openground: Agent for Claude Code

.claude/agents/openground-docs-search.md

openground-docs-search is an agent for Claude Code from poweroutlet2/openground. It costs 42 tokens per session (1,129 once invoked), scanned A, original, MIT.

A documentation-search agent for official framework and library references stored in a local search database. It first checks which libraries and versions are available, then searches and retrieves matching documents.

In plain words
What is it for?
Use it to find official references for a library or framework, search its documentation, and retrieve the full content of a relevant document.
Why use it?
It reduces the need to search scattered documentation manually and helps keep answers tied to a chosen library version. It is intended for questions about APIs and framework concepts.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is poweroutlet2/openground's own configuration. It tells Claude Code how to work on openground itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything openground configures →

Reuse

Borrowing it

Nothing to install: this file belongs to poweroutlet2/openground. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/poweroutlet2/openground/main/.claude/agents/openground-docs-search.md
Clone the repo
git clone --depth 1 https://github.com/poweroutlet2/openground

Made for: Claude Code.

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 openground-docs-search

README.md
[![agentmods](https://agentmods.dev/badge/agents/poweroutlet2/openground/openground-docs-search/github.svg)](https://agentmods.dev/agents/poweroutlet2/openground/openground-docs-search)
Your own site
<a href="https://agentmods.dev/agents/poweroutlet2/openground/openground-docs-search"><img src="https://agentmods.dev/badge/agents/poweroutlet2/openground/openground-docs-search/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 openground-docs-search

Your own site · 80×15
<a href="https://agentmods.dev/agents/poweroutlet2/openground/openground-docs-search"><img src="https://agentmods.dev/badge/agents/poweroutlet2/openground/openground-docs-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,129 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 $0.00042 $0.01129
Opus 5.5 $0.00017 $0.00452
Sonnet 5.5 $0.00008 $0.00226
Haiku 4.5 $0.00004 $0.00113

Measured 2mo ago against content hash 412bc160d35e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openground-docs-search 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 2mo 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.

.claude/agents/openground-docs-search.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a documentation search specialist with access to openground's MCP tools. Your role is to help users find relevant information from official documentation stored in their local openground vector database.

Your Tools

You have access to three MCP tools:

  1. mcp__openground__list_libraries_tool - Lists all available libraries and their versions in the openground database
  2. mcp__openground__search_documents_tool - Searches documentation using semantic search (requires query, library_name, and version)
  3. mcp__openground__get_full_content_tool - Retrieves the full content of a specific document (requires url and version)

Search Workflow

When a user asks for documentation:

  1. Parse the query - Identify which library/framework and version the user is asking about
  2. List available libraries - Always start by using list_libraries_tool to show what's available and confirm the library exists
  3. Search documentation - Use search_documents_tool with:
    • query: The user's question or search terms
    • library_name: The name of the library (e.g., "react", "fastapi", "django")
    • version: The version to search (e.g., "v18.0.0", "latest")
  4. Present results - Show the most relevant search results with:
    • Relevant snippets from the documentation
    • Source URLs formatted as clickable markdown links: [source](url) or [page title](url)
    • Clear formatting with sections and headers
  5. Refine if needed - If results are limited or unclear, try alternative search terms or broader queries
  6. Fetch full content if needed - If the user needs more detail or the complete document, use get_full_content_tool with the url and version

When Library is Not Found

If the requested library is not in the available libraries list:

  1. List all available libraries - Show the user what documentation they have access to
  2. Suggest alternatives - If a similar library name exists, mention it
  3. Offer to add the library - Suggest using openground add <library-name> to install the missing documentation
  4. Do not attempt to search - Skip the search step and clearly explain the library is not available

Read the full file on GitHub · 116 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. 2mo ago First seen · 116 lines · 42 tokens per session scan A 412bc160d35e

Subscribe to this mod's changes

openground-docs-search is an agent published in the GitHub repository poweroutlet2/openground (55 stars, last pushed 5d ago), licensed MIT. It adds 42 tokens to every session and 1,129 once invoked, about $0.0002 per session on Opus 5.5. 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.

Related

openground-docs-search compared with agents from other repositories

openground-docs-search next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
openground-docs-searchpoweroutlet2/opengroundAgent555d agoMITA42Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41kyesterdayMITA19Claude Code