docs-search

docs-search is a skill for Claude Code from 23blocks-OS/ai-maestro-plugins. It costs 73 tokens per session (1,762 once invoked), scanned A, original, MIT.

A tool for searching the documentation of a generated codebase before making changes. It finds function signatures, class details, APIs, comments, and existing implementation patterns.

In plain words
What is it for?
Use it to confirm an API or function signature, find an existing component pattern, or check documentation before implementing code.
Why use it?
It reduces mistakes caused by guessing how unfamiliar code or interfaces work.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the ai-maestro plugin — 8 skills, 3 hooks shipped together

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/23blocks-os/ai-maestro-plugins/docs-search
Any agent
npx skills add 23blocks-OS/ai-maestro-plugins --skill docs-search
Clone the repo
git clone --depth 1 https://github.com/23blocks-OS/ai-maestro-plugins

Made for: Claude Code.

Or install ai-maestro, the plugin that ships this one along with the rest of its 8 skills, 3 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-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/23blocks-os/ai-maestro-plugins/docs-search.svg)](https://agentmods.dev/skills/23blocks-os/ai-maestro-plugins/docs-search)
Your own site
<a href="https://agentmods.dev/skills/23blocks-os/ai-maestro-plugins/docs-search"><img src="https://agentmods.dev/badge/skills/23blocks-os/ai-maestro-plugins/docs-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,762 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00073 $0.01762
Opus 5 $0.00036 $0.00881
Sonnet 5 $0.00015 $0.00352
Haiku 4.5 $0.00007 $0.00176

Measured 6d ago against content hash 8284d6617e4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

docs-search scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Ensure AI Maestro is running: `curl http://127.0.0.1:23000/api/hosts/identity`
plugins/ai-maestro/skills/docs-search/SKILL.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRITICAL: AUTOMATIC BEHAVIOR - READ THIS FIRST

THIS IS NOT OPTIONAL. THIS IS YOUR DEFAULT BEHAVIOR.

When the user gives you ANY instruction or task, you MUST FIRST search documentation for:

  • Function signatures - What are the parameters and return types?
  • Class documentation - What methods and properties exist?
  • API documentation - How should this endpoint work?
  • Code comments - What did the author intend?

DO NOT:

  • Start implementing before checking documentation
  • Assume you know the function signature without checking
  • Skip doc search because "it's a simple task"
  • Wait for the user to ask you to check docs

ALWAYS:

  • Search docs IMMEDIATELY when you receive a task
  • Search for terms and concepts the user mentions
  • Check documentation before calling unfamiliar functions
  • Look for patterns before creating new components

The Rule: Receive Instruction → Search Docs → Then Proceed

1. User asks you to do something
2. IMMEDIATELY search docs for relevant context
3. NOW you know the correct signatures and patterns
4. NOW you can implement correctly the first time

Example - User asks to modify a service:

# IMMEDIATELY run:
docs-search.sh "PaymentService"
docs-find-by-type.sh class

Example - User mentions a function:

# IMMEDIATELY run:
docs-search.sh "validateUser"
docs-search.sh --keyword "authenticate"

Available Commands

All commands auto-detect your agent ID from the tmux session.

Search Commands

Command Description
docs-search.sh <query> Semantic search through documentation
docs-search.sh --keyword <term> Keyword/exact match search
docs-find-by-type.sh <type> Find docs by type (function, class, module, etc.)
docs-get.sh <doc-id> Get full document with all sections
docs-list.sh List all indexed documents
docs-stats.sh Get documentation index statistics

Read the full file on GitHub · 246 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. 6d ago First seen · 246 lines · 73 tokens per session scan A 8284d6617e4e

Subscribe to this mod's changes

docs-search is a skill published in the GitHub repository 23blocks-OS/ai-maestro-plugins (9 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 1,762 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

coding-investigation

Investigate unfamiliar code behavior, or answer an exact symbol's definition, callers, callees, references, impact, and cross-repository relationship questions. Use it to trace activation, ownership, data flow, configuration, registration, and runtime wiring with bounded source evidence without mutating code; do not…

evoelsewhere/evoflux · 81 tokens

skill-installer

Create, import, update, validate, or relocate portable Agent Skill bundles with SKILL.md, on-demand references, deterministic scripts, output assets, UI metadata, and EvoFlux mode settings. Use for explicit skill authoring or installation; do not use for invoking an existing skill, changing agent configuration, or…

evoelsewhere/evoflux · 71 tokens

pdf

Read, create and manipulate PDF files — extract text and tables, merge, split, rotate, reorder and delete pages, read and fill AcroForm fields, add or strip metadata, encrypt and decrypt, and generate new PDFs from HTML or from scratch. Also covers rasterising pages to images so a PDF can actually be looked at, and…

smith-network-solutions/threadknot · 88 tokens

easd-implement

Implement bounded work for an active EASD run under its accepted specification and AC ownership. Use only when EASD has authorized implementation; do not use while the run is Intent, authoring, draft, or merely accepted.

evoelsewhere/evoflux · 51 tokens

easd-verify

Run the final EASD integration and evidence gate against accepted AC policies, then prepare a convergence recommendation. Use after implementation and any required independent review; not for task-local code review or ordinary tests outside EASD.

evoelsewhere/evoflux · 49 tokens

coding-debugging

Use this skill when a test, build, runtime path, integration, or concurrent workflow fails and the responsible condition is unknown. It is for reproducing symptoms, isolating a cause, fixing it when authorized, and proving the regression; do not use it for general code exploration, proactive review, or an…

evoelsewhere/evoflux · 71 tokens