What is harness-init AGENTS.md?

A repository-orientation guide for a Claude Code plugin that prepares software projects for AI-assisted development using documented rules, tests, checks, and automation scripts.

Use it to understand the repository layout, required files, technology choices, development rules, testing boundaries, continuous-integration setup, and maintenance scripts.

It gives an agent a clear map of the project and the constraints it must follow, reducing confusion when working in an unfamiliar codebase.

How Gizele1/harness-init configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Gizele1/harness-init. 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/Gizele1/harness-init/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Gizele1/harness-init

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gizele1/harness-init/agents-md/github.svg)](https://agentmods.dev/instructions/gizele1/harness-init/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/gizele1/harness-init/agents-md"><img src="https://agentmods.dev/badge/instructions/gizele1/harness-init/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/gizele1/harness-init/agents-md"><img src="https://agentmods.dev/badge/instructions/gizele1/harness-init/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,100 This file is loaded in full into every session.

When invoked 1,100 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.

Model	Per session	Once invoked
Fable 5.1	$0.01100	$0.01100
Opus 5.5	$0.00440	$0.00440
Sonnet 5.5	$0.00220	$0.00220
Haiku 4.5	$0.00110	$0.00110

Measured 2mo ago against content hash 44012a997138, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

harness-init 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 · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

harness-init

Agent orientation map. Read this first when entering this repo.

What this is

A Claude Code plugin that scaffolds agent-ready repos using OpenAI's harness engineering methodology. It produces AGENTS.md, docs/, boundary tests, linter rules, CI pipelines, and GC scripts for target repos through 8 phases (Phase 0-7).

Stack

Layer	Tech
Language	Markdown + JSON
Platform	Claude Code Plugin
License	MIT

Directory structure

.
├── AGENTS.md                          # You are here
├── ARCHITECTURE.md                    # Layer definitions and file relationships
├── CLAUDE.md                          # Agent development instructions
├── INSTALL.md                         # Machine-readable install instructions
├── README.md                          # User-facing docs (English)
├── README_CN.md                       # User-facing docs (Chinese) — must mirror README.md
├── .claude-plugin/
│   ├── marketplace.json               # Marketplace registration (required for plugin install)
│   └── plugin.json                    # Plugin metadata (name, version, skills path)
├── docs/
│   ├── architecture/
│   │   └── LAYERS.md                  # Layer rules, dependency constraints
│   ├── golden-principles/
│   │   ├── SKILL_AUTHORING.md         # Skill file DO/DON'T patterns
│   │   ├── DOCUMENTATION.md           # Doc consistency patterns
│   │   └── REFERENCES.md              # Reference template patterns
│   └── SECURITY.md                    # Secrets, exclusion rules
├── skills/
│   └── harness-init/
│       ├── SKILL.md                   # The skill itself — 8-phase execution logic
│       └── references/                # Templates loaded on-demand by SKILL.md
│           ├── agents-md-template.md
│           ├── boundary-test-template.md
│           ├── ci-templates.md
│           ├── context-strategy.md
│           ├── exec-plan-template.md
│           ├── gc-patterns.md
│           ├── golden-principles-guide.md
│           ├── layer-templates.md
│           ├── security-template.md
│           ├── stack-routing.md
│           └── tool-routing.md
├── scripts/
│   ├── check-docs.sh                 # Doc consistency checker (CI + local)
│   └── gc/
│       └── check-consistency.sh       # GC consistency checker (CI + local)
└── .github/workflows/
    ├── ci.yml                         # Plugin validation + doc consistency
    └── gc.yml                         # Weekly entropy scan

Read the full file on GitHub · 103 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.

2mo ago First seen · 103 lines · 1,100 tokens per session scan A 44012a997138

Subscribe to this mod's changes

harness-init AGENTS.md is an instructions file published in the GitHub repository Gizele1/harness-init (57 stars, last pushed 7mo ago), licensed MIT. It adds 1,100 tokens to every session, about $0.0044 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 2026-08-30.

Building agents

harness-init AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
harness-init AGENTS.mdGizele1/harness-init	Instructions file	57	7mo ago	MIT	A	1,100	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

harness-init: Instructions file for Codex