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/aether-platform/circus-mcp/claude-mdgit clone --depth 1 https://github.com/aether-platform/circus-mcpWrote 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/aether-platform/circus-mcp/claude-md)<a href="https://agentmods.dev/instructions/aether-platform/circus-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aether-platform/circus-mcp/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 | $0.00959 | $0.00959 |
| Opus 5 | $0.00479 | $0.00479 |
| Sonnet 5 | $0.00192 | $0.00192 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
circus-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 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.
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 — 140 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
CircusMCP is a Domain-Driven Design (DDD) process management system that integrates Circus process manager with the Model Context Protocol (MCP). It enables AI agents to control development applications through standardized MCP tools and resources.
Architecture
The system follows a layered DDD architecture:
Controller → Service → Domain ← Infrastructure
- Controller Layer (
src/controller/): MCP protocol handling and external interfaces - Service Layer (
src/service/): Application logic and use cases - Domain Layer (
src/domain/): Business logic and domain models (framework-independent) - Infrastructure Layer (
src/infrastructure/): Data access and external system integration
Key components:
- ProcessService: Manages Circus watchers and process lifecycle
- LogService: Background log processing with pattern classification
- MCPController: JSON-RPC 2.0 protocol implementation for AI agent communication
- Repository Pattern: Abstracted data access (currently in-memory, extensible to file/database)
Development Commands
Installation and Setup
# Install dependencies with uv
uv sync
# Install development dependencies
uv sync --extra dev
# Initialize project structure
uv run python main.py init --create-dirs
# Validate configuration
uv run python main.py validate
# Start Circus daemon (in separate terminal)
uv run circusd config/circus.ini
Running the Application
# Start MCP server (main application)
uv run python app.py
# Alternative CLI interface
uv run python main.py start
# Check status
uv run python main.py status
Testing
# Run all tests
uv run pytest tests/ -v
# Run specific test categories
uv run pytest tests/test_new_architecture.py -v
uv run pytest tests/ -m "not slow"
uv run pytest tests/ -m integration
# Run with coverage
uv run pytest tests/ --cov=src --cov-report=html
# Run single test
uv run pytest tests/test_new_architecture.py::TestNewArchitectureIntegration::test_full_stack_integration -v
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 · 140 lines · 959 tokens per session scan A 57077f25503b
circus-mcp CLAUDE.md is an instructions file published in the GitHub repository aether-platform/circus-mcp (2 stars, last pushed 6mo ago), licensed MIT. It adds 959 tokens to every session, about $0.0048 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.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.