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/nervsystems/osmmcp/claude-mdgit clone --depth 1 https://github.com/NERVsystems/osmmcpWrote 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/nervsystems/osmmcp/claude-md)<a href="https://agentmods.dev/instructions/nervsystems/osmmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nervsystems/osmmcp/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 | $0.02107 | $0.02107 |
| Opus 5 | $0.01053 | $0.01053 |
| Sonnet 5 | $0.00421 | $0.00421 |
| Haiku 4.5 | $0.00211 | $0.00211 |
Grade A, and why
osmmcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build and Development Commands
Building
# Build all packages
go build -v ./...
# Build the main binary
go build -o osmmcp ./cmd/osmmcp
# Build with version information
VERSION=$(git describe --tags --always)
COMMIT=$(git rev-parse --short HEAD)
BUILD_DATE=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
go build -ldflags="-X main.buildVersion=$VERSION -X main.buildCommit=$COMMIT -X main.buildDate=$BUILD_DATE" -o osmmcp ./cmd/osmmcp
Running the Server
Stdio Transport (Default)
# Run with stdio transport for Claude Desktop integration
./osmmcp
# Run with debug logging
./osmmcp --debug
HTTP+SSE Transport (Anthropic API Integration)
# Enable HTTP+SSE dual transport for remote MCP clients
./osmmcp --enable-http --http-addr :7082
# With authentication
./osmmcp --enable-http --http-addr :7082 --http-auth-type bearer --http-auth-token your-secret
# With custom base URL for external access
./osmmcp --enable-http --http-addr :7082 --http-base-url https://your-domain.com
Monitoring and Health Checks
# Enable monitoring server (enabled by default)
./osmmcp --enable-monitoring --monitoring-addr :9090
# Disable monitoring
./osmmcp --enable-monitoring=false
# Run with both HTTP transport and monitoring
./osmmcp --enable-http --http-addr :7082 --enable-monitoring --monitoring-addr :9090
HTTP Transport Configuration
--enable-http: Enable HTTP+SSE transport (disabled by default)--http-addr: HTTP server address (default: ":7082")--http-base-url: Base URL for service discovery (auto-detected if empty)--http-auth-type: Authentication type - "none", "bearer", or "basic" (default: "none")--http-auth-token: Authentication token/credentials
Monitoring Configuration
--enable-monitoring: Enable Prometheus metrics and health endpoints (default: true)--monitoring-addr: Monitoring server address (default: ":9090")
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.
- 5d ago First seen · 261 lines · 2,107 tokens per session scan A 1cc19ff53584
osmmcp CLAUDE.md is an instructions file published in the GitHub repository NERVsystems/osmmcp (28 stars, last pushed 5mo ago), licensed MIT. It adds 2,107 tokens to every session, about $0.0105 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
pumperly-mcp CLAUDE.md
Claude Code instructions for GeiserX/pumperly-mcp, covering claude.md — pumperly-mcp, tech stack, development, build and run (http transport).
easy-notion-mcp CLAUDE.md
Claude Code instructions for Grey-Iris/easy-notion-mcp, covering easy-notion-mcp, open source context, .meta/ publication policy (hybrid, 2026-07-02), standing priorities and commands.
adeu GEMINI.md
Gemini CLI instructions for dealfluence/adeu, covering adeu — native track changes for ai, available tools, readdocx, processdocumentbatch and applytextrevision.
geolens CLAUDE.md
Claude Code instructions for geolens-io/geolens: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Guanlan CLAUDE.md
Instructions for shenyangs/Guanlan, covering claude.md, project, durable memory surfaces, development commands and core structure.
MCP-Airflow-API copilot-instructions.md
Instructions for call518/MCP-Airflow-API, covering copilot instructions for mcp-airflow-api, project architecture, critical patterns, functions.py - persistent session with retry strategy and standard pattern in airflowapi.py.