When you actually need a page, fetch that one page's clean-markdown route right then. Don't pre-copy pages you don't use.
  3. Curated copies (sparingly). Copy verbatim only the handful of pages you reference constantly (kept minimal, stamped verbatim-copy, re-fetched to refresh).

Never mirror a whole site. Verbatim-or-link: copied pages are stored as-is and never hand-edited — re-run the fetch to refresh.

Run it

# 1. Save the root llms.txt as an index note in <target-dir>
node "${CLAUDE_PLUGIN_ROOT}/scripts/mirror-llms-docs.mjs" index <domain> <target-dir> ["Note Name"]
#    e.g.
node "${CLAUDE_PLUGIN_ROOT}/scripts/mirror-llms-docs.mjs" index mastra.ai "<target-dir>" "Mastra Docs Index"

# 2. Copy specific clean pages verbatim into <target-dir>
node "${CLAUDE_PLUGIN_ROOT}/scripts/mirror-llms-docs.mjs" pages <target-dir> <clean-page-url> [<clean-page-url> ...]

<target-dir> is whatever folder should hold the docs (a vault docs folder, a repo docs/ dir, a scratch dir). The script hardcodes no paths.

Per-site clean-page routes

Site Root index Clean per-page route
Mastra https://mastra.ai/llms.txt append .md (e.g. .../docs/agents/overview.md) — the /llms.txt per-page route was retired 2026-07-04
Docker https://docs.docker.com/llms.txt append .md (e.g. .../engine/install.md)
other https://<domain>/llms.txt check the site's own retrieval guidance for its clean-page route

Read the full file on GitHub · 65 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. 2d ago First seen · 65 lines · 102 tokens per session scan A 9a6c8924af2b

Subscribe to this mod's changes

docs-lookup is a skill published in the GitHub repository hamchowderr/braynee (2 stars, last pushed 6d ago), licensed MIT. It adds 102 tokens to every session and 863 once invoked, about $0.0005 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens