safebreach-mcp: Instructions file for Claude Code

CLAUDE.md

safebreach-mcp CLAUDE.md is an instructions file for Claude Code from SafeBreach/safebreach-mcp. It costs 12,459 tokens per session, scanned A, original, BSD-3-Clause.

Project instructions for SafeBreach’s MCP server, which connects AI coding tools to SafeBreach development services. MCP is a standard way for AI tools to call external tools.

In plain words
What is it for?
Use them when starting the project, running its local servers, handling authentication, or changing code that connects to external SafeBreach services.
Why use it?
They enforce a secure launch process and help prevent real access tokens or other secrets from being committed to the codebase.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is SafeBreach/safebreach-mcp's own configuration. It tells Claude Code how to work on safebreach-mcp 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 safebreach-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SafeBreach/safebreach-mcp. 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/SafeBreach/safebreach-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/SafeBreach/safebreach-mcp

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 safebreach-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/safebreach/safebreach-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/safebreach/safebreach-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/safebreach/safebreach-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/safebreach/safebreach-mcp/claude-md/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 safebreach-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/safebreach/safebreach-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/safebreach/safebreach-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12,459 This file is loaded in full into every session.
When invoked 12,459 The same file — it is already loaded in full.
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 $0.12459 $0.12459
Opus 5 $0.06229 $0.06229
Sonnet 5 $0.02492 $0.02492
Haiku 4.5 $0.01246 $0.01246

Measured yesterday against content hash f6146937f40f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

safebreach-mcp 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 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.

CLAUDE.md · 850 lines

How it starts

The opening of the file, as written. The whole thing — 850 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.

🚨 SECURITY FIRST - CRITICAL FOR CLAUDE

IMPORTANT: Claude should always be launched using the secure launcher to ensure full project context and security awareness:

# ALWAYS use this command to launch Claude:
./claude-launcher.sh

This ensures Claude has:

  • ✅ Complete project architecture and best practices knowledge
  • ✅ Security context and awareness of token handling rules
  • ✅ Current git status and environment configuration
  • ✅ Pre-validated secure working environment

NEVER commit real secrets:

  • Use placeholders like your-token-here, REPLACE_WITH_ACTUAL_TOKEN
  • Use environment variables: ${API_TOKEN}, $SAFEBREACH_TOKEN
  • Pre-commit hooks will automatically scan for and block real secrets

📚 See TEAM_WORKFLOW.md for complete security practices and development workflow.

Development Commands

Running the Multi-Server Architecture (Recommended):

# Run all servers concurrently on ports 8000-8003 (localhost-only, secure default)
uv run start_all_servers.py


# External connection support (requires authentication token)
SAFEBREACH_MCP_AUTH_TOKEN="your-secure-token" uv run start_all_servers.py --external

# External connections for specific servers only
SAFEBREACH_MCP_AUTH_TOKEN="your-token" uv run start_all_servers.py --external-data --external-utilities

# Get help with all external connection options
uv run start_all_servers.py --help

# Custom base URL for reverse proxy deployment (the streamable-http endpoint becomes /api/mcp instead of /mcp)
SAFEBREACH_MCP_BASE_URL="/api/mcp" uv run start_all_servers.py

# Combined configuration with external access and custom base URL
SAFEBREACH_MCP_AUTH_TOKEN="your-token" SAFEBREACH_MCP_BASE_URL="/api/mcp" uv run start_all_servers.py --external

# Single-tenant deployment (SafeBreach internal use)
export DATA_URL="http://localhost:3400"
export CONFIG_URL="http://localhost:3401" 
export SIEM_URL="http://localhost:3402"
export ACCOUNT_ID="your-account-id"
export console_name_apitoken="your-api-token"
uv run start_all_servers.py

Read the full file on GitHub · 850 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. yesterday Changed · +3 lines · +75 tokens per session f6146937f40f
  2. 3d ago Changed · -10 lines · -141 tokens per session e580ad2b1dac
  3. 7d ago Changed · +29 lines · +663 tokens per session e85fb34916e4
  4. 11d ago First seen · 828 lines · 11,862 tokens per session scan A 5112615e1fd2

Subscribe to this mod's changes

safebreach-mcp CLAUDE.md is an instructions file published in the GitHub repository SafeBreach/safebreach-mcp (7 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 12,459 tokens to every session, about $0.0623 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens