harness-use

harness-use is a skill for Claude Code, Codex from autonomous-ai/autonomous-os. It costs 84 tokens per session (1,385 once invoked), scanned A, original, Apache-2.0.

A guide for sending tasks to coding and research agents through Harness, a system that connects agents running on another computer. It covers selecting agents, sending follow-ups, and checking results.

In plain words
What is it for?
Use it to list or select paired agents, send spoken tasks, answer them, and inspect progress or recaps.
Why use it?
It provides a defined way to communicate with remote agents and handle delivery states. This avoids duplicate requests when a message may already have been sent.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it to list or select paired agents, send spoken tasks, answer them, and inspect progress or recaps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/autonomous-ai/autonomous-os/harness-use
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.

Any agent
npx skills add autonomous-ai/autonomous-os --skill harness-use
Clone the repo
git clone --depth 1 https://github.com/autonomous-ai/autonomous-os

Made for: Claude Code, Codex.

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-use

README.md
[![agentmods](https://agentmods.dev/badge/skills/autonomous-ai/autonomous-os/harness-use/github.svg)](https://agentmods.dev/skills/autonomous-ai/autonomous-os/harness-use)
Your own site
<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-os/harness-use"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-os/harness-use/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.

agentmods 80×15 button for harness-use

Your own site · 80×15
<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-os/harness-use"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-os/harness-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,385 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.01385
Opus 5 $0.00042 $0.00692
Sonnet 5 $0.00017 $0.00277
Haiku 4.5 $0.00008 $0.00138

Measured yesterday against content hash 780ef584d074, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

harness-use 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/harness.py, tests/test_harness.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/harness-use/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness use

Run python3 scripts/harness.py ACTION - from this skill directory on the device, with one JSON object on stdin. The helper calls the OS API on localhost; agent work runs on the paired computer, never on the device.

Do not run harness.py --help, read this file again, or inspect the skill directory during a user task; the commands and JSON shapes below are the complete contract. A send or answer that returns a receipt in queued, delivered, started, completed, or rejected has a known outcome. With a response target, it is the last Harness command of this turn: immediately reply exactly NO_REPLY. Do not call receipt, status, recap, list, or a second send/answer after it. The OS receives lifecycle events and delivers the result to the original turn. Only inspect a receipt when the mutation result is explicitly unknown (DeliveryUnknown / no usable receipt), or when the user asks for its delivery state; never resend automatically after inspecting it.

When the current input includes [harness-reply run_id=... channel=voice|web], copy those values unchanged into the response object of a send or answer call. After a successful mutation, reply exactly NO_REPLY; do not poll receipt/recap or rewrite the result. The OS delivers Harness's terminal recap directly to that run. channel=web displays it in Web Chat and suppresses TTS; channel=voice speaks the same recap.

Routing

Use Harness when the user asks a named, selected, current, coding, or research agent on the Mac to perform work. This includes requests such as “ask Claude Code to search for sushi restaurants” even when the requested agent may use a browser while it works. Do not fall back to computer-use or agent-management because an Autonomous Buddy pairing is absent.

computer-use is only for directly operating a visible Mac app or browser. agent-management / Autonomous Buddy is only for an explicit request to use Buddy or a legacy Buddy session.

Read the full file on GitHub · 52 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 First seen · 52 lines · 84 tokens per session scan A 780ef584d074

Subscribe to this mod's changes

harness-use is a skill published in the GitHub repository autonomous-ai/autonomous-os (317 stars, last pushed yesterday), licensed Apache-2.0. It adds 84 tokens to every session and 1,385 once invoked, about $0.0004 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 2026-09-09.