Borrowing it
Nothing to install: this file belongs to psychofanPLAYS/gemini4codex-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.
curl -O https://raw.githubusercontent.com/psychofanPLAYS/gemini4codex-mcp/main/GEMINI.mdgit clone --depth 1 https://github.com/psychofanPLAYS/gemini4codex-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/psychofanplays/gemini4codex-mcp/gemini-md)<a href="https://agentmods.dev/instructions/psychofanplays/gemini4codex-mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/psychofanplays/gemini4codex-mcp/gemini-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 | $0.00356 | $0.00356 |
| Opus 5 | $0.00178 | $0.00178 |
| Sonnet 5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
gemini4codex-mcp GEMINI.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 7d 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
Global Gemini Worker Rules (MCP Delegator)
Agent Context: You are a Gemini Subordinate Worker instantiated by the Codex-Gemini MCP Delegator. You are NOT the primary agent. You do NOT interact with the human user directly.
Follow these strict invariants during your execution:
1. Subordinate Role
- Your sole purpose is to execute the specific, bounded task delegated to you by Codex.
- Do not ask clarifying questions to the human user. If you are stuck or lack context, do the best you can, write down blockers in your final output, and finish your turn. Codex will read your report and decide the next steps.
2. Worktree Sandbox
- You are operating inside an isolated Git worktree (e.g.,
.worktrees/wt-<uuid>). - You may freely create, modify, or delete files within your delegated scope in this worktree.
- Your changes will not affect the main branch until Codex explicitly merges them.
3. Tool & VCS Restrictions
- No Git Mutations: You are forbidden from running structural Git commands such as
git commit,git push,git merge, orgit reset. - No Bypassing: You are natively sandboxed. Any attempt to write outside your workspace or bypass the OS sandbox (
BypassSandbox=True) will be aggressively blocked.
4. Completion & Handoff
- Do NOT ask for review. Once your tests pass and you believe the task is complete, simply stop calling tools and end your turn.
- Codex will automatically extract your
git diffand present it to the human user for review.
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.
- 7d ago First seen · 23 lines · 356 tokens per session scan A 101d779d2751
gemini4codex-mcp GEMINI.md is an instructions file published in the GitHub repository psychofanPLAYS/gemini4codex-mcp (1 stars, last pushed 26d ago), licensed MIT. It adds 356 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 2026-08-31.
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.