Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/donghae0414/codex-gemini-mcp/agents-mdgit clone --depth 1 https://github.com/donghae0414/codex-gemini-mcpWrote 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/donghae0414/codex-gemini-mcp/agents-md)<a href="https://agentmods.dev/instructions/donghae0414/codex-gemini-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/donghae0414/codex-gemini-mcp/agents-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 | $0.01226 | $0.01226 |
| Opus 5 | $0.00613 | $0.00613 |
| Sonnet 5 | $0.00245 | $0.00245 |
| Haiku 4.5 | $0.00123 | $0.00123 |
Grade A, and why
codex-gemini-mcp 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 5d 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.
│ ├── runtime/ # foreground/background child_process execution How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PROJECT KNOWLEDGE BASE
Generated: 2026-02-25T19:13:00+09:00 Commit: 2dadb48 Branch: main Project: codex-gemini-mcp
OVERVIEW
CLI-only TypeScript MCP server that proxies local codex and gemini CLIs. Main concerns are strict input validation, foreground/background execution, file-backed job persistence, and structured JSONL logging.
STRUCTURE
./
├── src/
│ ├── mcp/ # MCP server registration + stdio entrypoints
│ ├── tools/ # zod schemas + provider handlers
│ ├── providers/ # CLI argument builders per provider
│ ├── runtime/ # foreground/background child_process execution
│ ├── logger/ # JSONL request/response/error logging
│ ├── config.ts # env defaults, caps, path resolution
│ ├── prompt-store.ts # jobs/prompts file persistence helpers
│ ├── job-management.ts
│ └── types.ts
├── src/AGENTS.md # src-specific map and constraints
├── README.md
├── package.json
└── tsconfig.json
WHERE TO LOOK
| Task | Location | Notes |
|---|---|---|
| Codex MCP tools | src/mcp/codex-server.ts |
registers ask_codex + job tools |
| Gemini MCP tools | src/mcp/gemini-server.ts |
registers ask_gemini + job tools |
| Stdio startup | src/mcp/codex-stdio-entry.ts, src/mcp/gemini-stdio-entry.ts |
stdio transport + startup logs to stderr |
| Input validation | src/tools/schema.ts |
model regex, job-id schema, enum constraints |
| Ask orchestration | src/tools/codex-handlers.ts, src/tools/gemini-handlers.ts |
foreground/background branch point |
| Provider command mapping | src/providers/codex.ts, src/providers/gemini.ts |
CLI args and provider defaults |
| Foreground runtime | src/runtime/run-cli.ts |
timeout, output cap, terminal error mapping |
| Background runtime | src/runtime/run-cli-background.ts |
detached process + status transitions |
| Job persistence | src/prompt-store.ts |
atomic JSON writes, file discovery by job id |
| Job APIs | src/job-management.ts |
wait/check/kill/list behavior |
| Logging pipeline | src/logger/index.ts, src/logger/file-sink.ts, src/logger/event.ts |
JSONL file write + stderr mirror |
| Runtime/env config | src/config.ts |
timeout clamp, output cap, runtime paths |
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.
- 5d ago First seen · 89 lines · 1,226 tokens per session scan A b1da1ee575ae
codex-gemini-mcp AGENTS.md is an instructions file published in the GitHub repository donghae0414/codex-gemini-mcp (5 stars, last pushed 6mo ago), licensed MIT. It adds 1,226 tokens to every session, about $0.0061 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.
Other instructions, from other repositories
Kokoro-Engine CLAUDE.md
Claude Code instructions for chyinan/Kokoro-Engine, covering claude.md, git 规范, 项目概述, 常用命令 and 安装依赖.
retry-axios GEMINI.md
Gemini CLI instructions for JustinBeckwith/retry-axios, covering project: retry-axios, project overview, building and running, dependencies and commands.
pcl copilot-instructions.md
Copilot instructions for personamanagmentlayer/pcl, covering project overview, pcl bootstrap system, core architecture principles, 1. compiler pipeline and 2. type system.
solo copilot-instructions.md
Copilot instructions for hiero-ledger/solo, covering github copilot instructions for hiero-ledger/solo and highest-frequency rules.
openmcp-client CLAUDE.md
Instructions for LSTM-Kirigaya/openmcp-client, covering claude.md, development commands, setup and installation, development and service development.
bedrock CLAUDE.md
Claude Code instructions for christopher-buss/bedrock, covering bedrock project context, what is bedrock?, architecture, architecture quick reference and testing requirements (non-negotiable).