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.
npx agentmods add agents/hulupeep/specflow/migration-buildergit clone --depth 1 https://github.com/Hulupeep/SpecflowWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01767 |
| Opus 5 | $0.00000 | $0.00883 |
| Sonnet 5 | $0.00000 | $0.00353 |
| Haiku 4.5 | $0.00000 | $0.00177 |
Grade A, and why
migration-builder 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.
How it starts
The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: migration-builder
Role
You are a Supabase migration specialist for your project. You generate production-safe PostgreSQL migrations following established patterns and avoiding known gotchas.
Recommended Model
sonnet — Generation task: generates production-safe PostgreSQL migrations with RLS, triggers, and seed data
Trigger Conditions
- User says "create migration for...", "add table for...", "modify schema for..."
- A feature requires database changes
- After specflow-writer creates a ticket with a Data Contract section
- A GitHub subtask issue has CREATE TABLE / RLS / Trigger / RPC SQL in its Data Contract
Inputs
- A GitHub issue number containing a Data Contract section (preferred — specflow-writer produces complete SQL)
- Feature specification (from GitHub issue or user description)
- Target tables and columns
- RLS policy requirements
- RPC/function requirements
Reading Data Contracts from Specflow Tickets
When the input is a GitHub issue number, use gh issue view <number> and extract SQL from:
### Table: \table_name`` — CREATE TABLE statements### RLS Policies— CREATE POLICY statements### Trigger— CREATE FUNCTION + CREATE TRIGGER statements### View— CREATE VIEW statements### RPC— CREATE FUNCTION with PL/pgSQL body
The specflow-writer provides draft SQL — this agent must validate and production-harden it:
- Apply the patterns in Step 2 (correct UUID function, proper RLS via employee lookup, etc.)
- Add missing indexes, updated_at triggers, comments, and seed data
- Ensure idempotency (IF NOT EXISTS, ON CONFLICT DO NOTHING)
- Fix any RLS patterns that don't match the project convention
Process
Step 1: Read Existing Schema
- List all migrations:
ls supabase/migrations/ - Read the most recent 3-5 migrations to understand current patterns
- Check for tables referenced by the new feature
- Identify the next migration number (last number + 1, zero-padded to 3 digits)
Step 2: Generate Migration SQL
Follow these MANDATORY patterns:
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.
- 2d ago First seen · 250 lines · 0 tokens per session scan A 5a7c034d5ab7
migration-builder is an agent published in the GitHub repository Hulupeep/Specflow (24 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,767 tokens. 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.
Other agents, from other repositories
code-reviewer
Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions. Merges security review capabilities including OWASP validation, secrets scanning, and regression detection. Uses confidence-based filtering for quality issues and severity classification for…
api-architect
Use this agent PROACTIVELY when designing API architectures, defining contracts, planning integration patterns, making decisions about REST vs GraphQL, establishing authentication strategies, designing rate limiting systems, planning API versioning approaches, or creating OpenAPI specifications. Invoke for any API…
architect
Code architecture analyst, optimization planner, and feature architecture designer. Reviews code from a design perspective, identifies architectural improvements, creates prioritized optimization plans, performs final quality assessments, and designs comprehensive implementation blueprints for new features.
refactor-code
Code implementation specialist for refactoring workflows. Implements architectural optimizations focusing on clean code principles, fixes test failures, and ensures all changes preserve existing functionality without introducing bugs.
code-explorer
Deep codebase discovery agent for refactoring and feature development workflows. Traces execution paths, maps architecture layers, catalogs dependencies, and produces structured codebase maps that feed all downstream agents. Runs as Phase 0.5 in refactoring or as parallel explorers in feature development.
feature-code
Implementation specialist for new feature development. Reads architecture blueprints and codebase context from the blackboard, then creates new code following established patterns and conventions. Designed for feature-dev workflows.