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 skills add marcoguillermaz/Tierward --skill migration-auditgit clone --depth 1 https://github.com/marcoguillermaz/TierwardWrote 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/skills/marcoguillermaz/tierward/migration-audit)<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/migration-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/migration-audit/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/skills/marcoguillermaz/tierward/migration-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/migration-audit.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 | $0.00000 | $0.03709 |
| Opus 5 | $0.00000 | $0.01854 |
| Sonnet 5 | $0.00000 | $0.00742 |
| Haiku 4.5 | $0.00000 | $0.00371 |
Grade A, and why
migration-audit 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 10d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuration (adapt before first run)
Replace these placeholders:
[MIGRATIONS_PATH]- e.g.prisma/migrations/,drizzle/,supabase/migrations/,db/migrations/[APP_SOURCE_PATH]- path to application source for column-reference cross-checks (e.g.src/,app/)[STAGING_DB_URL]- optional, for Step 4 applied-migration verificationDatabase scope: checks target PostgreSQL DDL patterns. MySQL and SQLite migrations may trigger false negatives on lock-heavy DDL checks (M1, M6) that use PostgreSQL-specific syntax.
Step 0 - Target resolution
Parse $ARGUMENTS for a target: or mode: token.
| Pattern | Meaning |
|---|---|
target:file:<filename> |
Audit a single migration file (for debugging before apply) |
target:range:<from>-<to> |
Audit a numeric range of migrations (e.g. target:range:042-051) |
mode:all / no argument |
Full audit - every migration file discovered in Step 2. |
STRICT PARSING: derive target ONLY from explicit text in $ARGUMENTS. Do NOT infer from conversation context, recent blocks, or memory.
Announce: Running migration-audit - scope: [FULL | target: <resolved>] - stack: <pending detection>
Step 1 - Stack detection
Detect the migration framework in this priority order. First matching marker wins.
| Framework | Marker file(s) | Path pattern for migrations |
|---|---|---|
| Prisma | prisma/schema.prisma |
prisma/migrations/*/migration.sql |
| Drizzle | drizzle.config.ts / drizzle.config.js |
drizzle/*.sql (journal at drizzle/meta/_journal.json) |
| Supabase CLI | supabase/config.toml |
supabase/migrations/*.sql |
| Raw SQL | .sql files in migrations/ or db/migrations/ |
same |
| Rails | config/application.rb + Gemfile |
db/migrate/*.rb |
| Django | manage.py + any */migrations/*.py |
*/migrations/*.py |
| Alembic | alembic.ini |
alembic/versions/*.py |
| Flyway | flyway.conf or flyway.toml |
**/db/migration/V*__*.sql |
| golang-migrate | go.mod + migrations/*.up.sql (numeric prefix NNNNNN_name.up.sql) |
migrations/ |
| goose | go.mod + migrations/ with -- +goose Up comment in .sql, OR .go migration files |
migrations/ |
| atlas | atlas.hcl or atlas.sum |
migrations/ |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 260 lines · 0 tokens per session scan A 0e2a309120f1
migration-audit is a skill published in the GitHub repository marcoguillermaz/Tierward (4 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,709 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 2026-08-31.
Other skills, from other repositories
managing-supabase
Supabase CLI for database management, Edge Functions, migrations, and local development. Use for managing Postgres databases, deploying serverless functions, and debugging Supabase projects.
databases
Work with PostgreSQL, MongoDB, and Redis for schema design, query optimization, migrations, and data modeling. Use when designing or optimizing data layers.
sqlike
Check SQL with sqlike — deterministic static analysis (validity, anti-patterns, rewrites, index advice) and query-equivalence verification. Use whenever you write, edit, review, or rewrite a SQL query, or need to prove two queries return the same results. Requires the sqlike MCP server (@sqlike/mcp) or the sqlike CLI…
israeli-postgres-toolkit
Best practices for PostgreSQL in Israeli apps, covering Supabase patterns, Hebrew text indexing with ICU collation, shekel/NIS currency handling, Israeli date formats, and Asia/Jerusalem timezone gotchas. Use when user asks to "set up Hebrew full-text search", "handle NIS currency in Postgres", "tipul b'ivrit…
postgresql
You are working with a PostgreSQL database. Apply these best practices.
supabase-postgres-best-practices
Use when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations — including indexing, connection pooling, RLS policies, and locking. Postgres performance best practices from Supabase.