What is cli-orchestrator-mcp CLAUDE.md?

A set of Claude Code instructions for a project that coordinates Claude, Gemini, and Codex command-line tools through an MCP server.

Use it when building, testing, linting, or debugging this MCP server.

It gives the coding agent the project’s commands, structure, testing rules, and tool details in one place.

How lleontor705/cli-orchestrator-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lleontor705/cli-orchestrator-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.

Copy the file

curl -O https://raw.githubusercontent.com/lleontor705/cli-orchestrator-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lleontor705/cli-orchestrator-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/lleontor705/cli-orchestrator-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/lleontor705/cli-orchestrator-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/lleontor705/cli-orchestrator-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lleontor705/cli-orchestrator-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/lleontor705/cli-orchestrator-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lleontor705/cli-orchestrator-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 792 This file is loaded in full into every session.

When invoked 792 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.

Model	Per session	Once invoked
Fable 5.1	$0.00792	$0.00792
Opus 5	$0.00396	$0.00396
Sonnet 5	$0.00158	$0.00158
Haiku 4.5	$0.00079	$0.00079

Measured 8d ago against content hash fe9b64650380, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cli-orchestrator-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 8d 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 · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 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.

Commands

npm run build          # TypeScript compilation to build/
npm run dev            # Run with tsx (no build step)
npm test               # Unit tests only (CI-safe, mocked, no real CLIs)
npm run test:local     # Integration + stress tests (requires real CLIs installed)
npm run test:all       # All tests: unit + integration + stress
npm run test:watch     # Vitest watch mode
npm run lint           # Type-check (tsc --noEmit)
npm run inspect        # MCP Inspector for debugging tool calls

Test files: *.test.ts run in CI; *.local.ts (integration/stress) run only locally via test:local or test:all.

Architecture

MCP server that orchestrates three AI CLI tools (Claude CLI, Gemini CLI, Codex CLI) with resilience patterns. Runs over stdio transport.

Request flow: MCP client → cli_execute tool → resilience pipeline (retry + circuit breaker + fallback) → CLI process execution → redacted output back to client.

Core Modules

src/cli/definitions.ts — Provider configs (binary names, arg builders, fallback chains). Each CLI has distinct arg formats: Claude uses -p with --allowedTools "", Gemini uses -e none -p, Codex uses exec --full-auto.
src/cli/detection.ts — Auto-detects installed CLIs via which/where with 5-minute cache per provider.
src/cli/executor.ts — Process execution via execa. Handles Windows .cmd/.bat shim detection, stdin fallback for prompts >30KB, PATH augmentation on Windows.
src/cli/circuit-breaker.ts — Per-provider state machine (closed→open→half-open). Opens after 3 consecutive failures, 60s cooldown.
src/cli/resilience.ts — Orchestrates retry (max 2 retries, exponential backoff with jitter), circuit breaker checks, and fallback chain traversal. Non-retryable errors (auth, permanent) skip directly to fallback.

MCP Surface

Four tools: cli_execute (run prompt with resilience), cli_stats (health dashboard), cli_list (installed CLIs), cli_route (role-based recommendation). One resource: mcp://cli-stats. Two prompts: code_review, architecture_design.

Read the full file on GitHub · 53 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.

8d ago First seen · 53 lines · 792 tokens per session scan A fe9b64650380

Subscribe to this mod's changes

cli-orchestrator-mcp CLAUDE.md is an instructions file published in the GitHub repository lleontor705/cli-orchestrator-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 792 tokens to every session, about $0.0040 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.

Building agents Claude Code ai-agents circuit-breaker codex gemini-cli mcp

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

cli-orchestrator-mcp: Instructions file for Claude Code