SDD-Pro: Command for Claude Code

.claude/commands/sdd-review.md

sdd-review is a command for Claude Code from zekiriabd/SDD-Pro. It costs 20 tokens per session (5,850 once invoked), scanned A, original, Apache-2.0.

A read-only quality command that combines existing code, security, accessibility, performance, and specification checks for one feature. It produces a consolidated pass, warning, or failure result.

In plain words
What is it for?
Use it to audit a feature, rerun quality scans, or inspect stored scan results. It can also include an architecture review in the audit process.
Why use it?
It gives a team one view of problems found by several separate checks. This makes it easier to see which team should handle each finding before release.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex.

This is zekiriabd/SDD-Pro's own configuration. It tells Claude Code how to work on SDD-Pro itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything SDD-Pro configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python .sdd/python/sdd_scripts/triage_quality.py --feat-number {n} --fail-on {ReviewFailOn} --threshold 5.

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/commands/sdd-review.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.

agentmods badge for sdd-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/sdd-review.svg)](https://agentmods.dev/commands/zekiriabd/sdd-pro/sdd-review)
Your own site
<a href="https://agentmods.dev/commands/zekiriabd/sdd-pro/sdd-review"><img src="https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/sdd-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,850 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.05850
Opus 5 $0.00010 $0.02925
Sonnet 5 $0.00004 $0.01170
Haiku 4.5 $0.00002 $0.00585

Measured 4d ago against content hash bc28708b6e9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sdd-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 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.

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/sdd-review.md · 464 lines

How it starts

The opening of the file, as written. The whole thing — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdd-review — Audit qualité consolidé par FEAT (style Sonar)

Phase A — rapport seul, 0 auto-fix. Re-run du scan déterministe quality_scan.py, agrégation des findings de tous les auditeurs déjà persistés dans console.db (qa_quality, qa_code_review, qa_security, qa_a11y, qa_performance, qa_spec_compliance), triage déterministe par owner (backend / frontend / shared / unknown) basé sur le path, calcul du verdict 🟢/🟡/🔴 contre ReviewFailOn, persistance dans validation_reports(report_type='review'). Rendu Markdown à la demande (aucun fichier, 2026-07-06) : query_console_db.py review --feat {n} --format md.

Phase B (à venir v7.2) : auto-fix loop (dispatcher dispatch_fixes.py écrit, non encore wired à une commande user-facing).

Phase C (✅ déjà câblée v7.0.0) : agent arch-reviewer (Pattern + Layers

  • ADRs) auto-invoqué par /dev-run STEP 6.4 (auditor batch) et /sdd-review STEP 3.0. Cf. agents/arch-reviewer.md.

Usage

/sdd-review {n}                       # audit FEAT {n}, verdict + report
/sdd-review {n} --skip-scans          # lecture DB seule (sans re-scan)
/sdd-review {n} --ensure-scans        # v7.0.0 : exit 3 si une source QA obligatoire manque
/sdd-review {n} --fail-on critical    # override seuil (info|minor|moderate|serious|critical)
/sdd-review {n} --json                # sortie JSON pour CI/tooling
/sdd-review {n} --no-adversarial      # v7.1 : skip adversarial-reviewer (actif par défaut)
/sdd-review {n} --no-spec-gate        # v7.0.0+ : skip Stage A spec-compliance gate (legacy comportement parallèle)

--ensure-scans (v7.0.0, codex audit follow-up) : exige que toutes les sources auditeur obligatoires soient présentes dans console.db avant de produire le verdict consolidé. Évite le faux 🟢 GREEN quand un agent auditor a simplement été oublié pour cette FEAT.

Read the full file on GitHub · 464 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 · 464 lines · 20 tokens per session scan A bc28708b6e9f

Subscribe to this mod's changes

sdd-review is a command published in the GitHub repository zekiriabd/SDD-Pro (191 stars, last pushed 4d ago), licensed Apache-2.0. It adds 20 tokens to every session and 5,850 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 2026-09-03.