Borrowing it
Nothing to install: this file belongs to madhavsomani/codex-copilot-relay. 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/madhavsomani/codex-copilot-relay/main/AGENTS.mdgit clone --depth 1 https://github.com/madhavsomani/codex-copilot-relayWrote 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/madhavsomani/codex-copilot-relay/agents-md)<a href="https://agentmods.dev/instructions/madhavsomani/codex-copilot-relay/agents-md"><img src="https://agentmods.dev/badge/instructions/madhavsomani/codex-copilot-relay/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.
<a href="https://agentmods.dev/instructions/madhavsomani/codex-copilot-relay/agents-md"><img src="https://agentmods.dev/badge/instructions/madhavsomani/codex-copilot-relay/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00700 | $0.00700 |
| Opus 5.5 | $0.00280 | $0.00280 |
| Sonnet 5.5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
codex-copilot-relay 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 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Copilot Relay agent instructions
Deployment invariant
- Every runtime or dashboard change intended for the live relay must increment
the version in both
package.jsonandpackage-lock.json. - After the version bump, run Start or Repair so a fresh watchdog is staged. The
watchdog reads
expectedVersiononce at startup. Arbitrary file edits and an unchanged version do not hot-reload or deploy automatically. - Repair, internal Start-Codex-CopilotProxy and automatic recovery must never force-restart healthy active work. They use deferred promotion so in-memory continuations can finish.
- Explicit desktop Start Relay and Stop & Restore are intentional cancellation exceptions: disable
recovery, cancel both adapters (including pending uploads/continuations), stop
only verified owned processes. Stop restores the protected TOML; Start keeps
the managed configuration and starts the latest local package. Never reuse
-CancelActivein internal Start, Repair or automatic upgrades/recovery. - The legacy automatic recovery exception is
Start-Codex-CopilotProxy.ps1 -RecoverDeadBackend: it must prove, across repeated samples, an owned listener, a fatal CLI heap crash after startup, and no remaining Copilot worker. Those stale exchanges are already lost. Supervised releases recover the SDK in-process and must never use this legacy exception to terminate a healthy worker. - Verify deployment by reading
http://127.0.0.1:4144/healthand matching itsversiontopackage.json. Refreshing the dashboard alone is not proof.
Required verification
- Preserve OpenAI desktop identity, native account/Remote services, device pairings and managed Remote policies when changing model routing. Never expose the loopback relay to make mobile access work. Keep the paired desktop-auth flag and nonsecret model bearer override together.
- For config/lifecycle changes, run
remote-compatibility.test.ps1; after a Codex engine upgrade rerunprobe-desktop-auth.mjsagainst that installed engine. Do not claim iPhone Remote is verified without a phone-to-host prompt/reply round trip. Seedocs/IPHONE-REMOTE.md. - Support unmodified stock Codex only. Do not ship or install custom engines.
Native app voice is unsupported on the tested engine; never weaken model
credential isolation to enable it. See
docs/NATIVE-VOICE.md. - Native OpenAI helpers are images-only. Search is removed, including legacy opt-ins. Browser and connector tools are separate, harness-owned capabilities.
- Run
basic-revert.test.ps1for lifecycle work. Connection status must distinguish configured routing from observed traffic and authentication. - The connection center is guided/read-only, not an automatic installer.
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 Changed · +8 lines · +141 tokens per session 79c69f33f5c3
- 1mo ago Changed · +8 lines · +121 tokens per session 9f4542baaaa9
- 1mo ago Changed · +9 lines · +129 tokens per session 0033c0d8b08c
- 1mo ago First seen · 25 lines · 309 tokens per session scan A b7208c0a571c
codex-copilot-relay AGENTS.md is an instructions file published in the GitHub repository madhavsomani/codex-copilot-relay (1 stars, last pushed yesterday), licensed MIT. It adds 700 tokens to every session, about $0.0028 per session on Opus 5.5. 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 2026-09-05.
Other instructions, from other repositories
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.