Borrowing it
Nothing to install: this file belongs to dnnyngyen/iron-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/dnnyngyen/iron-manus-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/dnnyngyen/iron-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/dnnyngyen/iron-manus-mcp/claude-md)<a href="https://agentmods.dev/instructions/dnnyngyen/iron-manus-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dnnyngyen/iron-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/dnnyngyen/iron-manus-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dnnyngyen/iron-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 | $0.00497 | $0.00497 |
| Opus 5 | $0.00249 | $0.00249 |
| Sonnet 5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
iron-manus-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 11d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iron Manus MCP - Development Context
Project Overview
Iron Manus MCP is a comprehensive FSM-driven orchestration system with 8-phase agent loop and 65+ API registry integration.
Key Components
- Core FSM: 8-phase state machine (INIT → QUERY → ENHANCE → KNOWLEDGE → PLAN → EXECUTE → VERIFY → DONE)
- Tool Registry: Modular tool architecture with JARVIS FSM controller
- API Registry: 65+ APIs with role-based selection and intelligent orchestration
- Security Layer: SSRF protection and input validation
- Type System: Comprehensive TypeScript interfaces for all components
Build & Test Commands
npm run build # TypeScript compilation
npm test # Run full test suite (266 tests)
npm run lint # ESLint checking
npm run dev # Build and start server
npm start # Start compiled server
Important Notes
- Uses MCP SDK v1.13.2 with correct import paths
- 265/266 tests passing (1 timing-related test flaky)
- TypeScript strict mode enabled
- ESM modules with proper .js extensions
- Production-ready with comprehensive validation
Recent Updates
-
v0.2.5: System Prompt Initialization Fix
- Fixed confusing system prompt during initialization
- Simplified prompt logic by combining INIT and QUERY phases
- Improved user experience with clearer messaging
-
v0.2.4: Tool Description Refinement
- Tool descriptions rewritten to guide intelligent thinking
- Parameter names transformed into cognitive guides
- Error messages enhanced with self-reflection frameworks
-
v0.2.3: Enhanced SSRF protection and security validation
-
Added intelligent output validation and rollback signaling
Development Status
✅ Core FSM functionality working ✅ Tool registry operational ✅ Build pipeline functional ✅ Test suite passing (265/266) ✅ MCP SDK v1.13.2 fully compatible ✅ Production ready
Architecture
Hybrid cognitive-deterministic system:
- Cognitive Layer (FSM): Strategic reasoning and workflow orchestration with role-based frameworks
- Tool Registry: Tool architecture with strategic guidance
- API Registry: Intelligent selection from 65+ endpoints
- Security System: Multi-layered protection with SSRF guards and input validation
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.
- 11d ago First seen · 65 lines · 497 tokens per session scan A 78b6e75e7442
iron-manus-mcp CLAUDE.md is an instructions file published in the GitHub repository dnnyngyen/iron-manus-mcp (64 stars, last pushed 6mo ago), licensed MIT. It adds 497 tokens to every session, about $0.0025 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
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
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.
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.
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.
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.