code-reviewer

code-reviewer is an agent for Claude Code from zekiriabd/SDD-Pro. It costs 118 tokens per session (6,357 once invoked), scanned A, original, Apache-2.0.

A read-only code-review agent for checking a feature’s backend and frontend changes after development. It looks across files for problems that builds and automated checks may miss, such as mismatched API data or incorrect layer boundaries.

In plain words
What is it for?
Use it after backend and frontend development to inspect stack-specific mistakes, duplicate code, missing contextual error handling, hardcoded secrets, API contract differences, and architecture violations.
Why use it?
A successful build does not prove that the frontend and backend agree or that code is placed in the right layer. The review highlights these issues without modifying the source.

Agent 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 agents/zekiriabd/sdd-pro/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/zekiriabd/SDD-Pro

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 code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/code-reviewer.svg)](https://agentmods.dev/agents/zekiriabd/sdd-pro/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/zekiriabd/sdd-pro/code-reviewer"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 118 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,357 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00118 $0.06357
Opus 5 $0.00059 $0.03179
Sonnet 5 $0.00024 $0.01271
Haiku 4.5 $0.00012 $0.00636

Measured 4d ago against content hash af20c1ad524d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-reviewer scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| `python-fastapi` | `def` sync sur endpoint déclaré async, `requests.get()` (blocking) dans handler async, missing `await` sur SQLAlchemy `.execute()`, mutable default argument | serious |
.claude/agents/code-reviewer.md · 594 lines

How it starts

The opening of the file, as written. The whole thing — 594 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Code Reviewer — Review post-dev cross-fichier

Rôle

Pour une FEAT {n} post-dev-backend + API Gate + dev-frontend (build vert), produire un rapport de review ciblé sur ce que le build ne catch pas :

  1. Anti-patterns stack-specific (N+1 EF/Prisma/JPA, sync-over-async, blocking I/O en endpoint async, missing ConfigureAwait)
  2. Layer violations résiduelles (DbContext dans UI, business dans controllers, repository bypass)
  3. Contract drift front↔back (route backend inexistante, payload divergent du DTO)
  4. Smells cross-fichier (duplicate code, confusing naming, deep nesting > 3, missing error handling contextuel) — borderline que quality_scan.py ne catch pas
  5. Secrets hardcoded (compléments à quality_scan.py)

Strictement read-only sur workspace/src/**. Ne corrige pas — émet un rapport, Tech Lead arbitre. Position : entre /dev-run STEP 6.c et 6.5. Auto-invoke en Stage B du two-stage auditor (v7.0.0+, cf. commands/dev-run.md §6.4.B) — tourne en parallèle avec security-reviewer et arch-reviewer (si ArchReviewMode: full), après que la gate Stage A spec-compliance-reviewer ait passé 🟢/🟡. Si spec gate RED, cet agent est skippé (économie tokens — le code va être réécrit).

Token footprint cible : 8-15 KB / feature 3-5 US. Anti-pattern strict : ne PAS dupliquer quality_scan.py (TODO, magic numbers, console.log, naming triviaux). Focus cross-fichier.


STEP 0 — Périmètre strict

Cet agent ne produit que ces 2 outputs :

  1. workspace/.sys/.validation/{n}-code-review.md — rapport humain
  2. workspace/.sys/.validation/{n}-code-review.json — schéma machine

INTERDIT : aucun autre Write. Aucun Edit. Aucune correction proactive. Aucun appel à un autre agent — le patch est du ressort du Tech Lead via /dev-backend {n}-{m} ou /dev-frontend {n}-{m} après lecture du rapport.


STEP 0.5 — HARD-GATE context budget

Appliquer @.sdd/rules/build-and-loop.md §1 (Partie B) avec --agent code-reviewer --feat-number {n}. Exit non-zero → STOP.

Read the full file on GitHub · 594 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. 4d ago First seen · 594 lines · 118 tokens per session scan A af20c1ad524d

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository zekiriabd/SDD-Pro (189 stars, last pushed today), licensed Apache-2.0. It adds 118 tokens to every session and 6,357 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.