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/madhavsomani/codex-copilot-relay/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.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 | $0.00309 | $0.00309 |
| Opus 5 | $0.00154 | $0.00154 |
| Sonnet 5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
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 today.
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
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. - Never force-restart while
/healthreportsactiveExchangesabove zero. Start or Repair uses deferred promotion so in-memory tool continuations can finish. - The sole legacy 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
- Run
npm testandgit diff --checkfor every code change. - For dashboard work, inspect the live page at desktop, tablet, and phone widths and confirm there is no page-level horizontal overflow or browser console error.
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.
- today 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 309 tokens to every session, about $0.0015 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 2026-09-05.
Other instructions, from other repositories
apm tests.instructions.md
Test conventions: URL assertions must use urllib.parse, never substring.
apm cli.instructions.md
CLI Design Guidelines for visual output, styling, and user experience standards.
apm integrators.instructions.md
Architecture rules for file-level integrators (BaseIntegrator pattern).
apm copilot-instructions.md
Copilot instructions for microsoft/apm, covering linting (canonical contract), ci-mirror commands, local workflow, common surprises and lifecycle binding.
apm architecture.instructions.md
Single canonical owner discipline: one authority per durable decision, guarded by a regression test + a static boundary check.
apm cicd.instructions.md
CI/CD Pipeline configuration for PyInstaller binary packaging and release workflow.