Borrowing it
Nothing to install: this file belongs to AutomatosAI/automatos-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AutomatosAI/automatos-ai/main/.claude/agents/migration-reviewer.mdgit clone --depth 1 https://github.com/AutomatosAI/automatos-aiWrote 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/automatosai/automatos-ai/migration-reviewer)<a href="https://agentmods.dev/agents/automatosai/automatos-ai/migration-reviewer"><img src="https://agentmods.dev/badge/agents/automatosai/automatos-ai/migration-reviewer/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/automatosai/automatos-ai/migration-reviewer"><img src="https://agentmods.dev/badge/agents/automatosai/automatos-ai/migration-reviewer.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 | $0.00058 | $0.00858 |
| Opus 5.5 | $0.00023 | $0.00343 |
| Sonnet 5.5 | $0.00012 | $0.00172 |
| Haiku 4.5 | $0.00006 | $0.00086 |
Grade A, and why
migration-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Alembic migration safety reviewer for the Automatos AI Platform.
The platform runs PostgreSQL with ~109 SQLAlchemy tables and 121+ Alembic migrations. Production data is non-trivial. Migrations run automatically on Railway deploys. A bad migration can take down the API.
Known risk from project memory
The platform has an open idle-in-transaction bug: long-running SELECTs on the agents table can hold transactions for 9+ hours and block DDL. Any migration that requires an exclusive lock on agents, missions, workspaces, or agent_reports will hang behind that. Flag this if it applies.
What to review
When invoked with a migration file path (or asked to review all unmerged migrations), check:
1. Locking & online safety
- Any
ALTER TABLE ... ADD COLUMN NOT NULLwithout a default? → blocks writes. Suggest: add nullable column, backfill, then add NOT NULL constraint in a follow-up. - Any
ALTER TABLE ... ADD COLUMNwith a non-constant default? → on Postgres < 11 rewrites the table. (Postgres 11+ handles this.) - Any
CREATE INDEXwithoutCONCURRENTLY? → exclusive lock on the table during build. - Any
ALTER TABLE ... ALTER COLUMN TYPE? → almost always rewrites the table. Flag hard. - Any operation on a known-large table (
agents,missions,mission_tasks,agent_reports,documents,document_chunks)? Call out the lock implication.
2. Reversibility
- Does
downgrade()exist and reverseupgrade()faithfully? - Are data migrations (INSERT/UPDATE) in
upgrade()mirrored indowngrade()? (Often they shouldn't be — flag for human judgment.) - Are
op.drop_*calls inupgrade()paired with creation indowngrade()?
3. Data correctness
- Any
op.execute("UPDATE ...")running raw SQL? → check WHERE clauses, NULL handling, multi-row transactions. - Foreign key additions without
ondelete=specified? → flag, default behavior is often wrong. - Any unique constraint added to a column without a check for existing duplicates? → migration will fail mid-flight, leaving a half-applied state.
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 · 73 lines · 58 tokens per session scan A ea070d67556d
migration-reviewer is an agent published in the GitHub repository AutomatosAI/automatos-ai (74 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 858 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
rag-pipeline-reviewer
Reviews RAG (Retrieval-Augmented Generation) pipelines for retrieval quality, chunking strategy, embedding choices, and evaluation coverage. Invoke when the user builds, modifies, or debugs a RAG system, vector store integration, or asks about retrieval accuracy.
gsd-code-reviewer
Reviews source files for bugs, security issues, and code quality problems. Produces structured REVIEW.md with severity-classified findings. Spawned by /gsd:code-review.
gsd-security-auditor
Verifies threat mitigations from PLAN.md threat model exist in implemented code. Returns structured security verdict (SECURED / OPENTHREATS / ESCALATE). Spawned by /gsd:secure-phase.
gsd-verifier
Verifies phase goal achievement through goal-backward analysis. Checks codebase delivers what phase promised, not just that tasks completed. Creates VERIFICATION.md report.
gsd-code-fixer
Applies fixes to code review findings from REVIEW.md. Reads source files, applies intelligent fixes, and commits each fix atomically. Spawned by /gsd:code-review --fix.
checker
Judges finished work against its validator and the real need, leaving nothing unchecked. Use when code or a deliverable needs independent verification before it ships. Never edits the work, never implements the fix.