harness-engineering

harness-engineering is a skill for Claude Code, Codex from bouob/agent-harness. It costs 167 tokens per session (2,312 once invoked), scanned A, original, MIT.

A framework for planning and running work with several AI agents using three roles: Planner, Generator, and Evaluator. It also helps design or review the surrounding instructions, tools, and checks that guide those agents.

In plain words
What is it for?
Use it to plan multi-agent tasks, split work between agents, review an existing agent workflow, diagnose a failed workflow, or decide how to break down a complex request.
Why use it?
It helps organize work that is too large for one context window, benefits from parallel agents, or needs browser-level verification with Playwright.

Skill for Claude CodeCodex

Part of the agent-harness plugin — 5 skills, 1 command, 1 hook shipped together

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 skills/bouob/agent-harness/harness-engineering
Any agent
npx skills add bouob/agent-harness --skill harness-engineering
Clone the repo
git clone --depth 1 https://github.com/bouob/agent-harness

Made for: Claude Code, Codex.

Or install agent-harness, the plugin that ships this one along with the rest of its 5 skills, 1 command, 1 hook.

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/bouob/agent-harness/harness-engineering.svg)](https://agentmods.dev/skills/bouob/agent-harness/harness-engineering)
Your own site
<a href="https://agentmods.dev/skills/bouob/agent-harness/harness-engineering"><img src="https://agentmods.dev/badge/skills/bouob/agent-harness/harness-engineering.svg" alt="Measured on agentmods" height="20"></a>
Per session 167 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,312 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00167 $0.02312
Opus 5 $0.00084 $0.01156
Sonnet 5 $0.00033 $0.00462
Haiku 4.5 $0.00017 $0.00231

Measured 4d ago against content hash 10b4038b9414, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

skills/harness-engineering/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/harness-engineering — Multi-Agent Harness Framework

A flexible framework for the Planner-Generator-Evaluator (P-G-E) design pattern as formalized by Anthropic Engineering on 2026-04-04. Where /sprint is a fixed 6-phase pipeline producing .sprint/<ts>/ artifacts, this skill helps you reason about, construct, or review harnesses that don't fit a rigid template — including the harness elements (skills/rules/hooks/references) that surround them.

Core Premise

Every component in a harness encodes an assumption about what the model can't do on its own — and those assumptions are worth stress-testing. (Anthropic, 2026-04-04)

The harness is durable goods; the model is a replaceable engine. As models strengthen, remove non-load-bearing scaffolding. As failure modes appear, add elements that survive model swaps (Hooks > Skills > Rules > References > Prompts on the durability axis).


Input

$ARGUMENTS

If empty: ask whether the user wants (a) execution of a P-G-E task, (b) design review of an existing skill/rule/hook, (c) routing/decomposition advice, or (d) diagnosis of a failed harness run — then proceed.


Procedure

Step 1 — Classify the Request

State the chosen mode in one line before proceeding. Do not collapse modes — they have different downstream procedures.

Mode Trigger Goes to
Execute "do X using multi-agent / subagents / P-G-E" Step 2
Design "should this be a hook / skill / rule?" or "review this skill" Step 6
Route "which model should handle X?" or "spawn subagent or inline?" Step 5
Diagnose "why did the harness fail?" / context drift / stale handoff Step 7

Step 2 — Plan: Expand the Spec

Apply Planner discipline. The Planner's job is to expand a brief prompt (1–4 sentences) into a detailed spec — not to write code. Output:

  1. Re-stated goal (one sentence)
  2. Deliverables (files, decisions, reports)
  3. Sprint contract: testable success criteria with hard thresholds
  4. Decomposition into 2–7 tasks; each:
    • Self-contained (cold-start agent can execute with task text alone)
    • Measurable (acceptance criteria start with a verb: Returns, Renders, Stores)
    • Scoped (≤50k tokens of work)
  5. Dependencies → tasks with no deps go to parallel_batch; with deps go to sequential_tasks.

Read the full file on GitHub · 182 lines

Files

What ships with it

5 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. 4d ago First seen · 182 lines · 167 tokens per session scan A 10b4038b9414

Subscribe to this mod's changes

harness-engineering is a skill published in the GitHub repository bouob/agent-harness (5 stars, last pushed 1mo ago), licensed MIT. It adds 167 tokens to every session and 2,312 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

ci-review

CI-optimized code review: multi-agent parallel review with confidence scoring and atomic GitHub PR review posting. Runs specialized review agents, scores findings, and submits a GitHub PR review via post-review.sh. Always executes post-review.sh to submit a review on every run (including zero-findings runs). Triggers…

rube-de/cc-skills · 127 tokens

pr-check

PR review compliance: fetch review comments from an open PR, categorize as resolved/unresolved/dismissed, critically evaluate fixable items, implement approved fixes, and reply inline. Pass --unattended to halt on human-judgment items (emitted as Pending-Human) instead of prompting via AskUserQuestion.

rube-de/cc-skills · 67 tokens

council

Consult external AI council (Gemini 3.8 Flash, Codex, GLM-5.3, Kimi) for thorough reviews and consensus-driven decisions. Use ONLY when explicitly invoked with "/council" or when user says "consult the council", "invoke council", or "council review". Do NOT auto-trigger on generic phrases like "thorough review".

rube-de/cc-skills · 82 tokens

babysit

PR babysitter: monitors CI status, auto-rebases when behind, auto-fixes CI where possible, delegates review comment handling to dlc:pr-check, and re-requests review after fixes. Designed for /loop usage with Remote Control.

rube-de/cc-skills · 53 tokens

pr-validity

PR validity analysis: fetch PR diff, extract new code additions, search existing codebase for duplicate or overlapping implementations, classify changes, and create a structured GitHub issue.

rube-de/cc-skills · 38 tokens

brainstorm

You MUST use this skill before /pm when work is ambiguous, scope is unclear, or multiple approaches exist. Explores problem space, proposes 2-3 approaches with trade-offs, and produces an approved spec document that feeds into both issue creation (/pm) and implementation planning (/cdt). Triggers: brainstorm, explore…

rube-de/cc-skills · 96 tokens