harness-engineering

harness-engineering is a skill for Claude Code, Codex from guanyang/open-agent-hub. It costs 47 tokens per session (2,297 once invoked), scanned A, a copy of harness-engineering, MIT.

Guidance for designing the control systems around agents that work autonomously for long periods.

In plain words
What is it for?
Use it to build autonomous research or experimentation loops, evaluation setups, durable logs, rollback rules, and systems that prepare changes for human approval.
Why use it?
It helps agents receive feedback, preserve progress, recover from failures, and stay within safe editing and approval limits.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Part of the open-agent-hub plugin — 102 skills, 3 commands, 5 agents, 6 MCP servers shipped together

Good fit Use it to build autonomous research or experimentation loops, evaluation setups, durable logs, rollback rules, and systems that prepare changes for human approval.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/guanyang/open-agent-hub/harness-engineering
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 guanyang/open-agent-hub --skill harness-engineering
Clone the repo
git clone --depth 1 https://github.com/guanyang/open-agent-hub

Made for: Claude Code, Codex.

Or install open-agent-hub, the plugin that ships this one along with the rest of its 102 skills, 3 commands, 5 agents, 6 MCP servers.

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-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/guanyang/open-agent-hub/harness-engineering.svg)](https://agentmods.dev/skills/guanyang/open-agent-hub/harness-engineering)
Your own site
<a href="https://agentmods.dev/skills/guanyang/open-agent-hub/harness-engineering"><img src="https://agentmods.dev/badge/skills/guanyang/open-agent-hub/harness-engineering.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,297 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 100% copy Near-identical to another mod 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 $0.00047 $0.02297
Opus 5 $0.00023 $0.01149
Sonnet 5 $0.00009 $0.00459
Haiku 4.5 $0.00005 $0.00230

Measured 5d ago against content hash dde3d8f46d4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

harness-engineering 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 5d 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.

Origin

This is a copy

100% identical to harness-engineering — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/harness-engineering/SKILL.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Engineering

Harness engineering designs the control system around an agent: what it may edit, how it receives feedback, where it writes state, how failures recover, and who can approve irreversible actions. The harness is the difference between a helpful agent session and an autonomous loop that can run for days without corrupting its objective.

When to Activate

Activate this skill when:

  • Building autonomous research or experimentation loops
  • Designing an agent environment with locked metrics and editable code or content
  • Creating PR-producing or background agents
  • Evaluating whether an agent can safely run without frequent human prompts
  • Adding novelty, ablation, pruning, rollback, or durable logging to an agent workflow
  • Preventing agents from gaming benchmarks, weakening rubrics, or losing state across compaction

Do not activate this skill for adjacent work owned by other skills:

  • General quality gates, regression suites, or outcome metrics without autonomous control surfaces: evaluation.
  • Tool schemas, response formats, and recovery errors for harness tools: tool-design.
  • Project-level task-model fit, pipeline shape, and cost planning: project-development.
  • Remote sandbox, warm-pool, and hosted session infrastructure: hosted-agents.

Core Concepts

Harness Boundary

Separate the agent from the environment it operates inside. The agent proposes actions; the harness defines allowed surfaces, feedback, persistence, and promotion rules.

Use four surface classes:

Surface Examples Rule
Locked Eval metric, rubric, validation script, merge policy Agent may read and propose changes, but cannot score itself with modified rules
Editable Skill draft, experiment file, prompt, config under test Agent may mutate during the loop
Append-only Results log, research thread, rejected ideas Agent may append, not rewrite
Human-controlled Merge, production deploy, credentials, destructive operations Requires explicit human approval

Read the full file on GitHub · 235 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. 5d ago First seen · 235 lines · 47 tokens per session scan A dde3d8f46d4d

Subscribe to this mod's changes

harness-engineering is a skill published in the GitHub repository guanyang/open-agent-hub (961 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 2,297 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to harness-engineering, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

ac-criteria-validator

Validate acceptance criteria and feature completion. Use when checking if features pass, validating test results, verifying acceptance criteria, or determining feature completion status.

majiayu000/claude-skill-registry · 33 tokens

writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment.

oyi77/1ai-skills · 20 tokens

iso-write

Implement a written plan using TDD, without committing. Use when invoked as /iso-write [--no-branch | --branch= | --worktree] or handed an implementation plan to build. By default it resumes or cuts a branch derived from the plan filename only when the current branch is a base branch (dev, develop, test, prod, main…

IsaiaScope/ai · 172 tokens

test-coverage-design

Use when deciding what to test, reviewing whether a feature is adequately covered before calling it done, or when tests pass but you're unsure they exercise the real risks. Derives coverage obligations from code + spec, finds gaps (including paths outside the test runner's scope), and designs a minimal…

Redtropig/harness-anchor · 86 tokens

bestow-curse

Bestow Curse saddles a target with a lasting disadvantage. The real-world version is constraint injection: deliberately adding friction, limitations, or handicaps to see how a system, process, or team adapts. This is the skill of resilience testing through artificial adversity — bandwidth throttling, feature removal…

Hmbown/Wizards-of-the-Ghosts · 68 tokens

confusion

Confusion makes targets act randomly and unpredictably. The real-world version is chaos engineering: injecting controlled randomness, unexpected inputs, and edge cases to discover how systems behave when things go wrong. This is fuzzing, monkey testing, and the art of breaking things on purpose so they do not break by…

Hmbown/Wizards-of-the-Ghosts · 65 tokens