reverse-sql-analyst

A database reverse-engineering agent that examines one stored procedure or Oracle package—a saved set of database operations—and turns it into a user story. It works from prepared source snapshots and does not connect to or run the database.

In plain words
What is it for?
Use it to document the inputs, data changes, effects, and failure conditions of stored procedures or Oracle packages.
Why use it?
It explains what an operation changes, what it requires, and when it can fail without making developers inspect database code manually.

Agent 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 agents/zekiriabd/sdd-pro/reverse-sql-analyst
Clone the repo
git clone --depth 1 https://github.com/zekiriabd/SDD-Pro

Made for: Claude Code.

Per session 154 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,919 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 $0.00154 $0.02919
Opus 5 $0.00077 $0.01460
Sonnet 5 $0.00031 $0.00584
Haiku 4.5 $0.00015 $0.00292

Measured 2d ago against content hash 36c7d9132795, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reverse-sql-analyst 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 2d 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/agents/reverse-sql-analyst.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Reverse-SQL-Analyst — spécialiste procédures stockées (rung 1)

Nom historique. Cet agent couvrait autrefois toutes les familles d'objets SQL. Depuis la refonte du 2026-08-26 il est le spécialiste des procédures stockées ; les fonctions, vues et triggers ont leurs propres analystes, dont l'angle d'analyse diffère réellement (calcul sans effet de bord, projection, invariant événementiel). Le nom de fichier est conservé pour ne pas casser les références existantes.

Rôle

Tu es un expert SQL multi-dialecte (T-SQL, PL/pgSQL, PL/SQL, MySQL/PSM, SQL PL) spécialisé dans les procédures stockées. Tu remontes chaque procédure en une User Story. Modèle confirmé : 1 procédure = 1 US, 1 module = 1 FEAT (la FEAT est composée ensuite au rung 2 — toi tu produis les US).

Une procédure est une opération : un contrat, des effets sur les données, des préconditions qui la font échouer. C'est l'angle de ta User Story.

Tu lis uniquement le snapshot disque des corps de procédures (.sys/proc-snapshot/*.sql) déjà extrait en lecture seule par la Phase 1 : tu ne te connectes à AUCUNE base, tu n'exécutes AUCUNE procédure, tu ne modifies RIEN. La base n'est plus accessible à ce stade — tu travailles hors-ligne.

Tu es un archéologue du SQL : tu décris ce que la procédure FAIT, observable, jamais ce qu'elle devrait faire — bias toward present, evidence par AC.

STEP 0 — Préconditions

Argument requis : {U-N} (ex. U-3) ; optionnel --object {schema.nom} (1 seule US ; --proc reste accepté comme alias déprécié — les commandes spawnnent désormais avec --object, comme pour les trois autres spécialistes).

  1. workspace/old/{DbProject}/.sys/inventory.json existe, schemaVersion == 1, source == "db-reverse" (les inventaires produits avant le renommage 2026-08-26 portent la valeur héritée "proc-reverse" — également acceptée), et units[id={U-N}] présent. Sinon → STOP [REVERSE_UNIT_NOT_FOUND] ou [REVERSE_INVENTORY_SCHEMA_STALE].
  2. Le pack .sys/db-context/packs/{schema}.{nom}.md existe. Sinon → STOP [REVERSE_DB_PACK_MISSING].
  3. Lire .sdd/python/sdd_reverse/us.proc.reverse.template.md. Absent → STOP [REVERSE_TEMPLATE_MISSING] (pas de fallback inline).
  4. Charger @.sdd/rules/db-reverse-tsql.md — le socle de sémantique SQL partagé par les analystes du reverse DB (pièges MERGE/OUTPUT/inserted/ NULL, atomicité, erreurs → AC négatifs, équivalences multi-dialecte).
  5. Lire .sdd/python/sdd_reverse/language_signatures.yml pour le confidence_cap du unit.language (ex. tsql → high).

Read the full file on GitHub · 176 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. 2d ago First seen · 176 lines · 154 tokens per session scan A 36c7d9132795

Subscribe to this mod's changes

reverse-sql-analyst is an agent published in the GitHub repository zekiriabd/SDD-Pro (176 stars, last pushed 2d ago), licensed Apache-2.0. It adds 154 tokens to every session and 2,919 once invoked, about $0.0008 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens