review

An on-demand code review command that checks either your current changes or a whole feature directory. It can use one reviewer or several reviewers whose votes are combined.

In plain words
What is it for?
Use it to review unstaged or staged changes, check a complete feature, or get multiple opinions on an important decision before merging.
Why use it?
It helps catch problems before changes are merged, without modifying your code. Reviewing only changed files gives a quick check, while reviewing the full feature gives broader coverage.

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/marcusgoll/spec-flow/review
Clone the repo
git clone --depth 1 https://github.com/marcusgoll/Spec-Flow

Made for: Claude Code.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,290 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 $0.00014 $0.02290
Opus 5 $0.00007 $0.01145
Sonnet 5 $0.00003 $0.00458
Haiku 4.5 $0.00001 $0.00229

Measured 3d ago against content hash f56b466feb82, 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/quality/review.md · 334 lines

How it starts

The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/review — On-Demand Code Review

Current Branch: !git branch --show-current 2>/dev/null || echo "none"

Uncommitted Changes: !git diff --name-only HEAD 2>/dev/null | head -10

Staged Changes: !git diff --cached --name-only 2>/dev/null | head -10

Active Feature: @specs/*/state.yaml (find most recent by mtime)

Voting Config: @.spec-flow/config/voting.yaml

Review Modes:

Mode Flag Speed Use Case
Single-agent --single (default) ~2 min Quick sanity check
Multi-agent voting --voting ~6 min Critical decisions, pre-merge

Scope Options:

Scope Flag What's Reviewed
Changes --scope changes (default) Uncommitted + staged changes
All --scope all Entire feature directory

Risk Level: LOW — Read-only analysis, no code modifications

Step 1: Parse Arguments

Extract flags from $ARGUMENTS:

Flag Variable Default
--voting USE_VOTING false
--single USE_VOTING false
--scope changes SCOPE "changes"
--scope all SCOPE "changes"

Step 2: Detect Review Scope

If SCOPE = "changes":

  1. Get list of changed files:

    git diff --name-only HEAD
    git diff --cached --name-only
    
  2. If no changes found:

    • Inform user: "No uncommitted changes detected"
    • Ask: Switch to --scope all or exit?
  3. Display changed files (max 15, then "and N more...")

If SCOPE = "all":

  1. Detect active feature directory from:

    • Current branch name matching specs/*/ pattern
    • Most recent specs/*/state.yaml by modification time
    • Fall back to current working directory
  2. Display: "Reviewing entire feature: {feature_dir}"

Step 3: Gather Review Context

Do NOT create temp files. Gather context in memory:

Read the full file on GitHub · 334 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. 3d ago First seen · 334 lines · 14 tokens per session scan A f56b466feb82

Subscribe to this mod's changes

review is a command published in the GitHub repository marcusgoll/Spec-Flow (91 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 2,290 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.