Borrowing it
Nothing to install: this file belongs to regenrek/codex-proofloop. 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/regenrek/codex-proofloop/main/AGENTS.mdgit clone --depth 1 https://github.com/regenrek/codex-proofloopWrote 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/regenrek/codex-proofloop/agents-md)<a href="https://agentmods.dev/instructions/regenrek/codex-proofloop/agents-md"><img src="https://agentmods.dev/badge/instructions/regenrek/codex-proofloop/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/regenrek/codex-proofloop/agents-md"><img src="https://agentmods.dev/badge/instructions/regenrek/codex-proofloop/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 | $0.00350 | $0.00350 |
| Opus 5.5 | $0.00140 | $0.00140 |
| Sonnet 5.5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
codex-proofloop 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 15d 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
Proofloop runner development
- The agent-neutral skill is maintained in
instructa/agent-skills, underskills/engineering/proofloop. This repository owns the optional runner only; do not reintroduce a skill entrypoint or duplicate its strategy here. Model, reviewer and transport choices belong to the caller. - New permanent tests need a concrete failure and a gap in existing checks before implementation. Prefer the public CLI, real Git repositories and real subprocesses. Do not test copied wording or private helper structure.
- The optional runner has real external contracts:
package.jsonowns the published package name and executable;src/policy.mts::validatePolicyowns the policy schema;src/cli.mts::mainandexecuteexpose commands and consume or produce persisted run records. Preserve these existing consumer boundaries unless deliberately changing them; do not add legacy-shape parsers, aliases or migration code. - Edit
src/*.mts;npm run buildregeneratesskills/proofloop/scripts/*.mjsand version metadata. Include source and generated runtime changes together. Keep runtime npm dependencies at zero unless a concrete need justifies one. - Use
npm run format,npm run lint,npm run format:checkandnpm run build.npm run acceptanceexercises the public CLI in disposable repositories and writes.proofloop/acceptance/result.json; its contract is indocs/runner-acceptance.md. - Keep one runner. No model-specific variants, background watchers, duplicate review workflow or new verification framework.
- Treat local review files as attestations. Local validation does not prove live product behavior, host skill loading, reviewer identity or delivery-speed improvement.
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.
- 15d ago Changed · +82 tokens per session 37011db608de
- 1mo ago First seen · 10 lines · 268 tokens per session scan A e45d1a967db1
codex-proofloop AGENTS.md is an instructions file published in the GitHub repository regenrek/codex-proofloop (38 stars, last pushed 15d ago), licensed MIT. It adds 350 tokens to every session, about $0.0014 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 2026-09-25.
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.