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/arch-initgit 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 | $0.00021 | $0.01386 |
| Opus 5 | $0.00010 | $0.00693 |
| Sonnet 5 | $0.00004 | $0.00277 |
| Haiku 4.5 | $0.00002 | $0.00139 |
Grade A, and why
arch-init 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 3d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/arch-init — Bootstrap idempotent (projets vides + scaffolding DB)
⚠️ Commande interne v7.0.0 — invoquée par
/dev-runSTEP 5. Utilisateur final : préférer/sdd-fullou/dev-run(gèrent pré-conditions, idempotence, état).
Invoque l'agent arch pour préparer l'ossature complète du projet
à partir des stacks actifs :
- Phase A : création de la solution, des projets vides, des références inter-projets, et installation des dépendances racine
- Phase B : si
DatabaseType ≠ none, introspection READ-ONLY de la base + scaffolding Database-First (entities + DbContext)
Idempotent : relancer la commande ne casse rien — les projets
déjà initialisés sont skippés. Le scaffolding DB --force est
incrémental.
Usage : /arch-init (aucun argument).
STEP 1 — Vérifier le stack
Vérifier que workspace/stack/stack.md existe et contient au moins une
entrée non commentée sous ## Active Tech Specs.
Si absent ou vide →
ERROR: /arch-init — stack non sélectionné
CAUSE: [STACK_MALFORMED] workspace/stack/stack.md manque ou ## Active Tech Specs vide
FIX: créer workspace/stack/stack.md et activer au moins un backend ou frontend
STEP 2 — Vérifier les blocs ## Active Database + ## Active Auth Specs
Lire workspace/stack/stack.md → récupérer le bloc
## Active Database (depuis 2026-05-14, DatabaseType n'est plus
dans ## Project Config).
- Si
## Active Databaseabsent OUDatabaseType: none→ SKIP le check DB. - Sinon → vérifier que les 5 clés sont présentes (valeur non vide) :
DB_HOST,DB_PORT,DB_NAME,DB_USER,DB_PASSWORD. Si une seule manque :ERROR: /arch-init — clé(s) DB manquante(s) dans ## Active Database CAUSE: [ENV_MISSING] clés non définies : {liste} FIX: renseigner les valeurs dans workspace/stack/stack.md ## Active Database
Si un stack auth est listé sous ## Active Auth Specs, vérifier les
clés AZ_* (cf. auth/azure-ad.md §2). Manquantes → ERROR similaire.
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.
- 3d ago First seen · 145 lines · 21 tokens per session scan A 6f9bb7bb0be0
arch-init is a command published in the GitHub repository zekiriabd/SDD-Pro (187 stars, last pushed yesterday), licensed Apache-2.0. It adds 21 tokens to every session and 1,386 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.