feat-generate

feat-generate is a command for Claude Code from zekiriabd/SDD-Pro. It costs 19 tokens per session (3,310 once invoked), scanned A, original, Apache-2.0.

A guided command that creates a functional feature specification after asking the product owner a few short sets of questions. It saves the result as a numbered Markdown file.

In plain words
What is it for?
Use it to gather requirements and create a new feature document in an initialized project.
Why use it?
It gives the team a consistent starting point for describing a feature and prevents specifications from being created before the project is initialized.

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/feat-generate
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 feat-generate

README.md
[![agentmods](https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/feat-generate.svg)](https://agentmods.dev/commands/zekiriabd/sdd-pro/feat-generate)
Your own site
<a href="https://agentmods.dev/commands/zekiriabd/sdd-pro/feat-generate"><img src="https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/feat-generate.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,310 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 $0.00019 $0.03310
Opus 5 $0.00010 $0.01655
Sonnet 5 $0.00004 $0.00662
Haiku 4.5 $0.00002 $0.00331

Measured 5d ago against content hash 0384dfc9e148, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feat-generate 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 5d 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/feat-generate.md · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/feat-generate — Création guidée d'une FEAT fonctionnelle

Crée un fichier workspace/feats/{n}-{Name}.md pré-rempli en interrogeant le PO via 2 séries de questions courtes. Le numéro {n} est auto-détecté.

Usage : /feat-generate ou /feat-generate {Nom}


STEP 0 — Preflight projet initialisé (greenfield gate)

Avant toute interaction avec l'utilisateur, vérifier que le projet est bootstrappé. Évite que /feat-generate produise une FEAT orpheline (sans stack.md aval cassé sur /sdd-full).

  1. Test existence : workspace/stack/stack.md existe et fait ≥ 100 octets.
  2. Test template rendu : Read le fichier, vérifier qu'il ne contient pas de placeholder {{Placeholder}} (regex \{\{[A-Za-z][A-Za-z0-9_]*\}\}).

Si l'un des tests échoue → STOP avec message actionnable (pas d'ERROR technique, c'est un onboarding utilisateur) :

🟡 [FEAT-GENERATE] Projet non initialise — bootstrap requis.

workspace/stack/stack.md {absent | contient des placeholders non substitues}.

Avant de creer une FEAT, lance depuis un terminal :
    python bootstrap.py

(interactif, ~5 questions, ~30s — choisit le combo stack, AppName, DB, auth)

Apres bootstrap, relance : /feat-generate {Nom}
Details et options : /sdd-bootstrap

Cette commande ne lance jamais bootstrap.py (interactif, requiert le terminal utilisateur — pas du sub-agent Claude).


STEP 0.5 — Phase 0 Discovery hint (v7.0.0+, opt-in)

Conditionnel : si Glob workspace/feats/*.md retourne ≥ 2 FEATs (le 3ᵉ+ FEAT projet, signal de "projet qui grossit"), ET aucun fichier product-brief.md ni prfaq.md dans workspace/discovery/, émettre avant les questions de cadrage :

💡 [FEAT-GENERATE] Astuce Phase 0 Discovery (facultative, projets > 3 FEATs)

Vous avez déjà N FEATs. Pour les projets qui grossissent, un brief
Discovery aide à cadrer la vision avant de continuer à empiler les FEATs :
  - `.sdd/templates/product-brief.template.md` (10 sections : vision, personas, KPIs, hypothèses, risques)
  - `.sdd/templates/prfaq.template.md` (Amazon "Working Backwards" — PR fictive + FAQ interne)

Bénéfice : éviter le scope creep en FEATs parasites. Une FEAT proposée
qui ne sert pas une promesse du brief = probablement à challenger.

Continuer avec /feat-generate quand même ? (oui / non / voir templates)
  - "oui" / Enter        → continuer cadrage FEAT [DEFAULT]
  - "non"                → STOP, copier les templates d'abord dans workspace/discovery/
  - "voir templates"     → afficher 5 lignes d'extrait pour chaque template puis re-demander

Read the full file on GitHub · 316 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. 5d ago First seen · 316 lines · 19 tokens per session scan A 0384dfc9e148

Subscribe to this mod's changes

feat-generate is a command published in the GitHub repository zekiriabd/SDD-Pro (191 stars, last pushed 2d ago), licensed Apache-2.0. It adds 19 tokens to every session and 3,310 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.