review

A command that reviews the code changes in a Git diff against the project's design, specification, and validation report.

In plain words
What is it for?
Use it for Java, Kotlin, Spring, SQL, Maven, and Angular changes, producing a Markdown code-review report.
Why use it?
It groups review findings before a commit, helping catch problems that automated tests may not identify.

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/loiane/specs-driven-development-spring-angular/review
Clone the repo
git clone --depth 1 https://github.com/loiane/specs-driven-development-spring-angular

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 601 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 $0.00018 $0.00601
Opus 5 $0.00009 $0.00300
Sonnet 5 $0.00004 $0.00120
Haiku 4.5 $0.00002 $0.00060

Measured 2d ago against content hash 0bcbb8ef5437, 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.

.claude/commands/review.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/review

Phase: 6 — pre-commit code review Owning agent: .claude/agents/spring-code-reviewer.md Skills used: spring-code-review-rubric, clarity-over-cleverness, spring-boot-4-conventions, spring-security-baseline, performance-optimization

Stack routing

Changed files in diff Agent
Java/Kotlin/POM/SQL only spring-code-reviewer (this agent)
Angular (.ts, .html, .scss) only angular-code-reviewer
Both Run both reviewers; merge findings into a single 08-code-review.md

Inspect the diff file list (git diff --name-only <base>...HEAD). If it contains only frontend files, delegate entirely to angular-code-reviewer.

Purpose

Run a structured self-review of the diff before the user commits. Produces 08-code-review.md with categorized findings.

Inputs

  • <feature-id> (optional). Defaults to the most recent feature.
  • Optional --base <ref> (defaults to origin/main).

Reads

  • git diff <base>...HEAD for changed Java/test/POM/SQL files.
  • 01-spec.md, 03-design.md, 07-validation-report.md.
  • .claude/skills/spring-code-review-rubric/SKILL.md (the rubric is authoritative).

Writes

  • .specs/<feature-id>/08-code-review.md.

Process

  1. Refuse if 07-validation-report.md verdict is not PASS.
  2. Walk every changed file. For each, evaluate against the rubric categories: correctness, security, design, testing, observability, performance, clarity, conventions.
  3. Classify findings as must-fix, should-fix, nit, or praise. Include file + line range + suggested change for must-fix and should-fix.
  4. Cross-check: every AC mentioned in 01-spec.md is exercised by at least one test in the diff (or already merged).
  5. If any must-fix exists, recommend /build or /code-simplify. Do NOT auto-apply fixes.
  6. Emit summary line: counts by severity + recommended next action.

Refuse if

  • Validation report is missing or FAIL.
  • The diff is empty.

Done when

08-code-review.md exists. If zero must-fix, the agent prints the suggested commit message and tells the user to run git commit themselves (the agent never commits).

Read the full file on GitHub · 51 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 · 51 lines · 18 tokens per session scan A 0bcbb8ef5437

Subscribe to this mod's changes

review is a command published in the GitHub repository loiane/specs-driven-development-spring-angular (58 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 601 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.