Borrowing it
Nothing to install: this file belongs to 0-SOFT/Manus-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.
curl -O https://raw.githubusercontent.com/0-SOFT/Manus-MCP/main/CLAUDE.mdgit clone --depth 1 https://github.com/0-SOFT/Manus-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/0-soft/manus-mcp/claude-md)<a href="https://agentmods.dev/instructions/0-soft/manus-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/0-soft/manus-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.
<a href="https://agentmods.dev/instructions/0-soft/manus-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/0-soft/manus-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02111 | $0.02111 |
| Opus 5.5 | $0.00844 | $0.00844 |
| Sonnet 5.5 | $0.00422 | $0.00422 |
| Haiku 4.5 | $0.00211 | $0.00211 |
Grade B, and why
Manus-MCP CLAUDE.md scanned grade B 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 2mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
For global registration, add to `~/.claude/settings.json`: How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project context for Claude Code. Loaded automatically when working in this directory.
What this is
Manus MCP — a Python 3.11+ MCP server that gives Claude Code full programmatic control over Manus.im through the official Manus API v2 (https://api.manus.ai). It implements all 30 documented endpoints, 3 composite tools, and a local webhook receiver with RSA-SHA256 verification.
The full Manus API documentation lives in ManusAPIDocs/ — that's the official mirror.
Running and verifying
# Install (one-time)
.venv/Scripts/python.exe -m pip install -e ".[dev]"
# All unit + integration tests (no live)
.venv/Scripts/python.exe -m pytest -m "not live"
# All live e2e (requires MANUS_API_KEY in .env or env)
.venv/Scripts/python.exe -m pytest -m live
# Full run + 80% coverage gate
.venv/Scripts/python.exe -m pytest -m "not live" --cov=manus_mcp --cov-fail-under=80
# Types and lint
.venv/Scripts/python.exe -m mypy --strict manus_mcp
.venv/Scripts/python.exe -m ruff check manus_mcp tests scripts
# Smoke probe (4 read-only calls)
.venv/Scripts/python.exe scripts/smoke.py
# Full live probe (writes JSON snapshots)
.venv/Scripts/python.exe scripts/live_e2e_probe.py
# MCP integration probe via mcp.client.stdio
.venv/Scripts/python.exe scripts/mcp_integration_probe.py
# List registered tools without starting the server
.venv/Scripts/python.exe scripts/list_tools.py
Test layers
| Layer | Files | Run | Dependencies |
|---|---|---|---|
| Unit | tests/test_client.py, test_schemas.py, test_storage.py, test_webhook_signature.py, test_input_schema_stability.py, test_main_smoke.py, test_registry.py |
pytest -m "not live" |
respx mock |
| Server (MCP wiring) | tests/test_server.py |
pytest -m "not live" |
AsyncMock |
| Webhook ASGI | tests/test_webhook_app.py |
pytest -m "not live" |
httpx ASGITransport, in-memory RSA keypair |
| Secret hygiene | tests/test_secret_logging.py |
pytest -m "not live" |
respx |
| Composite (mock) | tests/test_composite.py |
pytest -m "not live" |
respx |
| Live e2e | tests/test_live_e2e.py |
pytest -m live |
MANUS_API_KEY, ~5–10 credits per run |
| Live composite | tests/test_live_composite.py |
pytest -m live |
MANUS_API_KEY, ~5 credits per run |
| Live webhook e2e | tests/test_live_webhook_e2e.py |
pytest -m live |
cloudflared (Linux/CI), MANUS_API_KEY, ~3 credits |
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.
- 2mo ago First seen · 177 lines · 2,111 tokens per session scan B d3de7bf79779
Manus-MCP CLAUDE.md is an instructions file published in the GitHub repository 0-SOFT/Manus-MCP (7 stars, last pushed 5mo ago), licensed MIT. It adds 2,111 tokens to every session, about $0.0084 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.