Borrowing it
Nothing to install: this file belongs to dnnyngyen/gemini-cli-orchestrator. 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/gemini-cli-orchestrator/main/CLAUDE.mdgit clone --depth 1 https://github.com/dnnyngyen/gemini-cli-orchestratorWrote 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/gemini-cli-orchestrator/claude-md)<a href="https://agentmods.dev/instructions/dnnyngyen/gemini-cli-orchestrator/claude-md"><img src="https://agentmods.dev/badge/instructions/dnnyngyen/gemini-cli-orchestrator/claude-md.svg" alt="Measured on agentmods" 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 | $0.00363 | $0.00363 |
| Opus 5 | $0.00181 | $0.00181 |
| Sonnet 5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
gemini-cli-orchestrator 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.
What it actually says
Gemini CLI Orchestrator - Development Context
Project Overview
This is the gemini-cli-orchestrator project - a pure metaprompting MCP server that guides AI agents on how to collaborate with Google's Gemini AI model. It provides NO execution logic, only intelligent guidance.
Core Philosophy
Metaprompting-First: Don't build intelligence into the system. Build prompts that elicit intelligence from the agent.
Key Components
- gemini-collaboration-guide.mjs: Pure metaprompting MCP server that teaches collaboration strategies
- Pure Guidance Tools: Tools that return metaprompts, not execution results
- Universal Portability: Works anywhere the agent has bash access and gemini CLI installed
Architecture
- Teacher Model: Provides strategic guidance rather than executing commands
- No State Management: Stateless guidance system with no workflow storage
- No File Processing: Agents handle file operations using their own tools
- No Shell Execution: Agents run gemini commands using their own bash capabilities
Commands
node gemini-collaboration-guide.mjs # Start pure metaprompting MCP server
npm run mcp # Start server
npm test # Run tests
How It Works
- Agent requests guidance using MCP tools
- Server returns rich metaprompts that teach strategic thinking
- Agent applies guidance to execute their own bash commands
- Agent collaborates with gemini CLI directly using server's teaching
Requirements
- External
geminiCLI must be installed and configured on the agent's system - Agent must have bash/shell access for executing gemini commands
- No server-side authentication or file access required
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 · 36 lines · 363 tokens per session scan A 7e1947bae965
gemini-cli-orchestrator CLAUDE.md is an instructions file published in the GitHub repository dnnyngyen/gemini-cli-orchestrator (28 stars, last pushed 1y ago), licensed MIT. It adds 363 tokens to every session, about $0.0018 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
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).
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.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.