repository-harness: Instructions file for Codex

AGENTS.md

repository-harness AGENTS.md is an instructions file for Codex, OpenCode from hoangnb24/repository-harness. It costs 332 tokens per session, scanned A, original, MIT.

A set of instructions for working in repository-harness, a project that tests and guides coding-agent work. It explains which repository documents are authoritative and when changes or planning files are needed.

In plain words
What is it for?
Investigating requests, implementing bounded changes, validating results, coordinating longer work, and reporting reusable problems agents encounter.
Why use it?
It prevents agents from changing files during read-only tasks or making policy decisions without checking the project's source of truth.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: $skill-name invocation.

This is hoangnb24/repository-harness's own configuration. It tells Codex and OpenCode how to work on repository-harness 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 repository-harness configures →

About the project

repository-harness is a repository protocol that makes a software codebase easier for coding agents to understand and work on safely. It is for teams using Claude Code, Codex, Cursor, and similar agents who need authoritative documents, durable plans, explicit decision boundaries, and evidence for completed work. Its catalogue entries install the protocol's skills and instructions.

hoangnb24/repository-harness · 1,215 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to hoangnb24/repository-harness. 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/hoangnb24/repository-harness/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/hoangnb24/repository-harness

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 repository-harness AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hoangnb24/repository-harness/agents-md.svg)](https://agentmods.dev/instructions/hoangnb24/repository-harness/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/hoangnb24/repository-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/hoangnb24/repository-harness/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 332 This file is loaded in full into every session.
When invoked 332 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 $0.00332 $0.00332
Opus 5 $0.00166 $0.00166
Sonnet 5 $0.00066 $0.00066
Haiku 4.5 $0.00033 $0.00033

Measured 8d ago against content hash 745a9e87a0f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

repository-harness 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 8d 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 · 32 lines

What it actually says

Agent Instructions

Harness

Start with the requested outcome and use the repository as the system of record. Read docs/WORKFLOW.md and only relevant product, design, plan, code, and validation material.

  • Answers, explanations, reviews, diagnoses, plans, and status reports are read-only. Inspect only what is needed; change nothing.
  • For a bounded change, inspect affected behavior and proof, implement, and validate. No control-plane operation is required.
  • Use one docs/plans/active/ file when work spans sessions, coordinates contributors, has dependencies, or needs recovery. Move it to docs/plans/completed/ only after validation.
  • Before editing, identify repository authority for each new externally observable policy. If materially different choices remain open, stop before edits; configurable defaults are not authority.
  • For architecture, reliability, security, or quality invariant work, read docs/patterns/encoding-invariants.md and enforce only accepted rules.
  • Report reusable agent friction. Change guidance, tools, runbooks, or validation for that purpose only when explicitly asked to use $improve-harness.
  • Also pause when product intent remains ambiguous, recovery is difficult, validation is weakened, or authority is insufficient.
  • Claim completion only with executable or observable evidence. Report outcome, changes, validation, and unresolved risks.

Harness has no task database or orchestration lifecycle. Use repository plans and behavior-level proof; do not create parallel control-plane state.

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. 8d ago First seen · 32 lines · 332 tokens per session scan A 745a9e87a0f3

Subscribe to this mod's changes

repository-harness AGENTS.md is an instructions file published in the GitHub repository hoangnb24/repository-harness (1,215 stars, last pushed 25d ago), licensed MIT. It adds 332 tokens to every session, about $0.0017 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.

Related

Other instructions, from other repositories

agent-rulescope tests.instructions.md

Instructions for 13624725933/agent-rulescope, a project described as: See exactly which instructions your coding agent inherits. Scan AGENTS.md, CLAUDE.md, Cursor and Copilot rules.

13624725933/agent-rulescope · 38 tokens

agent-rulescope copilot-instructions.md

Copilot instructions for 13624725933/agent-rulescope, a project described as: See exactly which instructions your coding agent inherits. Scan AGENTS.md, CLAUDE.md, Cursor and Copilot rules.

13624725933/agent-rulescope · 25 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens