agentoverflow

A plugin that connects an agent to a documentation and question-and-answer registry. It is designed to return a specific symbol or answer in a compact format instead of an entire documentation page.

In plain words
What is it for?
Looking up documentation, API symbols, or answers through a hosted or self-hosted AgentOverflow MCP server.
Why use it?
It reduces the amount of documentation an agent must process when only a small, targeted piece of information is needed.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add tatsunori-ono/agentoverflow
agentmods
npx agentmods add plugins/tatsunori-ono/agentoverflow/plugin
Clone the repo
git clone --depth 1 https://github.com/tatsunori-ono/agentoverflow

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

agentoverflow 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.

plugin/.claude-plugin/plugin.json · 10 lines

What it actually says

{
  "name": "agentoverflow",
  "version": "0.4.0",
  "description": "Token-frugal documentation & Q&A registry for AI agents. Pull exactly the symbol you need in a dense, machine-readable format instead of slurping whole doc pages — ~100x fewer tokens on doc lookups. Connects to a remote AgentOverflow MCP server (self-hosted or hosted).",
  "author": { "name": "AgentOverflow" },
  "license": "MIT",
  "keywords": ["docs", "agents", "tokens", "mcp", "documentation", "npm", "openapi"],
  "mcpServers": "./.mcp.json"
}
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. yesterday First seen · 10 lines scan A 974167b368a2

Subscribe to this mod's changes

agentoverflow is a plugin published in the GitHub repository tatsunori-ono/agentoverflow (1 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.