A workflow for coordinating several fresh AI agents through planning, implementation, evaluation, and retrospective review. TDD, or test-driven development, means writing tests as part of the implementation process.

Use it to turn an approved design into code, run checkpoint evaluations, perform end-to-end and full verification, create a pull request, and record lessons for future tasks.

It separates discovery, coding, checking, and learning so long tasks are less likely to drift away from the agreed requirements. Review checkpoints provide additional quality checks during execution.

harness — Skill for Claude Code and Codex by stone16

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 stone16/harness-engineering-skills --skill harness

Clone the repo

git clone --depth 1 https://github.com/stone16/harness-engineering-skills

Made for: Claude Code, Codex.

Or install harness-engineering-skills, the plugin that ships this one along with the rest of its 2 skills, 5 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/stone16/harness-engineering-skills/harness/github.svg)](https://agentmods.dev/skills/stone16/harness-engineering-skills/harness)

Your own site

<a href="https://agentmods.dev/skills/stone16/harness-engineering-skills/harness"><img src="https://agentmods.dev/badge/skills/stone16/harness-engineering-skills/harness/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/stone16/harness-engineering-skills/harness"><img src="https://agentmods.dev/badge/skills/stone16/harness-engineering-skills/harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,132 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.00019	$0.02132
Opus 5	$0.00010	$0.01066
Sonnet 5	$0.00004	$0.00426
Haiku 4.5	$0.00002	$0.00213

Measured yesterday against content hash fa569f7c62b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

harness scanned grade C with 2 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 5 executable files (hooks/phase-guard.mjs, scripts/_cohort_spec.py, scripts/claude-agent-invoke.sh, …), 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Verify (review roles): `{ find ~/.claude/plugins -path '*/plugins/harness-engineering-skills/agents/harness-*.md' -type f 2>/dev/null; ls plugins/harness-engineering-skills/agents/harness-*.md 2>/dev/null; ls ~/.claude/a

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

If not found, try `find ~/.claude/skills -path "*/harness/scripts/harness-engine.sh"` or `find ~/.codex/skills -path "*/harness/scripts/harness-engine.sh"` as fallback. In a checked-out repo, `plugins/harness-engineering

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

harness — 89% identical, 41 lines differ

plugins/harness-engineering-skills/skills/harness/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness — Multi-Agent Orchestration

Orchestrate complex tasks through Planning -> Generation -> Evaluation -> Retro. Fresh sub-agents per checkpoint prevent drift. Retro accumulates learning across tasks.

Protocol Loading

This skill splits into two protocol files to minimize context usage. Read the one matching your intent before proceeding.

Intent	Trigger phrases	Action
Planning	"harness plan", "harness this task", "use harness", "harness spec"	Read references/planning-protocol.md
Execution	"harness continue", "harness execute ", "harness "	Read references/execution-protocol.md

After loading the protocol, follow it completely. Do not proceed without reading the appropriate reference file.

Recommended Workflow

Session 1 (Claude Code) → Brainstorm + Spec → Spec review with cross-model evaluator
    ↓ spec approved
Session 2 (Codex)       → Execute checkpoints → Evaluate → E2E → Full-verify → PR → Retro
    ↕ Claude CLI as review-loop peer (cross-model quality gate)

Session 1: Claude Code for interactive discovery — brainstorming + multi-turn Q&A to establish requirements. After the user approves the brainstormed design, spec drafting and the Spec Evaluator review loop run autonomously (agent-to-agent until consensus). See references/planning-protocol.md "Post-Brainstorming Autonomy".
Session 2: Codex for autonomous execution — implementation, evaluation, PR creation, retro. Claude CLI serves as cross-model reviewer via review-loop.
Both hosts support both phases. The above is the recommended flow, not a hard constraint.

Prerequisites

superpowers plugin installed (Claude Code): Generator preloads TDD, verification, debugging skills
Reviewer role definitions: harness-convention-scout.md, harness-spec-evaluator.md, harness-generator.md, harness-evaluator.md, harness-retro.md — ship with this plugin at plugins/harness-engineering-skills/agents/; user overrides may live at ~/.claude/agents/harness-*.md
python3 on PATH (engine JSON operations)
git repository initialized
For Codex-hosted execution: claude CLI on PATH for sub-agent dispatch and review-loop

Read the full file on GitHub · 151 lines

Files

What ships with it

10 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.

yesterday Changed · -9 lines · -111 tokens per session fa569f7c62b4
9d ago First seen · 160 lines · 130 tokens per session scan C 4c5ba6587e98

Subscribe to this mod's changes

harness is a skill published in the GitHub repository stone16/harness-engineering-skills (32 stars, last pushed yesterday), licensed Apache-2.0. It adds 19 tokens to every session and 2,132 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Claude Code Code review Planning ai-code-review claude claude-code-plugin code-quality

logic-health

Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where…

hyhmrright/logic-lens · 180 tokens

logic-diff

Compare two code versions for semantic equivalence via semi-formal tracing of both versions side-by-side. Trigger when the user shares a refactor, rewrite, migration, or A/B implementation and wants to confirm behavior is unchanged — "did I break anything", "is this equivalent", "are these equivalent", "semantically…

hyhmrright/logic-lens · 192 tokens

river-review-code

A general code-review skill that checks readability, maintainability, and type safety, with routing for several specialized checks.

s977043/river-review · 51 tokens

Standard Review Policy for Midstream

Applies standard AI review policy guidelines for midstream (implementation) phase reviews.

s977043/river-review · 23 tokens

recipe-front-review

Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.

shinpr/claude-code-workflows · 29 tokens

new-skill

Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…

hyhmrright/brooks-lint · 145 tokens

harness