review

review is a command for Claude Code from hautc-it/cil. It costs 25 tokens per session (332 once invoked), scanned A, original, MIT.

A command for reviewing the current Git changes, including both staged and unstaged edits. It checks each changed file for correctness, regressions, security, performance, error handling, tests, and style.

In plain words
What is it for?
Use `/review` to inspect the current working diff and receive a severity-ranked list of findings with file and line references. If no problems are found, it reports that the changes are ready to commit.
Why use it?
It gives developers a consistent final check before committing code and highlights issues that could break existing behavior or create security or maintenance problems.

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/hautc-it/cil/review
Clone the repo
git clone --depth 1 https://github.com/hautc-it/cil

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/hautc-it/cil/review.svg)](https://agentmods.dev/commands/hautc-it/cil/review)
Your own site
<a href="https://agentmods.dev/commands/hautc-it/cil/review"><img src="https://agentmods.dev/badge/commands/hautc-it/cil/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 332 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 $0.00025 $0.00332
Opus 5 $0.00013 $0.00166
Sonnet 5 $0.00005 $0.00066
Haiku 4.5 $0.00003 $0.00033

Measured 3d ago against content hash dd77ac5525d4, 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.

.claude/commands/review.md · 64 lines

What it actually says

/review

Review current changes for correctness, regressions, and quality.


Step 1 — Get the diff

git diff HEAD
# or for staged:
git diff --staged

If no git context, ask which files to review.


Step 2 — Per-file checklist

For each changed file:

Correctness

  • Does it do what it claims?
  • Are edge cases handled (null, empty, boundary)?
  • Is error handling appropriate?

Regressions

  • Does it preserve existing behavior?
  • Are tests updated to reflect changes?
  • Any implicit contracts broken?

Security

  • Unvalidated user input entering SQL/shell/eval?
  • Secrets or credentials exposed?
  • Auth/authz checks missing?

Performance

  • N+1 queries? Blocking calls in hot paths?
  • Unbounded loops or allocations?

Style

  • Consistent with surrounding code?
  • Names clear and accurate?
  • No unnecessary comments or dead code?

Step 3 — Report

If issues found: numbered list with severity.

  • Critical: must fix before merge
  • Major: should fix, blocks ship
  • Minor: suggestion, non-blocking

If clean: "Review passed. Ready to commit."

Store review outcome: memory_store("learning", "[what was caught in review]", ["review"])

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 · 64 lines · 25 tokens per session scan A dd77ac5525d4

Subscribe to this mod's changes

review is a command published in the GitHub repository hautc-it/cil (1 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 332 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 2026-08-31.