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/cornellsh/codex-proxy/agents-mdgit clone --depth 1 https://github.com/cornellsh/codex-proxyWhat 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 | $0.01411 | $0.01411 |
| Opus 5 | $0.00705 | $0.00705 |
| Sonnet 5 | $0.00282 | $0.00282 |
| Haiku 4.5 | $0.00141 | $0.00141 |
Grade A, and why
codex-proxy AGENTS.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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Proxy Context
Overview
The codex-proxy is a Python-based intermediary service for the Codex system, designed to handle API orchestration and environment-specific logic. It is container-native and relies on Docker for consistent execution.
Infrastructure: Docker
- Container Name:
codex-proxy - Port:
8765 - Mounts:
${HOME}/.geminiis mounted to/home/appuser/.geminifor credential access../srcis mounted to/app/srcto enable hot-reloading during development.
- Commands: Use
docker-composefor direct lifecycle management if scripts are not used.
Control Script (/scripts)
The project uses a unified control script for all operations. Execute from the codex-proxy/ root directory.
./scripts/control.sh <command> [options]
Commands:
start- Start the proxy container in detached modestop- Stop and remove the proxy containerlogs- Follow the logs of the proxy containertest- Run the pytest test suiterun [-p|--profile <name>] -- "prompt"- Rebuild container and run codex command through proxy
Development Patterns
- Credentials: Ensure your host machine has valid Gemini credentials at
~/.gemini. - Iteration: Use
control.sh runto quickly test end-to-end changes. - Verification: Always run
control.sh testafter modifications to ensure that chaining and proxy logic are still functional.
Examples:
# Start the proxy
./scripts/control.sh start
# Run a test command
./scripts/control.sh run -- "hello world"
# Run with specific profile
./scripts/control.sh run -p glm -- "test prompt"
# Check logs
./scripts/control.sh logs
# Run tests
./scripts/control.sh test
# Stop the proxy
./scripts/control.sh stop
Engineering Mandate: Deep API Parity
The primary goal of codex-proxy is to ensure seamless compatibility between multiple AI providers (Gemini, Z.AI) and the OpenAI Responses API protocol used by the Codex ecosystem. The proxy normalizes different wire formats to a unified internal OpenAI-like structure.
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.
- 2d ago First seen · 138 lines · 1,411 tokens per session scan A 3d56b152b9d1
codex-proxy AGENTS.md is an instructions file published in the GitHub repository cornellsh/codex-proxy (55 stars, last pushed 5mo ago), licensed MIT. It adds 1,411 tokens to every session, about $0.0071 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.
buildNext
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
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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
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.
langchain 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.