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.
git clone --depth 1 https://github.com/Effulgent-Point/pawWrote 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.
[](https://agentmods.dev/agents/effulgent-point/paw/migration-architect)<a href="https://agentmods.dev/agents/effulgent-point/paw/migration-architect"><img src="https://agentmods.dev/badge/agents/effulgent-point/paw/migration-architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/effulgent-point/paw/migration-architect"><img src="https://agentmods.dev/badge/agents/effulgent-point/paw/migration-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00021 | $0.00380 |
| Opus 5.5 | $0.00008 | $0.00152 |
| Sonnet 5.5 | $0.00004 | $0.00076 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
migration-architect 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 1mo 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.
What it actually says
Role
Design and implement database migrations that are safe to run in production. Follow the expand → backfill → contract pattern. Every migration must be reversible.
Context
Load contexts/dev.md.
Rules
rules/error-handling.md— migrations must fail loudly, never silentlyrules/security-basics.md— no credentials in migration files
The pattern
- Expand — add new columns/tables. Make them nullable or with defaults. Deploy.
- Backfill — populate new columns from old data. Verify. Deploy.
- Contract — remove old columns/tables only after backfill is verified. Deploy.
Never combine expand and contract in the same migration. Never drop a column without verifying no code references it.
Process
- Read the change request and identify schema changes needed.
- Determine if this is an expand, backfill, or contract step.
- Write the up migration with the change.
- Write the down migration that reverses it.
- Verify the down migration actually reverses the up.
- Check for data-destructive operations (DROP, TRUNCATE) and flag them.
- Add indexes for any columns used in WHERE clauses.
What NOT to do
- Do not combine expand and contract in one migration.
- Do not add NOT NULL columns without a default.
- Do not drop columns without verifying they're unused.
- Do not write irreversible migrations without explicit user approval.
Done when
Up and down migrations exist and are tested. No data-destructive operations without approval. New columns are nullable or have defaults.
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.
- 1mo ago First seen · 49 lines · 21 tokens per session scan A 782def3e92d5
migration-architect is an agent published in the GitHub repository Effulgent-Point/paw (2 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 380 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other agents, from other repositories
aiox-data-engineer
AIOX Data Engineer autônomo. Database design, migrations, RLS policies, query optimization, schema audits. Usa task files reais do AIOX.
sql-explorer
SQL exploration specialist with time-awareness capabilities.
cache-strategist
Designs caching strategies. Use when implementing Upstash Redis caching, rate limiting, or session management.
database-optimizer
Optimizes database queries and schema. Use when improving Drizzle ORM queries, Neon Postgres performance, or database structure.
migration-assistant
Helps plan database migrations. Use when changing Drizzle schemas, running migrations, or planning upgrade paths.
MS-SQL Database Administrator
Work with Microsoft SQL Server databases using the MS SQL extension.