code-review

code-review is a skill for Claude Code from boparaiamrit/skills-by-amrit. It costs 36 tokens per session (1,705 once invoked), scanned A, original, MIT.

A structured review of changed code for correctness, security, performance, and ease of maintenance.

In plain words
What is it for?
It is for reviewing completed features, bug fixes, refactors, and changes ready to merge or deploy.
Why use it?
It helps catch edge cases, untested error paths, security problems, and design issues before code is merged or deployed.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the skills-by-amrit plugin — 33 skills, 34 commands, 9 agents shipped together

Good fit It is for reviewing completed features, bug fixes, refactors, and changes ready to merge or deploy.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/boparaiamrit/skills-by-amrit/code-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 boparaiamrit/skills-by-amrit --skill code-review
Clone the repo
git clone --depth 1 https://github.com/boparaiamrit/skills-by-amrit

Made for: Claude Code.

Or install skills-by-amrit, the plugin that ships this one along with the rest of its 33 skills, 34 commands, 9 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.

agentmods badge for code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/code-review/github.svg)](https://agentmods.dev/skills/boparaiamrit/skills-by-amrit/code-review)
Your own site
<a href="https://agentmods.dev/skills/boparaiamrit/skills-by-amrit/code-review"><img src="https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/code-review/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.

agentmods 80×15 button for code-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/boparaiamrit/skills-by-amrit/code-review"><img src="https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,705 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 $0.00036 $0.01705
Opus 5 $0.00018 $0.00852
Sonnet 5 $0.00007 $0.00341
Haiku 4.5 $0.00004 $0.00170

Measured 8d ago against content hash abd3fc271037, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

code-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 8d 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/code-review/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review

Overview

Catch issues before they cascade. Every change gets reviewed systematically before it ships.

Core principle: Review early, review often. Fresh eyes find what familiar ones miss.

The Iron Law

NO MERGE WITHOUT REVIEW. NO REVIEW WITHOUT EVIDENCE.

When to Use

Mandatory:

  • Before merging to main/production branch
  • After completing a major feature
  • After completing each task in a plan
  • Before deploying

Optional but valuable:

  • When stuck (fresh perspective)
  • Before refactoring (baseline check)
  • After fixing complex bugs
  • When learning a new codebase

When NOT to Use

  • Reviewing auto-generated code (migrations, scaffolds) — verify output instead
  • Reviewing dependency lock file diffs — use dependency-audit
  • One-character typo fixes (just commit it)

Anti-Shortcut Rules

YOU CANNOT:
- Say "code looks good" — review every changed file, every function
- Say "logic is correct" — trace execution with edge case inputs (null, empty, max, negative)
- Say "tests are sufficient" — verify error paths are tested, not just happy paths
- Say "security is fine" — check for injection, auth bypass, data exposure explicitly
- Say "performance is acceptable" — check for N+1 queries, unbounded loops, missing pagination
- Skip unchanged files in the diff — context matters (does the change break callers?)
- Rubber-stamp small PRs — small bugs in small PRs cause large outages
- Review only the code, not the tests — tests ARE deliverables

Common Rationalizations (Don't Accept These)

Rationalization Reality
"It's just a small change" Small changes cause most production incidents. Review it.
"The tests pass" Tests can't catch what they don't test. Check coverage.
"I trust this developer" Trust is not a review strategy. Evidence is.
"We're in a hurry" Shipping a bug is slower than reviewing code.
"It's the same pattern as before" Same pattern ≠ correct pattern. Maybe the pattern is wrong.
"LGTM" Not a review. Name one thing you verified.

Read the full file on GitHub · 224 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. 8d ago First seen · 224 lines · 36 tokens per session scan A abd3fc271037

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 1,705 once invoked, about $0.0002 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 2026-09-03.