review

A command for reviewing code changes through several checks, including general code quality and security.

In plain words
What is it for?
It is for reviewing all staged or unstaged changes, or the latest commit when the working tree is clean, and producing a list of findings and fixes.
Why use it?
It helps find logic errors, missing error handling, performance problems, and security issues before changes are merged.

Command

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/zevtos/agentpipe/review
Clone the repo
git clone --depth 1 https://github.com/zevtos/agentpipe
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 733 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 $0.00024 $0.00733
Opus 5 $0.00012 $0.00367
Sonnet 5 $0.00005 $0.00147
Haiku 4.5 $0.00002 $0.00073

Measured 2d ago against content hash 5f22eb607d2e, 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 2d 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.

commands/review.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are orchestrating a comprehensive code review using multiple specialist agents in parallel. This is the quality gate before merging.

Context

@CLAUDE.md

What to Review

$ARGUMENTS

Auto-context

  • Status: !git status --short
  • Changed files: !git diff --name-only HEAD~1 2>/dev/null || git diff --name-only --staged 2>/dev/null || git diff --name-only
  • Diff stats: !git diff --stat HEAD~1 2>/dev/null || git diff --stat --staged 2>/dev/null || git diff --stat

Pipeline

Step 1: Determine Scope

If $ARGUMENTS specifies files or areas, review only those. Otherwise, review ALL staged and unstaged changes (or the last commit if working tree is clean).

Read ALL changed files in full — not just the diff. Context matters.

Step 2: Parallel Review (Reviewer + Security Agents)

Run BOTH agents simultaneously:

Reviewer agent: "Review all code changes in this repository. Changed files: [list from auto-context]

Perform a thorough review covering:

  • Correctness: logic errors, edge cases, off-by-one, null handling
  • Error handling: are all failure modes addressed? resources cleaned up?
  • Performance: N+1 queries, unbounded operations, missing indexes, memory leaks
  • API contracts: input validation, output format, status codes, idempotency
  • Conventions: consistent with project patterns and CLAUDE.md rules
  • Tests: are changes tested? are assertions meaningful?

For each finding, specify: file:line, severity, description, and specific fix."

Security agent: "Security review of all code changes in this repository. Changed files: [list from auto-context]

Check for:

  • Injection vulnerabilities (SQL, command, XSS, template)
  • Authentication/authorization gaps (missing checks, broken access control)
  • Sensitive data exposure (logs, error messages, API responses)
  • Cryptographic issues (weak algorithms, hardcoded keys, nonce reuse)
  • Input validation gaps (missing validation, improper sanitization)
  • Dependency risks (known CVEs, supply chain concerns)
  • Security headers and CORS configuration
  • Rate limiting on sensitive endpoints

Read the full file on GitHub · 94 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. 2d ago First seen · 94 lines · 24 tokens per session scan A 5f22eb607d2e

Subscribe to this mod's changes

review is a command published in the GitHub repository zevtos/agentpipe (11 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 733 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.