A development command that coordinates the implementation of one feature across architecture, database setup, server code, API checks, and user-interface code. An API is the interface through which software components exchange data.

Use it to implement all user stories in a feature, including server endpoints and interface work, while running the API gate between them.

It keeps dependent development stages in order and runs suitable independent user stories together. This reduces the need to invoke each development stage manually.

dev-run — Command 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 commands/zekiriabd/sdd-pro/dev-run

Clone the repo

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

Made for: Claude Code.

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 11,488 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	$0.00027	$0.11488
Opus 5	$0.00014	$0.05744
Sonnet 5	$0.00005	$0.02298
Haiku 4.5	$0.00003	$0.01149

Measured 2d ago against content hash 67996bb021e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-run 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-run.md · 920 lines

How it starts

The opening of the file, as written. The whole thing — 920 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dev-run — Orchestrateur dev (arch+db → back → API gate → front) pour 1 FEAT

Commande user-facing (cf. CLAUDE.md §3 — 13 user-facing). Phase 4 : orchestre arch+DB → dev-backend ALL US → QA API Gate → dev-frontend ALL US. Invoquée aussi par /sdd-full STEP 4. Pour un pipeline complet A→Z, préférer /sdd-full qui gère également Phase 2 (US) et Phase 5 (QA + reviews).

Dépendance load-bearing au runtime Claude Code : orchestration parallèle via tool Agent (alias Task) avec N calls indépendants dans un même message. Contrat externe garanti par Claude Code. Anti-régression : framework_smoke.py vérifie la présence de « parallèle » + Agent + dev-backend + dev-frontend.

Pour la FEAT {n}, en séquence (workflow gated séquentiel depuis v7.0.0, default GatedWorkflow: true — cf. STEP 6 et .sdd/rules/build-and-loop.md Partie A) :

Pré-step arch (idempotent) — bootstrap solution/projets selon stacks actifs + scaffolding DB Database-First si DatabaseType ≠ none (les deux phases sont gérées par le même agent arch)
dev-backend sur TOUTES les US (parallélisme intra-back borné par MaxParallel, default 3 US simultanées)
QA API Gate (tests d'intégration HTTP in-memory) — STOP si status=FAIL|INFRA_BLOCKED, continue sur PASS|WARN|SKIPPED
dev-frontend sur TOUTES les US (parallélisme intra-front borné par MaxParallel) ; chaque agent décide s'il a du travail (frontend pure / backend pure) ou exit silencieux

Anti-régression : framework_smoke.py valide la présence de Agent + parallèle + dev-backend + dev-frontend dans ce fichier (le parallélisme intra-phase reste un contrat load-bearing du runtime Claude Code). Le sequencing inter-phase back→gate→front est la nouveauté v7.0.0 vs v6.x parallèle. Legacy v6 disponible via GatedWorkflow: false (audit-log legacy-parallel.log).

Mode autonome : pas de Q/R utilisateur.

Usage : /dev-run {n} ({n} = numéro FEAT).

Hors scope : /us-generate doit avoir tourné avant. Consomme workspace/us/ (US) et workspace/ui/ (mockups HTML optionnels).

Read the full file on GitHub · 920 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 · 920 lines · 27 tokens per session scan A 67996bb021e5

Subscribe to this mod's changes

dev-run is a command published in the GitHub repository zekiriabd/SDD-Pro (187 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 11,488 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.

dev-run

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/dev-run — Orchestrateur dev (arch+db → back → API gate → front) pour 1 FEAT

What this file has done since we first saw it

Other commands, from other repositories

git

checklist

clarify

specify

analyze

constitution