harn AGENTS.md

harn AGENTS.md is an instructions file for Codex, OpenCode from burin-labs/harn. It costs 3,779 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Harn, a programming language and runtime for coordinating AI agents. It manages orchestration, transcripts, replay and evaluation, worker relationships, capability rules, and audit information.

In plain words
What is it for?
Use them when changing orchestration, agent transcripts, delegated workers, capability policies, mutation sessions, or host integrations.
Why use it?
They clarify which responsibilities belong to Harn and which belong to host applications, helping agents preserve shared behavior across command-line, terminal, editor, and cloud interfaces.

Instructions file for CodexOpenCode

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/burin-labs/harn/agents-md
Clone the repo
git clone --depth 1 https://github.com/burin-labs/harn

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 harn AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/burin-labs/harn/agents-md.svg)](https://agentmods.dev/instructions/burin-labs/harn/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/burin-labs/harn/agents-md"><img src="https://agentmods.dev/badge/instructions/burin-labs/harn/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,779 This file is loaded in full into every session.
When invoked 3,779 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 $0.03779 $0.03779
Opus 5 $0.01889 $0.01889
Sonnet 5 $0.00756 $0.00756
Haiku 4.5 $0.00378 $0.00378

Measured yesterday against content hash d29eb404ca64, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harn 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 yesterday.

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 · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Harn is a programming language and runtime for orchestrating AI agents.

This file is the repository contract for Codex, Claude, and other coding agents. CLAUDE.md must remain a symlink to it. The durable design principles live in Engineering principles:

  • ambitious outcomes behind boring seams;
  • one owner with many projections;
  • structure over prose;
  • evidence matched to claims;
  • canonical paths;
  • controllable autonomy;
  • cross-surface convergence;
  • operationally complete launches.

Ownership

  • Harn owns orchestration, transcript lifecycle, replay/eval, delegated-worker lineage, capability policy, and mutation-session audit metadata.
  • Hosts own native presentation, approval UX, concrete file mutations, and undo/redo semantics.
  • Prefer the Harn runtime and stdlib over new host glue.
  • A semantic decision has one owner. CLI, TUI, IDE, headless, and cloud behavior should be projections or adapters, not parallel implementations.
  • Prefer deep modules: small interfaces that hide substantial behavior.
  • Make contracts structural with types, registries, events, generated projections, and drift checks. Prose should explain the contract, not enforce it.

Working agreement

  • Research, implement, verify, recover, and ship autonomously inside the approved scope.
  • Pause for genuine ambiguity, destructive or out-of-scope action, production impact, exceptional spend, or new authority—not routine reversible work.
  • Treat stop, wait, stand down, and pivot as control events. Do not continue stale work after one arrives.
  • Start from the claim and name a plausible falsifier. Match evidence to the claim; test counts alone are not proof.
  • Exercise the canonical user path for product claims and progress, interruption, recovery, and terminal state for liveness claims.
  • Use multiple trials and calibrated graders for stochastic quality claims.
  • "Ship" means landed on the intended main branch with required post-merge or release checks complete.

Read the full file on GitHub · 284 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. yesterday Changed · +42 lines · +643 tokens per session d29eb404ca64
  2. 5d ago First seen · 242 lines · 3,136 tokens per session scan A 87434069ace2

Subscribe to this mod's changes

harn AGENTS.md is an instructions file published in the GitHub repository burin-labs/harn (20 stars, last pushed today), licensed Apache-2.0. It adds 3,779 tokens to every session, about $0.0189 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.