docs-lookup

docs-lookup is a skill for Claude Code from Redtropig/harness-anchor. It costs 32 tokens per session (1,632 once invoked), scanned A, original, MIT.

A lookup procedure for unfamiliar tools, programming interfaces, error messages, and libraries. It checks structured documentation first, then broader web results, and states what remains uncertain if neither helps.

In plain words
What is it for?
Use it when an unfamiliar dependency, command-line tool, API, error, or library feature needs authoritative documentation.
Why use it?
It reduces the risk of guessing about commands, APIs, configuration, or library behavior. That helps avoid fixes based on outdated or incorrect information.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the harness-anchor plugin — 14 skills, 9 commands, 5 agents, 5 hooks shipped together

Good fit Use it when an unfamiliar dependency, command-line tool, API, error, or library feature needs authoritative documentation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redtropig/harness-anchor/docs-lookup
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 Redtropig/harness-anchor --skill docs-lookup
Clone the repo
git clone --depth 1 https://github.com/Redtropig/harness-anchor

Made for: Claude Code.

Or install harness-anchor, the plugin that ships this one along with the rest of its 14 skills, 9 commands, 5 agents, 5 hooks.

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.

agentmods badge for docs-lookup

README.md
[![agentmods](https://agentmods.dev/badge/skills/redtropig/harness-anchor/docs-lookup/github.svg)](https://agentmods.dev/skills/redtropig/harness-anchor/docs-lookup)
Your own site
<a href="https://agentmods.dev/skills/redtropig/harness-anchor/docs-lookup"><img src="https://agentmods.dev/badge/skills/redtropig/harness-anchor/docs-lookup/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for docs-lookup

Your own site · 80×15
<a href="https://agentmods.dev/skills/redtropig/harness-anchor/docs-lookup"><img src="https://agentmods.dev/badge/skills/redtropig/harness-anchor/docs-lookup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,632 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.
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 5.1 $0.00032 $0.01632
Opus 5 $0.00016 $0.00816
Sonnet 5 $0.00006 $0.00326
Haiku 4.5 $0.00003 $0.00163

Measured 10d ago against content hash c95541f0e009, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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 · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docs Lookup (with fallback)

When you need authoritative information about an unfamiliar tool / API / error message / library behavior, follow this fallback chain. Each step has explicit success and failure criteria so the agent never silently degrades to guessing.

Step 1: Structured docs MCP   (Context7; or Microsoft Learn for .NET/Azure/Windows/MSVC)
   ↓ (unavailable / no match / wrong content / tool error)
Step 2: WebSearch     (broader web, recent ecosystem changes)
   ↓ (unavailable / no useful results / paywalled)
Step 3: Calibrated uncertainty (tell user what you tried + what's needed)

You do not skip steps. If Step 1 fails, you go to Step 2. If Step 2 fails, you go to Step 3. You do NOT retry Step 1 with the same query hoping for a different answer.


Step 1: Structured docs MCP — Context7, or a first-party MCP for its ecosystem

When it's the right tool: API references, configuration options, well-known libraries (React, CMake, Clang, etc.), version-specific behavior.

Two-call usage (typical Context7 / Microsoft Docs MCP shapes):

1. resolve-library-id(library_name)            → canonical id, e.g. /llvm/clang
2. get-library-docs(id, topic="<question>")    → structured snippet + citation URL

(Tool names vary by harness: mcp__Context7__*, mcp__plugin_context7_context7__*, mcp__73bcda44-…__query-docs, etc. Use whatever resolves to "Context7" in your tool inventory.)

First-party ecosystem docs MCP — prefer it over Context7 when the topic matches. Context7 is the general default for libraries, but if the question is about a specific vendor ecosystem and that vendor's docs MCP is in your inventory, it is higher-signal (first-party). The prime example: Microsoft Learn (microsoft_docs_searchmicrosoft_docs_fetch; microsoft_code_sample_search for snippets) for .NET / Azure / Windows / MSVC / Win32 topics — including MSVC compiler errors and Windows-SDK headers in C/C++ work. Same two-call shape (search → fetch) and the same failure-mode handling below; if it is absent or returns nothing useful, fall through to Context7 → WebSearch as normal. (General principle — prefer the first-party MCP for its ecosystem; not a hard dependency.)

Read the full file on GitHub · 122 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. 10d ago First seen · 122 lines · 32 tokens per session scan A c95541f0e009

Subscribe to this mod's changes

docs-lookup is a skill published in the GitHub repository Redtropig/harness-anchor (13 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,632 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 2026-08-30.