harness-review

harness-review is a skill for Claude Code, Codex from David405/harness-kit. It costs 81 tokens per session (372 once invoked), scanned A, original, Apache-2.0.

A production-readiness review process for pull requests, the proposed code changes submitted for team review before merging.

In plain words
What is it for?
Use it as a merge gate after implementation to compare changes with the contract, verify quality checks, identify risks, and decide whether the work should ship.
Why use it?
It checks first that the requested scope and success conditions were met, then looks for correctness, security, reliability, testing, and operational problems.

Skill for Claude CodeCodex

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

Good fit Use it as a merge gate after implementation to compare changes with the contract, verify quality checks, identify risks, and decide whether the work should ship.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/david405/harness-kit/harness-review
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 David405/harness-kit --skill harness-review
Clone the repo
git clone --depth 1 https://github.com/David405/harness-kit

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-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/david405/harness-kit/harness-review.svg)](https://agentmods.dev/skills/david405/harness-kit/harness-review)
Your own site
<a href="https://agentmods.dev/skills/david405/harness-kit/harness-review"><img src="https://agentmods.dev/badge/skills/david405/harness-kit/harness-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 372 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 $0.00081 $0.00372
Opus 5 $0.00041 $0.00186
Sonnet 5 $0.00016 $0.00074
Haiku 4.5 $0.00008 $0.00037

Measured 7d ago against content hash 56501e1eab16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

harness-review 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 7d 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-review/SKILL.md · 44 lines

What it actually says

Harness review

Kit-owned. Edit in the harness-kit repo, not in the consumer repo.

Decide whether this change should ship. Correctness over style.

When to use

  • After every contract execution — once VERIFY is green, before staging or reporting done
  • Reviewing a PR, or grading a feature sitting at PENDING_REVIEW
  • When the user asks whether a change should ship

Order matters

§0 contract compliance first, before any code reading: locate the contract, note the profile, walk Scope WILL and will NOT, compare the impact map to the actually changed files, mark every success criterion Pass / Fail / Untested with the observable quoted, then the quality gates.

Contract drift — partial or missing scope, failed criteria, scope creep — is request changes unless it was explicitly re-contracted.

If no contract exists, say so plainly and review on production readiness alone.

Rules that matter

  • Apply only the gates the declared profile puts in force; mark the rest N/A.
  • Architecture packs are graded only where AGENTS.md opts in.
  • Code-quality limits are graded by code-quality-gate, not re-litigated here.
  • The executor sets PENDING_REVIEW. PASS is human-only.

Form

templates/REVIEW.md

Files

What ships with it

1 file 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. 7d ago First seen · 44 lines · 81 tokens per session scan A 56501e1eab16

Subscribe to this mod's changes

harness-review is a skill published in the GitHub repository David405/harness-kit (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 81 tokens to every session and 372 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 2026-08-31.