review

review is a skill for Claude Code from 0xku/kon. It costs 11 tokens per session (866 once invoked), scanned A, original, MIT.

A code-review skill that examines current or selected changes and returns findings ranked by priority with concrete actions.

In plain words
What is it for?
Use it to review working-tree changes, staged files, commits, branches, or pull requests and identify issues an engineer should fix.
Why use it?
It helps catch important problems in a set of changes before they are merged, while focusing the review on the relevant diff.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it to review working-tree changes, staged files, commits, branches, or pull…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/0xku/kon/review
View source ↗ 0xku/kon
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 0xku/kon --skill review
Clone the repo
git clone --depth 1 https://github.com/0xku/kon

Made for: Claude Code.

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 review

README.md
[![agentmods](https://agentmods.dev/badge/skills/0xku/kon/review.svg)](https://agentmods.dev/skills/0xku/kon/review)
Your own site
<a href="https://agentmods.dev/skills/0xku/kon/review"><img src="https://agentmods.dev/badge/skills/0xku/kon/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 866 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 $0.00011 $0.00866
Opus 5 $0.00005 $0.00433
Sonnet 5 $0.00002 $0.00173
Haiku 4.5 $0.00001 $0.00087

Measured 7d ago against content hash 91f9fbe761a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 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.

src/kon/builtin_skills/review/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review the requested code changes as if you are reviewing another engineer's PR.

User-provided target or constraints (honor these): $ARGUMENTS

Target selection

  • If no target is provided, review the current code changes: staged, unstaged, and untracked files.
  • If the user provides a base branch, review the changes that would merge into that branch. Find the merge base and inspect the diff from that commit.
  • If the user provides a commit SHA, review only the changes introduced by that commit.
  • If the user provides a PR number, PR URL, or text like PR#68 feat/headless-mode "feat: add non-interactive prompt mode", assume the GitHub CLI is available. Use gh pr view to inspect PR metadata, resolve the base/head branches, fetch as needed, compute the merge base, and review the PR diff. Do not checkout a different branch unless the user explicitly asks or confirms.
  • For PRs, do not assume the head branch exists on origin; it may live on a contributor fork. Prefer gh pr checkout --detach <number> only if checkout is acceptable, or fetch the head repository/ref reported by gh pr view --json headRepository,headRefName into a temporary remote/ref before diffing.
  • For a PR scenario such as /review PR#68 feat/headless-mode "feat: add non-interactive prompt mode", use the PR number/title/branch as hints, verify them with gh pr view 68, then review the code changes relative to the PR base branch.

Review rubric

Only report issues the original author would likely fix if they knew about them.

Flag a finding only when:

  • it meaningfully affects correctness, security, performance, reliability, or maintainability;
  • it is discrete and actionable;
  • it appears introduced by the reviewed change;
  • you can identify the affected code path or user scenario;
  • it is not merely a style preference, nit, or intentional behavior change.

Do not stop at the first issue. Return all qualifying findings. If there are no findings worth fixing, say so clearly.

Investigation guidance

Read the full file on GitHub · 73 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. 7d ago First seen · 73 lines · 11 tokens per session scan A 91f9fbe761a9

Subscribe to this mod's changes

review is a skill published in the GitHub repository 0xku/kon (353 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 866 once invoked, about $0.0001 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 2026-08-30.