repo-foreman: Instructions file for Codex

AGENTS.md

repo-foreman AGENTS.md is an instructions file for Codex, OpenCode from sponyhub/repo-foreman. It costs 1,352 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for contributing to RepoForeman, a local tool that organizes and governs software delivery around the Codex command-line tool.

In plain words
What is it for?
Use them when making broad or behavior-changing edits to RepoForeman, especially changes involving configuration, isolation, recovery, security, or releases.
Why use it?
They explain which project documents to read, what the product must remain, and which compatibility and security constraints changes must respect.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents; mentions AGENTS.md; mentions Codex.

This is sponyhub/repo-foreman's own configuration. It tells Codex and OpenCode how to work on repo-foreman itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything repo-foreman configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sponyhub/repo-foreman. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sponyhub/repo-foreman/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/sponyhub/repo-foreman

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for repo-foreman AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sponyhub/repo-foreman/agents-md/github.svg)](https://agentmods.dev/instructions/sponyhub/repo-foreman/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sponyhub/repo-foreman/agents-md"><img src="https://agentmods.dev/badge/instructions/sponyhub/repo-foreman/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.

agentmods 80×15 button for repo-foreman AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sponyhub/repo-foreman/agents-md"><img src="https://agentmods.dev/badge/instructions/sponyhub/repo-foreman/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,352 This file is loaded in full into every session.
When invoked 1,352 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01352 $0.01352
Opus 5.5 $0.00541 $0.00541
Sonnet 5.5 $0.00270 $0.00270
Haiku 4.5 $0.00135 $0.00135

Measured 2mo ago against content hash cd2bfb2928a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

repo-foreman 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 2mo 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.

AGENTS.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — RepoForeman Contributor Contract

This file applies to the entire repository. It defines durable instructions for coding agents and contributors working on RepoForeman itself. It is not a template for consumer repositories and must not be injected into projects that use RepoForeman.

Start here

Before a broad or behavior-changing edit, read:

  • README.md for product scope, supported workflows, and public claims;
  • CONTRIBUTING.md for contribution expectations;
  • SECURITY.md for trust boundaries and vulnerability reporting;
  • docs/architecture.md for the pipeline, isolation, recovery, and security model;
  • the relevant file under docs/ when changing configuration, artifacts, or release behavior.

RepoForeman is an early public beta. Keep changes focused, reviewable, and explicit about compatibility and security consequences.

Product invariants

  • RepoForeman remains a local, deterministic delivery and governance layer around Codex CLI. Do not present it as a model provider, hosted service, OS security boundary, or replacement for native Codex Goal and subagent interfaces.
  • Preserve restrictive defaults. Broader filesystem, network, environment, command, or host access must be explicit, visibly unsafe, and covered by tests and documentation.
  • Keep the published runtime dependency-free unless a maintainer explicitly approves changing that contract. Prefer Node.js built-ins.
  • Support the Node.js, operating-system, and Git worktree matrix documented in package.json and README.md; verify that matrix manually before a release.
  • Keep every planning, worker, review, recovery, and verification loop bounded. Exhaustion must produce an explainable failure or partial result, never an unbounded retry cycle.
  • Validate agent-produced structured data before it becomes executable state. A valid schema is necessary but does not prove factual correctness.
  • Treat command and diff policy as defense in depth, not as a shell parser or sandbox. Do not weaken the documented trust boundary.
  • Preserve baseline verification so pre-existing failures are not silently reported as regressions introduced by a run.
  • Persist enough redacted state to explain and safely resume a run. Do not persist raw sensitive output by default.

Read the full file on GitHub · 90 lines

Changes

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.

  1. 2mo ago First seen · 90 lines · 1,352 tokens per session scan A cd2bfb2928a0

Subscribe to this mod's changes

repo-foreman AGENTS.md is an instructions file published in the GitHub repository sponyhub/repo-foreman (1 stars, last pushed 8d ago), licensed Apache-2.0. It adds 1,352 tokens to every session, about $0.0054 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 2026-08-31.

Related

repo-foreman AGENTS.md compared with instructions from other repositories

repo-foreman AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
repo-foreman AGENTS.mdsponyhub/repo-foremanInstructions file18d agoApache-2.0A1,352Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode