sdd-db-reverse-full

sdd-db-reverse-full is a command for Claude Code from zekiriabd/SDD-Pro. It costs 133 tokens per session (7,243 once invoked), scanned A, original, Apache-2.0.

A read-only database reverse-engineering tool that examines stored procedures, functions, views, and triggers—SQL objects that run or define database logic.

In plain words
What is it for?
Use it to inventory executable SQL, map calls and CRUD operations, and create one user story per SQL object plus feature documents for use by the SDD pipeline.
Why use it?
It turns database logic into structured project documentation without changing the database. It also groups related objects into business modules.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is python .sdd/python/sdd_reverse_scripts/scan_snapshot_secrets.py --project {DB} [--json].

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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-reverse-full

README.md
[![agentmods](https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/sdd-db-reverse-full.svg)](https://agentmods.dev/commands/zekiriabd/sdd-pro/sdd-db-reverse-full)
Your own site
<a href="https://agentmods.dev/commands/zekiriabd/sdd-pro/sdd-db-reverse-full"><img src="https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/sdd-db-reverse-full.svg" alt="Measured on agentmods" height="20"></a>
Per session 133 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,243 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 5.1 $0.00133 $0.07243
Opus 5 $0.00067 $0.03622
Sonnet 5 $0.00027 $0.01449
Haiku 4.5 $0.00013 $0.00724

Measured 6d ago against content hash a44a84949620, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sdd-db-reverse-full 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 6d 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-reverse-full.md · 405 lines

How it starts

The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdd-db-reverse-full [--project DB] [--max-parallel N] [--sequential] [--no-architect] [--json]

Rôle

Orchestrateur du reverse engineering base de données → FEATs. À partir de la connexion déclarée dans stack.md ## Active Database, il lit toutes les procédures stockées en lecture seule, les regroupe en modules métier, et produit des FEATs SDD_Pro standard consommables par /sdd-full.

stack.md (## Active Database)  ← config + variables d'environnement (${VAR} via .env)
   └─[Phase 1 introspect READ-ONLY]─► proc-snapshot/*.sql + db-introspection.json
        │                              + schema-snapshot/*.sql + db-schema.json + inventory.json
        └─[Phase 0.A déterministe]─► FAITS : CRUD, graphe d'appels, plan de vagues
             └─[Phase 0.B reverse-db-architect]─► HYPOTHÈSES : glossaire, domaines, risques
                  └─► db-context.json (SSoT versionné) + db-context/packs/{objet}.md
                       └─[vagues : feuilles d'abord, spécialistes en parallèle borné]
                       │    proc-analyst · function-analyst · view-analyst · trigger-analyst
                       │    └─► us/{n}-{m}-{Name}.md   (1 objet SQL = 1 US)
                       │         └─ résumé réinjecté dans db-context.findings ─┐
                       │            (barrière de vague, puis vague suivante) ◄─┘
                       └─[rung 2 : synthèse module]─► feats/{n}-{Module}.md  (1 module = 1 FEAT)
                            └─ validate_reverse_feat + check_reverse_feat_for_full
                                 └─► REVERSE-GATE ─► /sdd-full

Modèle (confirmé)

  • 1 objet SQL = 1 User Story · 1 module = 1 FEAT (objets d'un même objet métier).
  • Comprendre avant d'écrire : aucune User Story n'est produite avant que la Phase 0 ait construit le Database Context. Un analyste ne redécouvre jamais la base — il reçoit le slice qui le concerne.
  • Remontée stricte : la FEAT est composée depuis les US + l'inventaire, jamais en relisant le corps SQL. L'assembleur lit réellement les US (titre métier, ACs, mode d'extraction) et y écrit en retour Covers: + le Parent FEAT hash.
  • Faits ≠ hypothèses : les faits viennent des scripts déterministes et peuvent devenir des Acceptance Criteria ; les hypothèses viennent de l'architecte et ne le peuvent jamais. La séparation est structurelle.

Read the full file on GitHub · 405 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. 6d ago First seen · 405 lines · 133 tokens per session scan A a44a84949620

Subscribe to this mod's changes

sdd-db-reverse-full is a command published in the GitHub repository zekiriabd/SDD-Pro (191 stars, last pushed 2d ago), licensed Apache-2.0. It adds 133 tokens to every session and 7,243 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.