agentmods.dev

harness AGENTS.md

harness AGENTS.md is an instructions file for Codex, OpenCode from puristajs/harness. It costs 516 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for working in the puristajs/harness repository, a self-hosted system for running and coordinating coding agents. It identifies the approved specifications, implementation rules, interfaces, and testing guidance.

In plain words
What is it for?
Use it when changing the harness, locating authoritative specifications, following TypeScript workspace rules, or checking required tests and implementation practices.
Why use it?
It gives contributors a shared source of truth and reduces the risk of implementing against outdated documents or repository conventions.

Instructions file for CodexOpenCode

not rated 5 yesterday A scan 516 tokens original Apache-2.0
View the source file puristajs/harness
Install

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.

agentmods
npx agentmods add instructions/puristajs/harness/agents-md
Clone the repo
git clone --depth 1 https://github.com/puristajs/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 harness AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/puristajs/harness/agents-md.svg)](https://agentmods.dev/instructions/puristajs/harness/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/puristajs/harness/agents-md"><img src="https://agentmods.dev/badge/instructions/puristajs/harness/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 516 This file is loaded in full into every session.
When invoked 516 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00516 $0.00516
Opus 5 $0.00258 $0.00258
Sonnet 5 $0.00103 $0.00103
Haiku 4.5 $0.00052 $0.00052

Measured 4d ago against content hash baedfe2b291a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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 · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guidance

This repository defines a self-hosted enterprise agent harness. It is lower-level harness infrastructure, not a SaaS product.

Source of Truth

  • Approved specs: specs/
  • Approved readiness gate: specs/.readiness-report.yaml
  • Product, architecture, and scope: specs/00-overview.md, specs/01-architecture.md
  • Stack and public API: specs/02-harness-config.md, specs/13-public-api.md
  • Interfaces and ports: specs/04-state-queue-stream.md, specs/05-sandbox.md, specs/06-models.md, specs/07-tools.md
  • Failure handling: specs/15-error-catalog.md
  • Test strategy: specs/16-testing.md
  • Plans, reviews, and tickets: plans/ (review findings and implementation plans live here, not under docs/)
  • Implementation conventions: .agent/IMPLEMENTATION.md

Use specs/ and plans/ as the only approved definition sources. Historical review material and previous implementation code are not source of truth.

Repository Rules

  • Use npm workspaces for TypeScript packages unless the specs are changed by a human.
  • Keep shared harness logic in packages/.
  • v1 has no deployable service/workers/apps package; examples under examples/ are private workspaces.
  • Core harness code depends on ports and contracts, not concrete provider SDKs.
  • Adapter packages own provider SDK dependencies and must pass shared contract tests.
  • Harness code must not depend on evals/, k8s/, or repo-local skills/.

Expected Commands

  • npm run lint
  • npm run build
  • npm test
  • npm run test:coverage
  • npm run test:types
  • npm run test:contracts
  • npm run test:integration
  • npm run test:failure

Implementation Rules

  • Follow each ticket's write_scope and read_scope.
  • Do not invent missing contracts, interfaces, data models, or failure behavior during implementation.
  • If a ticket depends on missing definition work, flag it in specs/.readiness-report.yaml or add a gap report under plans/ instead of guessing.
  • Preserve timeout, retry, idempotency, cleanup, DLQ/manual-intervention, backpressure, and telemetry behavior from specs.

Read the full file on GitHub · 46 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. 4d ago First seen · 46 lines · 516 tokens per session scan A baedfe2b291a

Subscribe to this mod's changes

harness AGENTS.md is an instructions file published in the GitHub repository puristajs/harness (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 516 tokens to every session, about $0.0026 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 2026-08-31.

agentagent-skillsagentic-aiagentic-workflowaiai-agents
Related

Other instructions, from other repositories

deer-flow copilot-instructions.md

Copilot instructions for bytedance/deer-flow, covering copilot onboarding instructions for deerflow, 1) repository summary, 2) runtime and toolchain requirements, 3) build/test/lint/run - verified command sequences and a. bootstrap and install.

bytedance/deer-flow · 1,714 tokens

LeAgent AGENTS.md

Instructions for vixues/LeAgent, covering leagent development guidelines, project overview, architecture, execution topology (one kernel, many ingresses) and surface map (where things live).

vixues/LeAgent · 6,799 tokens

sprawling CLAUDE.md

Instructions for 2youg1/sprawling: See AGENTS.md. It is the whole instruction set for this repository — the loop, what to read first, the five steps of one change, the rules a machine holds, and the language and commit conventions.

2youg1/sprawling · 83 tokens

codex-acp-bridge AGENTS.md

Instructions for normahq/codex-acp-bridge, covering codex-acp-bridge — agents.md, development standards, quality gates (required), logging policy and bridge guardrails.

normahq/codex-acp-bridge · 743 tokens

deckforge AGENTS.md

Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.

tph-kds/deckforge · 498 tokens

vant AGENTS.md

AGENTS.md instructions for dhaupin/vant, covering agents.md — vant agent guide, what is vant?, your job, brain router interface and middleware chain.

dhaupin/vant · 2,053 tokens