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-db-contextgit 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-db-context)<a href="https://agentmods.dev/commands/zekiriabd/sdd-pro/sdd-db-context"><img src="https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/sdd-db-context.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 | $0.00134 | $0.02203 |
| Opus 5 | $0.00067 | $0.01102 |
| Sonnet 5 | $0.00027 | $0.00441 |
| Haiku 4.5 | $0.00013 | $0.00220 |
Grade A, and why
sdd-db-context 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdd-db-context [--project DB] [--refresh] [--no-architect] [--diff-against PATH] [--json]
Rôle
Construit le Database Context, la source de vérité partagée du reverse base de données. Aucun objet SQL n'est remonté en User Story avant qu'elle existe : c'est ce qui empêche chaque analyste de redécouvrir la base, chacun à sa façon.
db-introspection.json + db-schema.json (déjà extraits en LECTURE SEULE)
└─[0.A déterministe, 0 token]─► faits + graphe + plan de vagues
└─[0.B agent reverse-db-architect]─► hypothèses (glossaire, domaines, risques)
└─ db-context.json (SSoT versionné) + db-context/ (arbre découpé)
└─ packs/{objet}.md ─► consommés par les analystes spécialisés
Le contrat central — faits ≠ hypothèses
| Produit par | Contenu | Peut devenir un AC ? | |
|---|---|---|---|
facts |
scripts déterministes (0 token) | tables, colonnes, clés, CHECK, CRUD, graphe | oui |
hypotheses |
agent reverse-db-architect |
glossaire, sous-domaines, rôles, risques | jamais |
La séparation est structurelle : l'agent écrit un fichier distinct
(db-context.hypotheses.json) qu'un script fusionne dans la seule branche
hypotheses. Il ne peut pas écraser un fait, même en essayant. Même garde que
db-schema.enrichment.json (ADV-3).
Args
| Arg | Type | Description |
|---|---|---|
--project DB |
optionnel | Dossier sous workspace/old/ (défaut = DB_NAME de stack.md) |
--refresh |
flag | Ignore le contexte précédent et relance l'architecte (les hypothèses portées sont abandonnées) |
--no-architect @llm-only-flag |
flag | S'arrête après 0.A — faits seuls, aucun coût LLM. Interprété par la commande (elle ne spawne pas l'architecte) ; le script 0.A n'en a pas besoin |
--depth N |
optionnel | Profondeur d'appelés portée dans un pack (défaut 2) |
--budget N |
optionnel | Taille max d'un pack en octets (défaut 14000) |
--diff-against PATH |
optionnel | Compare à un db-context.json antérieur et rapporte la dérive (exit 4), sans rien écrire |
--json |
flag | Sortie machine |
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 · 142 lines · 134 tokens per session scan A 0245ecc6c3f0
sdd-db-context is a command published in the GitHub repository zekiriabd/SDD-Pro (191 stars, last pushed 2d ago), licensed Apache-2.0. It adds 134 tokens to every session and 2,203 once invoked, about $0.0007 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
review-renovate
Review and merge renovate PRs with automerge configuration updates.
monitor-ci
Monitors pull request CI checks until they are resolved (pass or fail).
plan-regression-tests
Plan regression tests for existing code with it.skip statements.
init
Initialize configurations for Supabase local development.
volume-admin-set-status
Changes the operational status of a named volume.
notebook-query
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…