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/sdd-helpgit 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/sdd-help)<a href="https://agentmods.dev/commands/zekiriabd/sdd-pro/sdd-help"><img src="https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/sdd-help.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 | $0.00017 | $0.02736 |
| Opus 5 | $0.00009 | $0.01368 |
| Sonnet 5 | $0.00003 | $0.00547 |
| Haiku 4.5 | $0.00002 | $0.00274 |
Grade A, and why
sdd-help 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.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdd-help — Aide contextuelle "what's next"
Nouveau v7.0.0+ (emprunt
bmad-help) : guidance contextuelle orientée action — pas un diagnostic brut comme/sdd-status, mais une recommandation de la prochaine commande logique selon l'état détecté du projet.Lecture seule, aucune écriture, aucune invocation d'agent. Coût : ~0 token (délégation à
sdd_state.py+query_console_db.py).
Usage :
/sdd-help— guidance globale projet (où on en est + quoi faire)/sdd-help {n}— guidance focalisée sur FEAT{n}/sdd-help "comment X ?"— réponse FAQ (matching mots-clés)
Différence avec /sdd-status : /sdd-status rend un tree ASCII
de l'état complet (snapshot). /sdd-help fait la même introspection
mais retourne 1-3 lignes de guidance actionnable : la commande
suivante à lancer + son but. Pour les utilisateurs qui ne connaissent
pas les 13 commandes par cœur.
STEP 1 — Détection du mode
| Argument | Mode |
|---|---|
| absent | global : scanner toutes les FEATs, identifier le plus gros gap |
| entier ≥ 1 | focused : focus sur FEAT {n}, suggérer prochaine étape |
commence par " ou ' ou contient un ? |
FAQ : matcher mots-clés contre §FAQ ci-dessous |
Si argument numérique mais aucune FEAT {n}-*.md trouvée →
Aucune FEAT {n} dans workspace/feats/.
Pour la créer : /feat-generate {NomDeLaFeature}
STEP 2 — Collecte d'état déterministe (0 LLM)
# État global (FEATs, US, mockups, ARCH, DB, CLAUDE.md projets)
python .sdd/python/sdd_scripts/sdd_state.py status [--feat-number {n}] --json
# Métriques QA (si FEAT donnée)
python .sdd/python/sdd_scripts/query_console_db.py feat-stats --feat {n} 2>/dev/null
Latence cumulée ~100 ms. Échec script → fallback minimal : retourner
la commande /sdd-status et inviter Tech Lead à diagnostiquer.
STEP 3 — Décision (arbre)
3.A — Mode global (aucune FEAT en argument)
Évaluer dans l'ordre, premier match gagne :
| Condition détectée | Recommandation (1L) |
|---|---|
0 FEAT dans workspace/feats/ |
/feat-generate <Nom> — démarrer la 1ʳᵉ FEAT (3-6 questions, ~2 min) |
| ≥ 1 FEAT, 0 US générée pour ≥ 1 FEAT | /us-generate {n} — découper la FEAT en User Stories testables |
≥ 1 FEAT avec US, aucun rapport readiness workspace/.sys/.validation/{n}-readiness.md |
/feat-validate {n} — vérifier la maturité avant de coder (gate GO/NO-GO) |
≥ 1 FEAT validée, aucun projet sous workspace/src/ |
/sdd-full {n} — pipeline A→Z (arch + back + API gate + front + QA + review) |
Projet bootstrappé mais ≥ 1 FEAT avec US Status: Ready sans code |
/dev-run {n} — matérialiser le code (back → API gate → front) |
Code généré, QA non exécutée (coverage.json absent) |
/qa-generate {n} — générer tests + coverage + quality scan |
QA OK, pas de /sdd-review récent (> 24h ou absent) |
/sdd-review {n} — audit consolidé style Sonar |
| Toutes FEATs en 🟢 ✓ | /sdd-status — voir le récap, ou créer une nouvelle FEAT avec /feat-generate |
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 Changed cf3b4f96886d
- 4d ago First seen · 178 lines · 17 tokens per session scan A 99b7384349c9
sdd-help is a command published in the GitHub repository zekiriabd/SDD-Pro (190 stars, last pushed yesterday), licensed Apache-2.0. It adds 17 tokens to every session and 2,736 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
git
Git operations with intelligent commit messages and workflow optimization.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.