dev-plan

A planning command that turns one feature into technical work plans without writing code. It asks backend and frontend agents to list the files they expect to create or change for each user story.

In plain words
What is it for?
Use it to review a feature’s technical breakdown, edit its planned files, or compare how a change might fit a different technology stack.
Why use it?
It lets a developer inspect and adjust the proposed implementation before code generation begins. The plans can then be reused by the development command instead of being created again.

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-plan
Clone the repo
git clone --depth 1 https://github.com/zekiriabd/SDD-Pro

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,927 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 $0.00018 $0.02927
Opus 5 $0.00009 $0.01463
Sonnet 5 $0.00004 $0.00585
Haiku 4.5 $0.00002 $0.00293

Measured 2d ago against content hash 4709717c07a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-plan 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-plan.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dev-plan — Génère les plans techniques d'1 FEAT sans coder

⚠️ Commande interne v7.0.0 — invoquée par /sdd-full STEP 3.6 (conditionnel). Utilisateur final : préférer /sdd-full ou /dev-run (gèrent pré-conditions, idempotence, état).

Pour chaque US de la FEAT {n}, invoque les agents dev-backend et dev-frontend en mode Plan Only : ils lisent l'US (+ mockup HTML en lecture texte directe pour le front), planifient inline les fichiers à produire, écrivent le plan dans workspace/plans/{n}-{m}-{Name}.{back|front}.md, et s'arrêtent — aucun fichier de code généré, aucun build.

L'humain peut relire et éditer ces fichiers de plan, puis lancer /dev-run {n} qui détectera les plans et les consommera tels quels au lieu de re-planifier.

Usage : /dev-plan {n} — où {n} est le numéro de la FEAT.

Cas d'emploi :

  • Tu veux valider le découpage technique avant la génération
  • Tu veux ajuster manuellement les fichiers à produire (retirer, ajouter, renommer)
  • Tu veux tester un changement de stack et comparer ce que les agents prévoient avant d'effectivement coder

STEP 1 — Valider l'argument

Argument obligatoire : {n} (entier ≥ 1).

Si absent → demander :

Quel est le numéro de la FEAT à planifier ? (ex. : 1)

Si non numérique →

ERROR: /dev-plan — argument invalide
CAUSE: [INVALID_ARG] "{argument}" n'est pas un entier
FIX: relancer /dev-plan {n} (ex. /dev-plan 1)

STEP 2 — Lister les US à planifier

Glob workspace/us/{n}-*.md → liste US_LIST (basenames sans extension).

Si US_LIST est vide →

ERROR: /dev-plan — aucune US à planifier
CAUSE: [US_NOT_FOUND] aucun fichier workspace/us/{n}-*.md
FIX: lancer /us-generate {n} pour générer les US d'abord

Émettre 1 ligne :

FEAT {n} — {U} US à planifier (back + front en parallèle, mode Plan Only)

STEP 3 — Vérifier les stacks actifs

Lire workspace/stack/stack.md.

  • Si aucun ## Active Tech Specs backend-* ET aucun frontend-* → ERROR comme dans /dev-run.

Read the full file on GitHub · 263 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 · 263 lines · 18 tokens per session scan A 4709717c07a8

Subscribe to this mod's changes

dev-plan is a command published in the GitHub repository zekiriabd/SDD-Pro (187 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 2,927 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.