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.
npx agentmods add commands/zekiriabd/sdd-pro/feat-generategit clone --depth 1 https://github.com/zekiriabd/SDD-ProWrote 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.
[](https://agentmods.dev/commands/zekiriabd/sdd-pro/feat-generate)<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>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 | $0.00019 | $0.03310 |
| Opus 5 | $0.00010 | $0.01655 |
| Sonnet 5 | $0.00004 | $0.00662 |
| Haiku 4.5 | $0.00002 | $0.00331 |
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.
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).
- Test existence :
workspace/stack/stack.mdexiste et fait ≥ 100 octets. - 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
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.
- 5d ago First seen · 316 lines · 19 tokens per session scan A 0384dfc9e148
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.