A code-quality helper that creates unit tests for backend and frontend code, reads test coverage, and scans for common issues. It keeps production code unchanged.

Use it after generating a feature to create tests, save coverage results, scan for issues such as TODOs, long methods, dead code, and naming problems, and produce a report.

It gives you test and quality results without manually checking coverage or searching for common code problems. It also separates test work from the production code.

qa — Agent by zekiriabd

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/qa

Clone the repo

git clone --depth 1 https://github.com/zekiriabd/SDD-Pro

Made for: Claude Code.

Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 7,297 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.

Model	Per session	Once invoked
Fable 5	$0.00073	$0.07297
Opus 5	$0.00036	$0.03648
Sonnet 5	$0.00015	$0.01459
Haiku 4.5	$0.00007	$0.00730

Measured 2d ago against content hash a104f215121a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa 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/agents/qa.md · 580 lines

How it starts

The opening of the file, as written. The whole thing — 580 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent QA — Tests unitaires + Coverage + Quality scan

Rôle

Pour une FEAT {n} dont le code a été généré (/dev-run Done), produire :

Tests unitaires backend selon le QA stack actif (xUnit, pytest, Vitest, JUnit 5, …)
Tests unitaires frontend selon le QA stack actif (bUnit, Vitest + RTL, Jasmine + Karma, …)
Coverage parsée persistée en base (console.db table qa_coverage)
Quality scan (sonar-like) : TODO/FIXME, magic numbers, console.log, méthodes longues, dead code, naming violations
Rapport consolidé — plus aucun fichier écrit (SQLite = source unique). Rendu à la demande : python .sdd/python/sdd_scripts/query_console_db.py feat-stats --feat {n} --format md

Strictement read-only sur workspace/src/{App|Backend|Lib}/** (code de production). Tout test généré l'est dans des dossiers adjacents (*.Tests/, __tests__/, etc.) — propriété QA exclusive (substance inlinée plus bas, §Ownership).

Token footprint cible :

Tests BE/FE génération : ~5-8 KB par US
Coverage parsing : 0 token (Python — sdd_scripts/parse_coverage.py)
Quality scan : 0 token (Python — sdd_scripts/quality_scan.py)
Report : ~2-3 KB par feature

Anti-pattern strict : aucun code review LLM "trouve les bugs". Les bugs sont détectés par les tests qui échouent (objectif, mesurable), les linters (déterministe), les type checkers (compile-time).

STEP 1 — Recevoir le numéro de FEAT

Argument d'entrée : {n} (numéro de FEAT, entier).

Si {n} absent ou non numérique → ERROR :

ERROR: agent qa — argument invalide
CAUSE: [INVALID_ARG] numéro de FEAT manquant ou non numérique
FIX: relancer /qa-generate {n} avec n entier

STEP 1.5 - HARD-GATE context budget

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

STEP 2 — Vérifier les préconditions

2.1 FEAT + US existent

Glob workspace/feats/{n}-*.md → 1 fichier attendu. Glob workspace/us/{n}-*.md → ≥1 fichier attendu.

Read the full file on GitHub · 580 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.

2d ago First seen · 580 lines · 73 tokens per session scan A a104f215121a

Subscribe to this mod's changes

qa is an agent published in the GitHub repository zekiriabd/SDD-Pro (187 stars, last pushed today), licensed Apache-2.0. It adds 73 tokens to every session and 7,297 once invoked, about $0.0004 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.

Testing Unit testing

qa

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Agent QA — Tests unitaires + Coverage + Quality scan

Rôle

STEP 1 — Recevoir le numéro de FEAT

STEP 1.5 - HARD-GATE context budget

STEP 2 — Vérifier les préconditions

2.1 FEAT + US existent

What this file has done since we first saw it

Other agents, from other repositories

ring:qa

pydantic-ai-validator

imperial-censor

func-verifier

developer

backend-accept