mcp-conductor: Instructions file for Claude Code

CLAUDE.md

mcp-conductor CLAUDE.md is an instructions file for Claude Code from niradler/mcp-conductor. It costs 1,911 tokens per session, scanned A, original, MIT.

Repository instructions for Conductor, a tool gateway that combines tools from multiple backends behind bearer-token login, group-based permissions, and audit logging. They include commands for building, testing, developing, and running individual tests.

In plain words
What is it for?
Working on the Conductor codebase, including installation, builds, type checks, tests, development runs, and API-key handling.
Why use it?
They help a coding agent understand the project structure and follow its required commands and access-control rules.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

Nothing to install: this file belongs to niradler/mcp-conductor. 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/niradler/mcp-conductor/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/niradler/mcp-conductor

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 mcp-conductor CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/niradler/mcp-conductor/claude-md"><img src="https://agentmods.dev/badge/instructions/niradler/mcp-conductor/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,911 This file is loaded in full into every session.
When invoked 1,911 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 $0.01911 $0.01911
Opus 5.5 $0.00764 $0.00764
Sonnet 5.5 $0.00382 $0.00382
Haiku 4.5 $0.00191 $0.00191

Measured 2mo ago against content hash dfeaad33e312, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-conductor 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 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.

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 · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 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 summary

conductor is a tool gateway for AI agents. It speaks MCP to clients and aggregates tools from multiple backends (ToolProvider implementations) behind bearer-token auth, group-based access control, and full audit. Packaged as a pnpm workspace.

Commands

Run from the repo root — all scripts fan out across packages via pnpm workspace filters.

  • pnpm install — install + link workspaces
  • pnpm build — tsc -p tsconfig.build.json in each package (packages/*)
  • pnpm typecheck — tsc --noEmit per package (checks both src/ and tests/)
  • pnpm test — run the full vitest suite (workspace config at vitest.workspace.ts)
  • pnpm test:watch — vitest in watch mode
  • pnpm clean — wipe dist/ and .tsbuildinfo everywhere
  • pnpm dev — run the server via tsx packages/server/src/cli.ts (honours CONDUCTOR_CONFIG)
  • pnpm hash-key <plaintext> — prints sha256:<hex> for an API key (what the config expects)

Running a single test

Vitest's workspace picks up each package's vitest.config.ts. Target a specific file by path, and narrow inside a file with -t:

pnpm test -- packages/gateway/tests/auth.test.ts
pnpm test -- packages/gateway/tests/auth.test.ts -t "rejects invalid bearer"
# or scope by project name (packages self-name: "core", "gateway", etc.)
pnpm test -- --project gateway

Running the gateway locally

The repo ships a working config at examples/conductor.json (user alice, key changeme, one provider everything via npx @modelcontextprotocol/server-everything):

CONDUCTOR_CONFIG=examples/conductor.json pnpm dev
# → http://127.0.0.1:18080/mcp  (Authorization: Bearer changeme)
# → GET /health returns { ok, sessions, providers }

Architecture

Five packages in packages/*, strict layering — core has no sibling deps; gateway/provider-mcp/provider-openshell depend on core; server wires everything.

Read the full file on GitHub · 98 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. 2mo ago First seen · 98 lines · 1,911 tokens per session scan A dfeaad33e312

Subscribe to this mod's changes

mcp-conductor CLAUDE.md is an instructions file published in the GitHub repository niradler/mcp-conductor (0 stars, last pushed 6mo ago), licensed MIT. It adds 1,911 tokens to every session, about $0.0076 per session on Opus 5.5. 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

mcp-conductor CLAUDE.md compared with instructions from other repositories

mcp-conductor CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-conductor CLAUDE.mdniradler/mcp-conductorInstructions file06mo agoMITA1,911Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot