What is harness AGENTS.md?

Repository instructions for Harness, a containerized environment for running coding agents. They document the project structure, commands, documentation site, images, linting, formatting, and end-to-end tests.

Use them when building Harness, creating container images, updating documentation, running checks, or testing the command-line tool.

They help agents follow the repository’s build and testing process without guessing which commands or components matter.

How boldblackai/harness configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to boldblackai/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/boldblackai/harness/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/boldblackai/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.

README.md

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

Your own site

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

Per session 4,509 This file is loaded in full into every session.

When invoked 4,509 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	$0.04509	$0.04509
Opus 5.5	$0.01804	$0.01804
Sonnet 5.5	$0.00902	$0.00902
Haiku 4.5	$0.00451	$0.00451

Measured 17d ago against content hash 6fdaba83c773, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 17d 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 · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

harness

Project Overview

Harness is a portable containerized environment for running coding agents. See README.md for more project details.

Documentation website: Built with Zensical from docs/. Config in zensical.toml. Deploys to GitHub Pages via .github/workflows/docs.yml, which also runs a build-only check on PRs that touch docs/, zensical.toml, or the workflow itself (so doc build failures are caught before merge). Build locally with pip install zensical && zensical build --clean (CI uses uv tool install zensical==0.0.43). Canonical URL is https://harness.boldblack.ai/docs/ (site_url in zensical.toml): the marketing site (boldblackai/harness-site, AWS Amplify) mirrors the published Pages tree into its build via scripts/fetch-docs.py and serves it at /docs/; the Pages deploy optionally pings an Amplify rebuild webhook (AMPLIFY_DOCS_WEBHOOK_URL secret). Zensical emits relative links, so the tree is relocatable — keep it that way (no absolute-internal-link builds).

Commands

pnpm build            # Compile TypeScript → bin/harness.js
make build            # Same via Makefile
make image            # Build all Docker images (base + opencode + hermes variants)
make image-base       # Build base image only
make image-opencode   # Build opencode variant
make image-hermes     # Build hermes variant
make image-egress-proxy # Build the egress gateway image (squid)
pnpm link --global    # Make `harness` CLI available globally for local testing
pnpm lint             # Run all linters (biome, markdownlint, shellcheck, hadolint, actionlint)
pnpm format           # Auto-format with Biome
pnpm test:e2e         # Run e2e CLI tests (uses a docker shim, no real docker needed)

System linters (shellcheck, hadolint, actionlint) must be installed separately (brew install shellcheck hadolint actionlint).

Architecture

All CLI logic lives in src/harness.ts (compiles to bin/harness.js). It:

Read the full file on GitHub · 138 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.

17d ago Changed · +6 lines · +634 tokens per session 6fdaba83c773
1mo ago Changed · +1 tokens per session a486a52f6236
2mo ago Changed · +1 lines · +233 tokens per session e05156529b33
2mo ago First seen · 131 lines · 3,641 tokens per session scan A f7db8e04d30d

Subscribe to this mod's changes

harness AGENTS.md is an instructions file published in the GitHub repository boldblackai/harness (14 stars, last pushed 4d ago), licensed MIT. It adds 4,509 tokens to every session, about $0.0180 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.

harness AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
harness AGENTS.mdboldblackai/harness	Instructions file	14	4d ago	MIT	A	4,509	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: Instructions file for Codex