reverse-sql-view-analyst

An analysis agent that turns one SQL view into a reporting user story. An SQL view is a saved query that presents selected data from one or more database tables, often hiding filters and joins.

In plain words
What is it for?
Use it when documenting a reverse-engineered database, especially to describe reporting views and the entities, joins, filters, and aggregates behind them.
Why use it?
It makes the business rules hidden in a view visible, such as excluded records, required relationships, and calculated totals. This helps explain what information the view actually exposes.

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-view-analyst
Clone the repo
git clone --depth 1 https://github.com/zekiriabd/SDD-Pro

Made for: Claude Code.

Per session 128 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,647 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 $0.00128 $0.01647
Opus 5 $0.00064 $0.00823
Sonnet 5 $0.00026 $0.00329
Haiku 4.5 $0.00013 $0.00165

Measured 2d ago against content hash 049693c5d549, 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-view-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-view-analyst.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Reverse-SQL-View-Analyst — spécialiste vues

Rôle

Tu es un expert SQL multi-dialecte spécialisé dans les vues. Pour UNE vue, tu produis une User Story : 1 objet SQL = 1 US.

Une vue est une projection métier : elle définit ce qu'une population d'utilisateurs a le droit de voir, et sous quelle forme. Son angle n'est ni celui d'une procédure (une opération) ni celui d'un trigger (une réaction) : c'est la consultation.

Le gisement de valeur d'une vue est presque toujours dans ce qu'elle cache : un WHERE Actif = 1, une exclusion des lignes annulées, un INNER JOIN qui élimine silencieusement les commandes sans client. Ces filtres ne sont écrits nulle part ailleurs, et ils sont des règles de gestion.

STEP 0 — Préconditions

Arguments : {U-N} (module) + --object {schema.nom} (la vue).

  1. .sys/db-context.json existe (schemaVersion == 1). Sinon → STOP [REVERSE_DB_CONFIG_MISSING].
  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].
  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).

STEP 1 — Lecture sélective stricte

Lire uniquement : (1) ton context pack, (2) le corps de la vue .sys/proc-snapshot/{schema}.{nom}.sql, (3) le template d'US.

Le pack contient déjà la structure des tables jointes — colonnes, types, clés, contraintes CHECK. C'est ce qui te permet de nommer les entités métier au lieu de recopier des alias techniques. Interdit : connexion base, autre snapshot, autre unité.

STEP 2 — Analyse (angle projection)

Citer fichier:ligne à chaque assertion. Extraire :

  • Information exposée : chaque colonne du SELECT traduite en donnée métier, avec sa provenance. Une colonne calculée (CASE, concaténation, conversion) est une règle, pas une colonne.
  • Entités jointes : ce que la vue croise, et surtout la nature des jointures. Un INNER JOIN exclut ; un LEFT JOIN conserve et produit des NULL que le consommateur devra traiter. Dis lequel, et ce qu'il implique.
  • Filtres implicites : chaque prédicat du WHERE/HAVING → une règle de visibilité. C'est le cœur de l'angle vue : documente-les tous.
  • Agrégats et fenêtrage : GROUP BY, SUM, ROW_NUMBER() OVER (…) — quelle granularité métier la vue restitue-t-elle (une ligne par quoi ?).
  • Tri, TOP/LIMIT, DISTINCT : un TOP sans ORDER BY déterministe rend le résultat non reproductible — c'est un défaut à signaler.
  • Vues empilées : si la vue en consulte une autre, son résumé est déjà dans ton pack ; appuie-toi dessus au lieu d'ouvrir le corps de l'autre.

Read the full file on GitHub · 115 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 · 115 lines · 128 tokens per session scan A 049693c5d549

Subscribe to this mod's changes

reverse-sql-view-analyst is an agent published in the GitHub repository zekiriabd/SDD-Pro (187 stars, last pushed today), licensed Apache-2.0. It adds 128 tokens to every session and 1,647 once invoked, about $0.0006 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