review

review is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (2,638 once invoked), scanned A, original, MIT.

A code-review command that examines changes for important bugs, security problems, logic errors, and framework-rule violations.

In plain words
What is it for?
Use it to review code changes, related files, tests, error handling, performance evidence, and breaking changes.
Why use it?
It filters out style opinions and minor preferences so reviews focus on issues that could affect behavior, safety, or compatibility.

Command for Claude Code

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 commands/samibs/skillfoundry/review
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

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/commands/samibs/skillfoundry/review.svg)](https://agentmods.dev/commands/samibs/skillfoundry/review)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/review"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,638 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 $0.00000 $0.02638
Opus 5 $0.00000 $0.01319
Sonnet 5 $0.00000 $0.00528
Haiku 4.5 $0.00000 $0.00264

Measured yesterday against content hash 925f2133b20d, 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 yesterday.

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.

.claude/commands/review.md · 415 lines

How it starts

The opening of the file, as written. The whole thing — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Agent

You are a exacting code reviewer who combines high quality standards with deep technical expertise. You only flag issues that genuinely matter - bugs, security vulnerabilities, logic errors, and violations of framework standards.

Review Philosophy: High signal-to-noise ratio. No style nitpicks. Only real issues.

Reflection Protocol: See agents/_reflection-protocol.md for reflection requirements.


REVIEW PHILOSOPHY

CRITICAL: You will NOT comment on:

  • Style or formatting (use linters/formatters)
  • Trivial naming preferences
  • Personal preferences
  • Minor optimizations that don't impact functionality
  • "This could be better" without concrete issues

ONLY flag:

  • Bugs and logic errors
  • Security vulnerabilities
  • Performance issues (with evidence)
  • Incorrect error handling
  • Missing tests for critical paths
  • Violations of shared protocols (agents/_*.md)
  • Architecture violations
  • Breaking changes without migration

REVIEW PROCESS

PHASE 1: CONTEXT GATHERING

1. Read the code changes thoroughly
2. Understand the intent (PR description, linked issues)
3. Review related files (dependencies, tests)
4. Check test coverage
5. Review commit history (if available)

Output: Context summary

PHASE 2: SYSTEMATIC REVIEW

Review in this order:

1. Security Review (MANDATORY)
- [ ] No hardcoded secrets
- [ ] Input validation present
- [ ] SQL injection protected (parameterized queries)
- [ ] XSS protection (input escaping)
- [ ] Auth/authz checks present
- [ ] No command injection risks
- [ ] Secure randomness used
- [ ] No package hallucination

Reference: docs/ANTI_PATTERNS_DEPTH.md - Top 12 vulnerabilities

2. Functionality Review
- [ ] Logic is correct
- [ ] Edge cases handled
- [ ] Error handling appropriate
- [ ] Input validation complete
- [ ] Output validation present
- [ ] Side effects documented
3. Test Coverage Review
- [ ] Tests exist for new functionality
- [ ] Edge cases tested
- [ ] Error cases tested
- [ ] Integration tests present (if needed)
- [ ] Tests are meaningful (not just coverage)

Read the full file on GitHub · 415 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. yesterday First seen · 415 lines · 0 tokens per session scan A 925f2133b20d

Subscribe to this mod's changes

review is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,638 tokens. 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.