review

A structured code-review skill for local changes, GitHub pull requests, or selected paths. It identifies concrete issues with severity labels and includes file locations and line numbers when possible.

In plain words
What is it for?
Use it with /review, a pull-request number, a folder or file path, or a Git comparison such as main...HEAD.
Why use it?
It turns a broad request to check code into actionable findings instead of general comments. It is read-only, so it reports results without changing files or posting review comments.

Skill for Claude CodeCodex

Part of the review plugin — 1 skill, 1 agent 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/harnessprotocol/harness-kit/review
Any agent
npx skills add harnessprotocol/harness-kit --skill review
Clone the repo
git clone --depth 1 https://github.com/harnessprotocol/harness-kit

Made for: Claude Code, Codex.

Or install review, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,589 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 $0.00103 $0.01589
Opus 5 $0.00051 $0.00794
Sonnet 5 $0.00021 $0.00318
Haiku 4.5 $0.00010 $0.00159

Measured 3d ago against content hash 25540dd45263, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

plugins/review/skills/review/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer

Overview

Produce structured code reviews for local branch changes, open PRs, or scoped paths. Designed to give concrete, actionable feedback — not a vague summary.

Core principles:

  1. Read-only. Never modify files or post comments anywhere. Output goes to the conversation only.
  2. Concrete over vague. Every concern includes a file path, line number if possible, and a specific issue. No "consider refactoring this" without saying exactly what and why.
  3. Severity matters. Distinguish production-breaking blockers from style nits. Don't inflate every concern to a warning.
  4. No praise inflation. "Straightforward rename, no concerns" is a complete review. Don't add empty praise.

Invocation Examples

/review                    # review current branch vs base branch
/review 123                # review PR #123 via gh pr diff
/review src/auth/          # review changes scoped to a path
/review main...HEAD        # review with explicit git range

Workflow Order (MANDATORY)

You MUST follow this order. No skipping steps.


Step 1: Parse Input

Classify the argument:

Input Detection Action
No argument Empty / bare /review Review current branch vs base using git diff main...HEAD
PR number Numeric string (e.g. 123) Fetch diff with gh pr diff 123
Path filter Looks like a file or directory path Scope git diff main...HEAD -- <path> to that path
Git range Contains ... or .. Use directly as the git range

If gh CLI is not available and user provided a PR number: say "gh CLI not found — run brew install gh and authenticate with gh auth login to review PRs by number. For local branch review, run /review without arguments." Then stop.


Step 2: Gather Changes

Run the appropriate command to get the diff:

  • Local branch: git diff main...HEAD (or git diff $(git merge-base HEAD main)..HEAD if the first fails)
  • PR number: gh pr diff <number>
  • Path-scoped: git diff main...HEAD -- <path>

Read the full file on GitHub · 162 lines

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. 3d ago First seen · 162 lines · 103 tokens per session scan A 25540dd45263

Subscribe to this mod's changes

review is a skill published in the GitHub repository harnessprotocol/harness-kit (10 stars, last pushed 3d ago), licensed Apache-2.0. It adds 103 tokens to every session and 1,589 once invoked, about $0.0005 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

learn

Guided, hands-on course teaching architects how to use Codex or Claude Code — six short modules, each built around an exercise on a bundled sandbox project (a fictional Brooklyn art museum expansion). Resumable across sessions via PROGRESS.md. Use when the user runs $learn or /as:learn, says they're new to AI-assisted…

AlpacaLabsLLC/skills-for-architects · 80 tokens

studio

Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.

AlpacaLabsLLC/skills-for-architects · 65 tokens

epd-to-spec

Write CSI specification language for EPD submittals and sourced GWP limits. Use to add embodied-carbon or EPD requirements to specs; not to parse, find, or compare EPDs.

AlpacaLabsLLC/skills-for-architects · 45 tokens

occupancy-calculator

Calculate code occupant loads by area with gross/net factors and jurisdiction checks. Use for "how many people can this space hold," IBC Table 1004.5, egress inputs, or occupancy-load reports; not for workplace headcount planning.

AlpacaLabsLLC/skills-for-architects · 55 tokens

zoning-analysis-nyc

Analyze NYC lot zoning, FAR, height, setbacks, uses, and buildable envelope from PLUTO and the Zoning Resolution. Use for "what can I build"; use nyc-bsa for relief and zoning-envelope for 3D visualization.

AlpacaLabsLLC/skills-for-architects · 57 tokens

workplace-programmer

Build office space programs through guided workplace strategy: area splits, room schedules, and planned seat counts. Use to program or size a workplace; not for code occupant-load calculations.

AlpacaLabsLLC/skills-for-architects · 40 tokens