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 mgiovani/cc-arsenal --skill db-migrategit clone --depth 1 https://github.com/mgiovani/cc-arsenalWrote 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/mgiovani/cc-arsenal/db-migrate)<a href="https://agentmods.dev/skills/mgiovani/cc-arsenal/db-migrate"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/db-migrate.svg" alt="Measured on agentmods" 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 | $0.00189 | $0.01825 |
| Opus 5 | $0.00095 | $0.00912 |
| Sonnet 5 | $0.00038 | $0.00365 |
| Haiku 4.5 | $0.00019 | $0.00183 |
Grade A, and why
db-migrate 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 7d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DB Migrate
Create, check the status of, and validate database migrations across any framework. Auto-detects the migration tool from project marker files and drives its native CLI: this skill never invents a migration command.
Ground rules
- Detect before acting. Scan for marker files (Phase 1) before running anything.
- Never invent commands. Only run commands from the detection table in references/framework-commands.md or found in the project's own docs/scripts.
- Flag destructive operations and never auto-fix them.
DROP TABLE,DROP COLUMN,TRUNCATE,DELETE FROMget a warning and require the user's explicit go-ahead: this skill reports, it does not silently rewrite or apply a migration containing one. - Report only what a command actually produced. File paths, migration names, and status output in the final summary must come from
ls/cat/the framework CLI's own output, never guessed or reconstructed from memory.
Workflow
Phase 1: Detect framework
ls alembic.ini prisma/schema.prisma knexfile.* flyway.conf flyway.toml \
db/migrate/ manage.py atlas.hcl typeorm.config.* ormconfig.* \
liquibase.properties 2>/dev/null
Also check package.json (knex, db-migrate, sequelize, typeorm), pyproject.toml/requirements.txt (alembic, sqlalchemy), and Gemfile (activerecord) for framework dependencies when no marker file is conclusive.
If multiple frameworks are detected (e.g. a monorepo with both a Python and a Node service), ask the user which one they mean. If none is detected, ask the user to name it: don't guess a command for a framework you can't confirm.
Full detection table and per-framework commands: references/framework-commands.md, load it once the framework is identified, before running any create/status/rollback command.
Phase 2: Parse the request
Determine the operation from $ARGUMENTS or the user's phrasing:
What ships with it
3 files 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.
- 7d ago First seen · 146 lines · 189 tokens per session scan A 61521edb9a7c
db-migrate is a skill published in the GitHub repository mgiovani/cc-arsenal (7 stars, last pushed 7d ago), licensed MIT. It adds 189 tokens to every session and 1,825 once invoked, about $0.0009 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 skills, from other repositories
postgres
Operate PostgreSQL instances safely: configuration review, index and query-plan analysis, vacuum and bloat management, WAL archiving and point-in-time recovery, replication and failover, extensions, major-version upgrades, and evidence-based diagnostics with the bundled read-only pgdiag script. Use when running or…
supabase
Use this skill when developing applications with Supabase, running the Supabase CLI, designing migrations and RLS policies, testing database behavior, generating client types, deploying the official self-hosted Docker stack, or administering its Postgres, Auth, Storage, Realtime, Functions, API gateway, backups…
db-query
Query the JHT SQLite DB (positions, applications, stats). Use it whenever you need position status, per-agent queues, scores, match rate, or record counts. DB path from $JHTDB, fallback /jhthome/jobs.db.
cv-disk-audit
Healthcheck periodico (Dottore) per riconciliare CV su disk e cvpdfpath nel DB. Identifica orfani (file su disk senza riga DB) e ghost (riga DB con cvpdfpath che punta a file inesistente). Notifica il Capitano sui mismatch così l'utente non perde top PASS invisibili e non vede "CV da scrivere" per CV già scritti.
db-insert
Insert NEW records into the JHT DB (positions / scores / applications / companies / positionhighlights). Use it ONLY when an agent needs to create a record — Scout for positions, Analyst for companies and highlights, Scorer for scores, Writer for applications. Never blind-overwrite — for updates use db-update.
database
A database design and migration guide written in Korean. It covers table structure, naming conventions, common columns, indexes, foreign keys, and versioned migration files.