sdd-db-reverse

sdd-db-reverse is a command for Claude Code from zekiriabd/SDD-Pro. It costs 135 tokens per session (2,381 once invoked), scanned A, original, Apache-2.0.

A read-only tool for reverse-engineering one database object, such as a stored procedure, function, view, or trigger, into project documentation.

In plain words
What is it for?
Use it to inspect one SQL object, create a user story for it, and create or update the feature document for its business module.
Why use it?
It lets you document a specific piece of database logic without first processing the entire database or changing its contents.

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-reverse
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-reverse

README.md
[![agentmods](https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/sdd-db-reverse.svg)](https://agentmods.dev/commands/zekiriabd/sdd-pro/sdd-db-reverse)
Your own site
<a href="https://agentmods.dev/commands/zekiriabd/sdd-pro/sdd-db-reverse"><img src="https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/sdd-db-reverse.svg" alt="Measured on agentmods" height="20"></a>
Per session 135 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,381 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 $0.00135 $0.02381
Opus 5 $0.00068 $0.01190
Sonnet 5 $0.00027 $0.00476
Haiku 4.5 $0.00014 $0.00238

Measured 4d ago against content hash 550d3ba49669, 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-reverse 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 4d 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.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdd-db-reverse {proc-name} [--project DB] [--no-architect] [--json]

Rôle

Reverse engineering ciblé d'un seul objet SQL exécutable — procédure stockée, fonction, vue, trigger (ou package Oracle, routé vers le proc-analyst). Pendant unitaire de /sdd-db-reverse-full. L'objet devient une User Story ; il est rattaché à la FEAT de son module (créée si absente, sinon mise à jour).

/sdd-db-reverse dbo.usp_Contact_Insert
   └─ introspect READ-ONLY (1 objet) ─► snapshot + inventory (module Contact)
       └─ Phase 0 db-context (0.A faits + pack de l'objet, 0.B interprétation)
          └─ spécialiste de SA famille (proc/fonction/vue/trigger)
             ─► us/{n}-{m}-Creer-Contact.md
              └─ build_proc_feats --unit U-x ─► feats/{n}-Contact.md (assemblé/rafraîchi)

Phase 0 câblée ici (correctif 2026-08-30). La commande enchaînait l'introspection directement sur le spécialiste, alors que celui-ci exige .sys/db-context/packs/{objet}.md (pré-condition 2 de sa définition). Sur un projet frais — aucun /sdd-db-context ni /sdd-db-reverse-full préalable — le pack n'existait pas et l'analyste sortait en [REVERSE_DB_PACK_MISSING]. Le mode objet unique construit désormais le Database Context lui-même : il ne dépend d'aucun run full antérieur.

Args

Arg Type Description
{proc-name} requis Nom de la procédure ([schema.]nom, ex. dbo.usp_Contact_Insert ou usp_Contact_Insert)
--project DB optionnel Dossier sous workspace/old/ (défaut = DB_NAME de stack.md)
--no-architect @llm-only-flag flag Phase 0 limitée à 0.A (faits + pack, 0 token) — aucune interprétation d'architecte. Interprété par la commande (elle ne spawne alors pas l'architecte) ; db_context_build.py n'en a pas besoin
--json flag Sortie machine

Garanties lecture seule

Identiques à /sdd-db-reverse-full : SELECT catalogue + OBJECT_DEFINITION uniquement (validés par readonly_guard), jamais de DDL/DML, jamais d'exécution de la procédure. Le mot de passe (stack.md) reste en RAM, jamais loggé.

Read the full file on GitHub · 138 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. 4d ago First seen · 138 lines · 135 tokens per session scan A 550d3ba49669

Subscribe to this mod's changes

sdd-db-reverse is a command published in the GitHub repository zekiriabd/SDD-Pro (190 stars, last pushed yesterday), licensed Apache-2.0. It adds 135 tokens to every session and 2,381 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.