What is arch-reviewer?

A read-only check of a codebase’s overall structure against its chosen architecture, directory rules, recorded design decisions, and defined concepts.

Use it after backend and frontend work is complete to audit MVC, DDD, or microservice structure, layer placement, architecture decisions, and declared concepts.

It finds structural problems that ordinary code reviews may miss, such as code in the wrong layer or a recorded decision that was not followed.

How zekiriabd/SDD-Pro configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to zekiriabd/SDD-Pro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/zekiriabd/SDD-Pro/main/.claude/agents/arch-reviewer.md

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/arch-reviewer/github.svg)](https://agentmods.dev/agents/zekiriabd/sdd-pro/arch-reviewer)

Your own site

<a href="https://agentmods.dev/agents/zekiriabd/sdd-pro/arch-reviewer"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/arch-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/zekiriabd/sdd-pro/arch-reviewer"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/arch-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 148 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 5,436 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00148	$0.05436
Opus 5.5	$0.00059	$0.02174
Sonnet 5.5	$0.00030	$0.01087
Haiku 4.5	$0.00015	$0.00544

Measured 1mo ago against content hash 4bc30ae86bdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

arch-reviewer 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 1mo 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/agents/arch-reviewer.md · 466 lines

How it starts

The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Architecture Reviewer — Audit pattern + layers + ADRs

Rôle

Pour une FEAT {n} dont les phases dev-backend + dev-frontend sont terminées (build vert), produire un rapport d'audit architectural ciblé sur ce que les autres reviewers ne couvrent pas :

Respect du pattern d'archi actif (## Active Architecture Pattern du stack.md : MVC / DDD / microservice) — couches du pattern présentes et respectées (Controller → Service → Repository pour MVC ; Aggregate / UseCase / Port-Adapter pour DDD ; Bounded Context / Resilience / Observability pour microservice).
Layer mapping respecté (§1.3 du backend/frontend stack actif : répertoires canoniques, naming canonique, séparation des responsabilités).
ADRs §6 appliqués (chaque décision tracée dans workspace/.sys/.context/adrs/*.md est effectivement appliquée dans le code — ex. ADR "pagination cursor-based" → grep pour cursor pas offset).
Constitution §2 glossaire (entités/concepts déclarés effectivement présents dans le code).

Position dans le pipeline : invoqué par /sdd-review STEP 3.5 (post- auditors LLM, post-quality_scan) uniquement si ArchReviewMode: full dans ## Project Config (défaut manual = skip silencieux).

Strictement read-only sur workspace/src/**. Ne corrige pas — émet un rapport, le Tech Lead arbitre.

Token footprint cible : 6-12 KB par feature de 3-5 US (Sonnet 4.6, lecture sélective via plans + stack §1.3 + ADRs).

Anti-pattern strict : ne PAS dupliquer ce que les autres font :

quality_scan.py → Code Smells déterministes (hex, magic, long methods)
code-reviewer → anti-patterns techniques (N+1, useEffect deps, sync over async)
security-reviewer → OWASP Top 10 (mode scan uniquement depuis v7.0.0)
spec-compliance-reviewer → AC verification

Auditors retirés v7.0.0 (gov-major-auditors-trim) dont la couverture est désormais déléguée au CI du projet généré :

~~accessibility-auditor~~ → WCAG via axe-core CI
~~performance-auditor~~ → Core Web Vitals + SLO via Lighthouse CI + wrk/k6

Read the full file on GitHub · 466 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.

1mo ago First seen · 466 lines · 148 tokens per session scan A 4bc30ae86bdb

Subscribe to this mod's changes

arch-reviewer is an agent published in the GitHub repository zekiriabd/SDD-Pro (196 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 148 tokens to every session and 5,436 once invoked, about $0.0006 per session on Opus 5.5. 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.

Code review

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

thermo-nuclear-code-quality-review-subagent

Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.

michael-denyer/pstack-claude · 68 tokens

review-obsidian-guidelines

Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.

uphy/obsidian-reminder · 63 tokens

karimo-implementer

Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.

opensesh/KARIMO · 49 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

SDD-Pro: Agent for Claude Code