gemini-cli-mcp-slim: Instructions file for Codex

AGENTS.md

gemini-cli-mcp-slim AGENTS.md is an instructions file for Codex, OpenCode from tksfjt1024/gemini-cli-mcp-slim. It costs 1,287 tokens per session, scanned A, original, MIT.

Repository instructions for an MCP bridge that lets AI coding tools consult Google’s Gemini command-line tool, including files and web searches.

In plain words
What is it for?
Use them when developing, testing, or reviewing this Gemini-to-MCP bridge, especially for analysis across multiple repositories.
Why use it?
They explain the project’s design and commands so an AI coding tool can make changes without misunderstanding its limited scope or safety choices.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is tksfjt1024/gemini-cli-mcp-slim's own configuration. It tells Codex and OpenCode how to work on gemini-cli-mcp-slim 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 gemini-cli-mcp-slim configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tksfjt1024/gemini-cli-mcp-slim. 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/tksfjt1024/gemini-cli-mcp-slim/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/tksfjt1024/gemini-cli-mcp-slim

Made for: Codex, OpenCode.

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 gemini-cli-mcp-slim AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tksfjt1024/gemini-cli-mcp-slim/agents-md/github.svg)](https://agentmods.dev/instructions/tksfjt1024/gemini-cli-mcp-slim/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tksfjt1024/gemini-cli-mcp-slim/agents-md"><img src="https://agentmods.dev/badge/instructions/tksfjt1024/gemini-cli-mcp-slim/agents-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 gemini-cli-mcp-slim AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tksfjt1024/gemini-cli-mcp-slim/agents-md"><img src="https://agentmods.dev/badge/instructions/tksfjt1024/gemini-cli-mcp-slim/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,287 This file is loaded in full into every session.
When invoked 1,287 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01287 $0.01287
Opus 5 $0.00643 $0.00643
Sonnet 5 $0.00257 $0.00257
Haiku 4.5 $0.00129 $0.00129

Measured 8d ago against content hash c2544e547d93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gemini-cli-mcp-slim AGENTS.md scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **Required**: pass `asyncio.subprocess.DEVNULL` whenever `stdin_text` is `None`.
AGENTS.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — gemini-cli-mcp-slim

This file gives AI coding agents (Claude Code, Codex, Cursor, Gemini CLI, etc.) the project-specific context required to work on this repository. Claude Code reads it via CLAUDE.md, which is a one-line @AGENTS.md import shim.

What this project is

A thin bridge that exposes Google's Gemini CLI to MCP clients (Claude Code, Codex MCP, Cursor MCP, and other tools that speak MCP).

  • Inputs: MCP tools (consult_gemini, consult_gemini_with_files, web_search)
  • Outputs: argv-list subprocess invocation of the gemini CLI (the binary path is configurable via $GEMINI_CMD)

History management, caching, streaming, and similar higher-level features are deliberately not provided. The killer feature is cross-repository analysis via directory (cwd) + include_directories.

Architectural decisions (load-bearing principles)

The author started this project from "don't blindly route your prompts and code through someone else's wrapper." Recent supply-chain incidents (xz-utils backdoor, postmark-mcp typosquat, npm chalk/debug compromise) inform every design choice; default toward auditability.

  • Auditable: the core implementation is a single file (src/gemini_cli_mcp_slim/server.py, ~290 lines) that anyone can read end-to-end in 30 minutes. If a feature would meaningfully grow this size, prefer dropping or omitting the feature over splitting the file.
  • Minimum dependencies: [project].dependencies in pyproject.toml is mcp>=1.0.0 only. Adding a direct dependency expands supply-chain surface; always check whether the standard library can do the job first.
  • Forward-compatible: known flags are typed parameters; unknown / rare flags flow through extra_args: string[] verbatim. The server should not need to be re-released every time the upstream gemini CLI grows a new flag.
  • Transparent: every subprocess invocation logs its full argv to stderr (logger.info("exec %s ...")).
  • No shell: always use asyncio.create_subprocess_exec with an argv list. shell=True and string-concatenated commands are forbidden.
  • Configurable binary: keep $GEMINI_CMD working so users can swap or wrap the gemini binary.

Read the full file on GitHub · 111 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. 8d ago First seen · 111 lines · 1,287 tokens per session scan A c2544e547d93

Subscribe to this mod's changes

gemini-cli-mcp-slim AGENTS.md is an instructions file published in the GitHub repository tksfjt1024/gemini-cli-mcp-slim (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,287 tokens to every session, about $0.0064 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens