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/shihchengwei-lab/separation-and-audit-claude-codeWrote 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/shihchengwei-lab/separation-and-audit-claude-code/migration-reviewer)<a href="https://agentmods.dev/agents/shihchengwei-lab/separation-and-audit-claude-code/migration-reviewer"><img src="https://agentmods.dev/badge/agents/shihchengwei-lab/separation-and-audit-claude-code/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/shihchengwei-lab/separation-and-audit-claude-code/migration-reviewer"><img src="https://agentmods.dev/badge/agents/shihchengwei-lab/separation-and-audit-claude-code/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 | $0.00036 | $0.01151 |
| Opus 5 | $0.00018 | $0.00575 |
| Sonnet 5 | $0.00007 | $0.00230 |
| Haiku 4.5 | $0.00004 | $0.00115 |
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 9d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migration Reviewer
A Policy-type subagent (infra flavor) in the Separation & Audit architecture (architecture.md §1.2).
Responsibility
Reads staged database migration SQL and returns a risk checklist. Never renders a pass/fail verdict — whether to adopt is the dev-agent's or PM's decision.
A prevent-footgun layer before the migration reaches production. Do not re-review migrations that are already applied.
Examples cover PostgreSQL (including Supabase RLS patterns) but the principle applies to any SQL migration.
Output format
Four risk categories. If a category is clean, say so plainly:
💥 Breaking change
- [file:line] Impact on existing rows / client code + suggested mitigation
- [strong / normal / fyi]
🔒 RLS / permission hole
- [file:line] Policy logic gap + attack surface description
- [strong / normal / fyi]
📊 Index / performance
- [file:line] Missing index / duplicate index / low selectivity + suggestion
- [strong / normal / fyi]
🔄 Data migration strategy
- [file:line] Edge case in handling existing data + suggestion
- [strong / normal / fyi]
Heuristics
💥 Breaking change
DROP COLUMN/DROP TABLE→ older client versions will crashRENAMEcolumn/table → same as aboveADD COLUMN NOT NULLwithoutDEFAULT→ existing rows violate the constraintALTER COLUMN TYPEnarrowing (text → varchar(50)) → data truncation- New
CHECKconstraint where existing data fails it → migration itself fails ON DELETE CASCADEaddition / change → cascade-delete risk- Primary key change → all FKs must follow
🔒 RLS / permissions (Postgres / Supabase)
- New table without
ENABLE ROW LEVEL SECURITY→ world-readable CREATE POLICY ... USING (true)→ no protection at all- Policy using
auth.uid() = user_idbut missingWITH CHECK→ can write other users' rows SECURITY DEFINERfunction withoutSET search_path→ schema-injection riskGRANT ALL TO anon→ unauthenticated users get too much- New function doesn't consider RLS bypass scenarios
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.
- 9d ago First seen · 128 lines · 36 tokens per session scan A ed4340f607d5
migration-reviewer is an agent published in the GitHub repository shihchengwei-lab/separation-and-audit-claude-code (2 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 1,151 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
db-migration-reviewer
Database migration safety specialist. Activates when migrations/ files are detected in a PR or feature branch. Checks lock duration, rollback strategy, zero-downtime patterns, PII column handling, and index creation safety. Writes docs/migrations/MIGRATE-{slug}.md. Blocks deploy if no rollback path exists.
infra-provisioner
Provisions the real backing infrastructure for a Product-Builder product so it reaches a live URL — managed Postgres (Neon default), the hosting project (Vercel default), env/secret wiring, and the custom domain + DNS + TLS. Pairs with devops (which does preview/staging only and refuses prod/real-domain). Runs after…
app-scaffolder
Project-scaffolding builder that stands up a working base application from the pinned stack-baseline so senior-dev implements FEATURES, not boilerplate. Creates the Next.js + TypeScript + Tailwind/shadcn skeleton, wires Drizzle + Postgres, Auth.js (to the auth-engineer contract), env template, folder structure, CI…
validator
Read-only adversarial validator. Spawned by scout to verify research findings against the actual code. Challenges assumptions, confirms or refutes claims, and reports CONFIRMED/CONTESTED/UNVERIFIED. Cannot modify files or run commands — enforced by tool restrictions.
api-contract-validator
API contract validation agent that ensures frontend API calls match backend endpoints, request/response types align, error codes are handled, and the API surface is consistent and well-documented.
code-reviewer
Systematic code review agent with two-pass review (CRITICAL then INFORMATIONAL), fix-first heuristic (auto-fix mechanical issues, ask about ambiguous ones), battle-tested pattern detection, suppression list, and evidence-backed findings with file:line citations.