dev-backend

A command that turns one user story—a written description of a user need—into server-side code. It can produce items such as services, API endpoints, data objects, database entities, and request-processing setup.

In plain words
What is it for?
Use it to implement the server portion of a specific user story, identified by its feature and story numbers, or let the feature orchestrator process multiple stories.
Why use it?
It gives a focused way to implement one backend requirement and checks the result with a backend build. User-interface-only stories are skipped.

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/zekiriabd/sdd-pro/dev-backend
Clone the repo
git clone --depth 1 https://github.com/zekiriabd/SDD-Pro

Made for: Claude Code.

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 704 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 $0.00017 $0.00704
Opus 5 $0.00009 $0.00352
Sonnet 5 $0.00003 $0.00141
Haiku 4.5 $0.00002 $0.00070

Measured 2d ago against content hash 5125610284db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-backend 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/dev-backend.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dev-backend — Génère le code serveur d'UNE US

⚠️ Commande interne v7.0.0 — invoquée par /dev-run STEP 6.a (batch 1 US). Utilisateur final : préférer /sdd-full ou /dev-run (gèrent pré-conditions, idempotence, état).

Invoque l'agent dev-backend pour matérialiser l'US workspace/us/{n}-{m}-{Name}.md en code serveur (services, endpoints, DTOs, entities, mappers, Program.cs, middleware). L'agent planifie inline les fichiers à produire à partir de l'US + du stack actif.

Si l'US n'a aucune contrepartie backend (US frontend pure), l'agent exit silencieusement avec une ligne skipped (frontend-only US).

1 invocation = 1 US = 1 build backend. Pour traiter plusieurs US, lancer la commande plusieurs fois ou utiliser /dev-run {n}.

Usage : /dev-backend {n}-{m} — où {n}-{m} cible une US existante (ex. /dev-backend 1-3).


STEP 1 — Valider l'argument

Argument obligatoire : {n}-{m} (deux entiers ≥ 1 séparés par un tiret).

Si absent → demander :

Quelle est l'US à matérialiser côté backend ? (format : {n}-{m}, ex. 1-3)

Si format invalide →

ERROR: /dev-backend — argument invalide
CAUSE: [INVALID_ARG] "{argument}" ne respecte pas le format {n}-{m}
FIX: relancer /dev-backend {n}-{m} (ex. /dev-backend 1-3)

STEP 2 — Invoquer l'agent dev-backend

Lancer l'agent dev-backend (défini dans .claude/agents/dev-backend.md) avec l'argument {n}-{m}. L'agent gère :

  • la lecture sélective de l'US, du mockup HTML éventuel (passif), du stack actif
  • le plan inline des fichiers serveur (ou exit silencieux si US frontend-only)
  • la génération de code conforme au mapping du stack
  • le build loop (max 3 itérations)
  • la confirmation 1 ligne

Attendre la fin de l'agent. Relayer sa sortie telle quelle.


STEP 3 — Confirmation finale

Si l'agent réussit avec génération, ajouter UNE SEULE ligne :

Prochaine étape : si l'US a une partie frontend, lancer /dev-frontend {n}-{m}.

Si l'agent réussit en skipped ou échoue, ne rien ajouter.

Read the full file on GitHub · 78 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 · 78 lines · 17 tokens per session scan A 5125610284db

Subscribe to this mod's changes

dev-backend is a command published in the GitHub repository zekiriabd/SDD-Pro (187 stars, last pushed today), licensed Apache-2.0. It adds 17 tokens to every session and 704 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.