Agent Conductor MCP server

Agent Conductor

AGENTS.md in, governed agent team out.

Agent Conductor is an MCP server that turns the two conventions the coding-agent ecosystem has converged on — AGENTS.md operating manuals and SKILL.md skills — from passive documentation into an active orchestration layer, with a consensus-hardened decision engine gating high-stakes changes.

• Mirrors: codeberg.org/cubiczan/agent-conductor · github.com/icohangar-ops/agent-conductor
• License: MIT
• Status: v0.1 — working scaffold; see Roadmap

The problem

Every serious agent tool — Claude Code, Cursor, Copilot, Codex, Gemini CLI — now reads an AGENTS.md at the repo root and a catalog of SKILL.md files. But both conventions are honor-system prose:

boundaries, and verification checklists live as markdown the agent may or may not internalize.

• Nothing compiles the contract. The non-negotiable rules, layer

scoring model proceeds with the same confidence as one renaming a variable.

• Nothing gates the decision. An agent that's about to rewrite your

is a suggestion, not a gate.

• Nothing verifies the checklist ran. "Run npm test before handing off"

Conductor makes the conventions executable — without asking any agent tool to change. It ships as a standard MCP server, so anything that speaks MCP gets contract compilation, skill discovery, and decision gating for free.

How it works

MCP client (Claude Code / Cursor / Copilot / ...)
        │  stdio (JSON-RPC, MCP)
        ▼
┌────────────────────────────────────────────────┐
│ TypeScript front end (src/)                    │
│   contract/parser.ts   AGENTS.md → contract    │
│   contract/workspace.ts Multi-root merge       │
│   skills/loader.ts     SKILL.md discovery      │
│   server.ts            7 MCP tools             │
└────────────────┬───────────────────────────────┘
                 │  newline-delimited JSON, child stdio
                 ▼
┌────────────────────────────────────────────────┐
│ Python decision engine (engine/)               │
│   vendored Consensus Hardening Protocol core   │
│   R0 gates · foundation attacks · lifecycle    │
└────────────────────────────────────────────────┘

Three capability groups:

non-negotiable rules, layer do/don't boundaries, verification gates, skill recommendations, and an out-of-scope list.

1. Contract — compile an AGENTS.md into structured mission,

scopes with progressive disclosure: metadata costs ~100 tokens, bodies load only on demand.

1. Skills — discover SKILL.md skills across project and personal

Consensus Hardening Protocol: a cheap R0 sanity gate before work starts, and an adversarial foundation-attack pass before a high-stakes change locks.

1. Decision — gate work through the

Quick start

Requirements: Node 23+ (runs TypeScript natively) and Python 3.9+ (stdlib only — the engine needs no pip installs).

git clone https://codeberg.org/cubiczan/agent-conductor.git
cd agent-conductor
npm install
npm test            # TypeScript tests (parser, skills, multi-root, live engine bridge)
npm run test:engine # Python bridge protocol tests
npm run build

Register with Claude Code:

claude mcp add agent-conductor -- node /path/to/agent-conductor/dist/index.js

Or in any MCP client's JSON config:

{
  "mcpServers": {
    "agent-conductor": {
      "command": "node",
      "args": ["/path/to/agent-conductor/dist/index.js"]
    }
  }
}

Set CONDUCTOR_PYTHON if your Python 3 lives somewhere other than python3.

Then, from any project that has an AGENTS.md:

"Load this project's agent contract, list its verification gates, and run a

decision_adversary pass on the change I'm about to make."

Shortened. The full README is on GitHub.