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/dev-plangit clone --depth 1 https://github.com/zekiriabd/SDD-ProWhat 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 | $0.00018 | $0.02927 |
| Opus 5 | $0.00009 | $0.01463 |
| Sonnet 5 | $0.00004 | $0.00585 |
| Haiku 4.5 | $0.00002 | $0.00293 |
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.
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-fullSTEP 3.6 (conditionnel). Utilisateur final : préférer/sdd-fullou/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 Specsbackend-*ET aucunfrontend-*→ ERROR comme dans/dev-run.
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 · 263 lines · 18 tokens per session scan A 4709717c07a8
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.
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.