sdd-db-context

sdd-db-context is a command for Claude Code from zekiriabd/SDD-Pro. It costs 134 tokens per session (2,203 once invoked), scanned A, original, Apache-2.0.

A command that builds a versioned description of a database before the database is converted into user stories. It records tables, columns, keys, constraints, database operations, dependencies, and planned analysis waves, while separating facts from interpretations.

In plain words
What is it for?
Use it as the first phase of a reverse-engineering process for a database, including schema inventory, dependency planning, and analyst context packs.
Why use it?
It gives later analysts one shared view of the database instead of making each analyst rediscover its structure.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/zekiriabd/sdd-pro/sdd-db-context
Clone the repo
git clone --depth 1 https://github.com/zekiriabd/SDD-Pro

Made for: Claude Code.

Wrote 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.

agentmods badge for sdd-db-context

README.md
[![agentmods](https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/sdd-db-context.svg)](https://agentmods.dev/commands/zekiriabd/sdd-pro/sdd-db-context)
Your own site
<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>
Per session 134 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,203 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash 0245ecc6c3f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/commands/sdd-db-context.md · 142 lines

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

Read the full file on GitHub · 142 lines

Changes

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.

  1. 5d ago First seen · 142 lines · 134 tokens per session scan A 0245ecc6c3f0

Subscribe to this mod's changes

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.