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/gizele1/harness-init/agents-mdgit clone --depth 1 https://github.com/Gizele1/harness-initWhat 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 | $0.01100 | $0.01100 |
| Opus 5 | $0.00550 | $0.00550 |
| Sonnet 5 | $0.00220 | $0.00220 |
| Haiku 4.5 | $0.00110 | $0.00110 |
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 3d 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.
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
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.
- 3d ago First seen · 103 lines · 1,100 tokens per session scan A 44012a997138
harness-init AGENTS.md is an instructions file published in the GitHub repository Gizele1/harness-init (53 stars, last pushed 5mo ago), licensed MIT. It adds 1,100 tokens to every session, about $0.0055 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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.