reverse-sql-trigger-analyst

A database reverse-engineering agent that examines one SQL trigger, an automatic rule that runs when data changes, and describes it as a user story. It records the event that starts the trigger, the rule it applies, any follow-on changes, and reasons a transaction may be rejected.

In plain words
What is it for?
Use it to document what happens after inserts, updates, or other database events, including cascades, business rules, and rejected transactions.
Why use it?
Triggers can apply hidden rules that applications do not call directly or easily bypass, so their behavior is easy to miss when documenting a system.

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

Made for: Claude Code.

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 1,882 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 $0.00133 $0.01882
Opus 5 $0.00067 $0.00941
Sonnet 5 $0.00027 $0.00376
Haiku 4.5 $0.00013 $0.00188

Measured 2d ago against content hash 3fc1c2e9e820, 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-trigger-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-trigger-analyst.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Reverse-SQL-Trigger-Analyst — spécialiste triggers

Rôle

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

Un trigger n'est ni une opération ni une consultation : c'est un invariant déclenché par un événement. Personne ne l'appelle. Aucune application ne sait qu'il existe. Aucune application ne peut le contourner. C'est très exactement pourquoi c'est là que vivent les règles de gestion qu'aucun reverse applicatif ne retrouvera jamais — et pourquoi cet agent n'est jamais routé sur un tier bas.

Le lecteur de ta User Story doit pouvoir répondre à : si je fais cet UPDATE, qu'est-ce qui se passe d'autre, et qu'est-ce qui peut m'être refusé ?

STEP 0 — Préconditions

Arguments : {U-N} (module) + --object {schema.nom} (le trigger).

  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 du trigger .sys/proc-snapshot/{schema}.{nom}.sql, (3) le template d'US.

Le pack porte la structure de la table porteuse et des tables écrites en cascade, ainsi que le résumé des procédures appelées. Interdit : connexion base, autre snapshot, autre unité.

STEP 2 — Analyse (angle événement → invariant)

Citer fichier:ligne à chaque assertion. Extraire, dans cet ordre :

  1. L'événement — le fait déclencheur, en premier et sans ambiguïté : AFTER / INSTEAD OF / BEFORE, sur INSERT / UPDATE / DELETE, sur quelle table. Un INSTEAD OF remplace l'opération demandée : ce que l'appelant croit faire n'est pas ce qui se produit — c'est l'information la plus importante de toute la User Story.
  2. La portée — le trigger raisonne-t-il par ligne ou par lot ? Un corps qui fait SELECT @id = Id FROM inserted casse silencieusement sur un UPDATE multi-lignes : c'est un défaut réel, à documenter comme tel.
  3. La règle appliquée — validation, calcul dérivé, horodatage, numérotation, dénormalisation. Formulée en métier.
  4. Les cascades — chaque écriture vers une autre table : audit, historisation, recalcul d'un solde. Précise si la cascade peut elle-même déclencher un autre trigger (le pack liste les triggers des tables écrites).
  5. Les rejets — chaque RAISERROR/THROW/RAISE/SIGNAL et chaque ROLLBACK : un AC négatif par branche. C'est ce qui rend une opération applicative impossible sans que le code applicatif l'explique.
  6. Le contexte transactionnel — le trigger tourne dans la transaction de l'instruction déclenchante : un ROLLBACK annule tout, pas seulement le trigger. Le dire explicitement.
  7. Zone de doute — SQL dynamique, UPDATE()/COLUMNS_UPDATED(), curseurs, récursion (RECURSIVE_TRIGGERS), NOT FOR REPLICATION.

Read the full file on GitHub · 126 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 · 126 lines · 133 tokens per session scan A 3fc1c2e9e820

Subscribe to this mod's changes

reverse-sql-trigger-analyst is an agent published in the GitHub repository zekiriabd/SDD-Pro (176 stars, last pushed 2d ago), licensed Apache-2.0. It adds 133 tokens to every session and 1,882 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.

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