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/badchars/osint-mcp-server/claude-mdgit clone --depth 1 https://github.com/badchars/osint-mcp-serverWrote 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/badchars/osint-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/badchars/osint-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/badchars/osint-mcp-server/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 5.1 | $0.01238 | $0.01238 |
| Opus 5 | $0.00619 | $0.00619 |
| Sonnet 5 | $0.00248 | $0.00248 |
| Haiku 4.5 | $0.00124 | $0.00124 |
Grade A, and why
osint-mcp-server CLAUDE.md 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
OSINT MCP — the fifth project in the MCP security suite. Provides AI agents with access to OSINT data sources: Shodan, Censys, VirusTotal, SecurityTrails + public DNS/WHOIS/crt.sh/Wayback/BGP/IP geolocation.
Published as npx osint-mcp-server on npm. Public tools work without API keys; paid providers (Shodan, VT, SecurityTrails, Censys) require env vars and return descriptive messages when keys are missing.
Build & Development Commands
bun install # Install dependencies
bun run dev # Watch mode (bun --watch run src/index.ts)
bun run build # Compile for npm (tsc -p tsconfig.build.json → dist/)
npm publish # Publishes to npm (prepublishOnly runs build automatically)
npx . --help # Test local package as if installed via npx
No test framework is set up yet. When adding tests, use bun test (Bun's built-in test runner).
Architecture
Follows the same architecture as cve-mcp, github-security-mcp, cloud-audit-mcp, and hackbrowser-mcp.
Core Pattern
src/
├── index.ts # Entry point: shebang, buildToolContext(), main()
├── types/
│ └── index.ts # ToolDef, ToolContext, ToolResult interfaces + text()/json() helpers
├── protocol/
│ ├── mcp-server.ts # Creates McpServer, loops allTools to register, stdio transport
│ └── tools.ts # All ToolDef objects + allTools[] export
├── <provider>/ # One directory per data source
│ └── index.ts # API functions (fetch calls, response normalization)
└── utils/
├── rate-limiter.ts # Shared RateLimiter (prevents 429s)
└── cache.ts # TTLCache with expiry
Key Interfaces
interface ToolDef {
name: string; // e.g. "shodan_search"
description: string;
schema: Record<string, z.ZodType>; // Zod validators per param
execute: (args: Record<string, unknown>, ctx: ToolContext) => Promise<ToolResult>;
}
interface ToolContext {
config: { shodan_api_key?: string; vt_api_key?: string; /* ... */ };
// shared caches, rate limiters
}
interface ToolResult {
content: { type: "text"; text: string }[];
}
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.
- 6d ago First seen · 117 lines · 1,238 tokens per session scan A 4faf95b0f319
osint-mcp-server CLAUDE.md is an instructions file published in the GitHub repository badchars/osint-mcp-server (48 stars, last pushed 5mo ago), licensed MIT. It adds 1,238 tokens to every session, about $0.0062 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.
Other instructions, from other repositories
attack-surface-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/attack-surface-mcp-server, covering developer protocol, authorized-use posture, core rules, patterns and tool.
attack-surface-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/attack-surface-mcp-server, covering developer protocol, authorized-use posture, core rules, patterns and tool.
Cybermes AGENTS.md
Instructions for Zyrexnn/Cybermes, covering 🛡️ cybermes master operational directives (agents.md), 1. 🎯 persona & core mission, 2. ⚡ core operational principles, 3. 📁 strict target-scoped workspace & deliverables and mandatory rules for file creation.
rustchain-bounties claims.instructions.md
Instructions for Scottcjn/rustchain-bounties: Claim files are public audit records for bounty submissions and code reviews.
Threatswarm CLAUDE.md
Instructions for mukul975/Threatswarm, covering cybersecurity workspace — master context, scope enforcement (mandatory — zero exceptions), tool paths, agent delegation table and opsec defaults.
The-Scaffolding AGENTS.md
AGENTS.md instructions for Shad0wMazt3r/The-Scaffolding, covering bug bounty and ctf harness, rules and skills index.