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.
npx agentmods add instructions/vincentwei1021/agent-toolbox/claude-mdgit clone --depth 1 https://github.com/Vincentwei1021/agent-toolboxWrote 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.
[](https://agentmods.dev/instructions/vincentwei1021/agent-toolbox/claude-md)<a href="https://agentmods.dev/instructions/vincentwei1021/agent-toolbox/claude-md"><img src="https://agentmods.dev/badge/instructions/vincentwei1021/agent-toolbox/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01180 | $0.01180 |
| Opus 5 | $0.00590 | $0.00590 |
| Sonnet 5 | $0.00236 | $0.00236 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
agent-toolbox CLAUDE.md 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 3d 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.
- Manual testing via curl or the /playground page How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Agent Toolbox API
Project Overview
Production REST API providing 13 data tools for AI agents. Also serves as an MCP server via SSE transport.
Architecture
src/
├── index.ts # Entry point — createServer() + getRequestListener() for raw SSE support
├── openapi.ts # OpenAPI 3.0 spec (served at /v1/docs)
├── routes/ # Hono route handlers (one file per endpoint)
│ ├── search.ts # /v1/search — DuckDuckGo web search
│ ├── extract.ts # /v1/extract — URL content extraction (Readability)
│ ├── weather.ts # /v1/weather — Open-Meteo forecasts
│ ├── finance.ts # /v1/finance — Yahoo Finance quotes + exchange rates
│ ├── screenshot.ts # /v1/screenshot — Playwright browser screenshots
│ ├── email.ts # /v1/validate-email — Email validation (MX, SMTP)
│ ├── translate.ts # /v1/translate — Google Translate (free)
│ ├── geoip.ts # /v1/geoip — ip-api.com geolocation
│ ├── news.ts # /v1/news — Google News RSS
│ ├── whois.ts # /v1/whois — Domain WHOIS lookup
│ ├── dns.ts # /v1/dns — DNS record queries
│ ├── pdfExtract.ts # /v1/pdf-extract — PDF text extraction
│ ├── qrcode.ts # /v1/qr — QR code generation
│ ├── auth.ts # /v1/auth/* — API key registration + usage
│ ├── billing.ts # /v1/billing/* — Creem subscription management
│ ├── landing.ts # / — Landing page (HTML)
│ ├── docsPage.ts # /docs — Interactive docs page (HTML)
│ ├── playground.ts # /playground — API playground (HTML)
│ └── seo.ts # /robots.txt, /sitemap.xml
├── services/ # Business logic (one file per endpoint)
├── middleware/ # Auth, rate limiting, usage tracking
├── mcp-sse.ts # MCP SSE server (13 tool definitions)
├── cache.ts # LRU cache with TTL
└── db.ts # SQLite via better-sqlite3
docs/
openapi.json # Static copy (NOT the served spec — src/openapi.ts is canonical)
data/
agent-toolbox.db # SQLite DB (api_keys, usage, monthly_usage tables)
integrations/
langchain/ # langchain-agent-toolbox PyPI package
llamaindex/ # llamaindex-agent-toolbox PyPI package
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.
- 3d ago First seen · 88 lines · 1,180 tokens per session scan A 8e750f0f2928
agent-toolbox CLAUDE.md is an instructions file published in the GitHub repository Vincentwei1021/agent-toolbox (6 stars, last pushed 5mo ago), licensed MIT. It adds 1,180 tokens to every session, about $0.0059 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.
Other instructions, from other repositories
pfsense-mcp-server AGENTS.md
Instructions for night4me/pfsense-mcp-server, covering pfsense mcp server, architecture and security, development workflow, long-running validation and test parallelism.
pdf-toolkit-mcp CLAUDE.md
Instructions for AryanBV/pdf-toolkit-mcp, covering pdf-toolkit-mcp, 1. project overview, 2. tech stack, 3. project structure and 4. mcp sdk patterns.
clawstash CLAUDE.md
Claude Code instructions for fo0/clawstash, covering claude.md -- project guide, session start -- read order, workflow triggers, output languages and performance / modes.
sui-mcp CLAUDE.md
Claude Code instructions for 0xfreak0/sui-mcp, covering sui-mcp, stack, architecture, which transport to use and archive fallback.
datadog-mcp CLAUDE.md
Instructions for dreamiurg/datadog-mcp, covering agent instructions, project, stack, commands and releases.
spotify-mcp-server CLAUDE.md
Claude Code instructions for NovaLux12/spotify-mcp-server, covering spotifymcp — claude code rules, spotify api reference, authorization, redirect uris and oauth scopes.