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 Hainrixz/claude-db --skill db-migration-safetygit clone --depth 1 https://github.com/Hainrixz/claude-dbWrote 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/hainrixz/claude-db/db-migration-safety)<a href="https://agentmods.dev/skills/hainrixz/claude-db/db-migration-safety"><img src="https://agentmods.dev/badge/skills/hainrixz/claude-db/db-migration-safety/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/hainrixz/claude-db/db-migration-safety"><img src="https://agentmods.dev/badge/skills/hainrixz/claude-db/db-migration-safety.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 | $0.00124 | $0.01417 |
| Opus 5 | $0.00062 | $0.00709 |
| Sonnet 5 | $0.00025 | $0.00283 |
| Haiku 4.5 | $0.00012 | $0.00142 |
Grade A, and why
db-migration-safety 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
db-migration-safety (M22) — the migration lint contract
M22 lints a candidate migration as a static artifact before execution. It is the contract the migration-safety auditor and the db-migration-writer agent both honor. Feeds Performance & Scale (Almacenamiento/operability category). A destructive irreversible migration is the sev-5 cap on the performance axis.
What it checks (the lint contract)
- Reversibility — a usable
down/rollback exists, or the change follows expand-contract (add-new → backfill → switch → drop-old in separate deploys). A one-shot destructive step with no down is the highest-severity finding here. - Lock level — does the statement take a blocking lock on a hot table? In Postgres: adding a column
with a volatile default (pre-11),
ALTER COLUMN TYPE, adding aCHECK/FK withoutNOT VALID, non-CONCURRENTLYindex creation all takeACCESS EXCLUSIVE/ block writes. PreferCREATE INDEX CONCURRENTLY,ADD CONSTRAINT ... NOT VALIDthenVALIDATE CONSTRAINT. - Table rewrite — changes that force a full-table rewrite (certain
ALTER COLUMN TYPE, adding aNOT NULLcolumn with a volatile default on old engines) → slow + long lock on large tables. - Destructive ops —
DROP COLUMN,DROP TABLE,TRUNCATE,DROP NOT NULLreversals, dropping a column still read by deployed code. Destructive + irreversible = sev 5 (caps performance). - NOT NULL without default added to a populated table → fails or locks; require a backfill plan.
- Enum mutation — the durable concern: enum values cannot be removed or reordered (removal is
unsupported; renaming/reordering breaks dependents), so a changing set should be a lookup table,
not a native enum.
ALTER TYPE ... ADD VALUEis append-only and runs in a transaction on PG12+ (only older PG forbade it mid-txn). Flag enum changes; suggest lookup tables. - Schema drift — the declarative artifact (schema.prisma / structure.sql / snapshot) disagrees with the migration history (a column exists in one but not the other) → directional warn.
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 · 75 lines · 124 tokens per session scan A 964b78f6bddb
db-migration-safety is a skill published in the GitHub repository Hainrixz/claude-db (19 stars, last pushed 2mo ago), licensed MIT. It adds 124 tokens to every session and 1,417 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
malloy-dashboards
Build or modify a Malloy Publisher dashboard, a tagged .malloy file in a package's dashboards/ directory, with auto-rendered filter controls, a grid layout, and # drill click-through. Use when the user asks for a dashboard, a filterable operational view, or drill-through between views, and no code is wanted.
malloy-gotchas-modeling
Common Malloy modeling mistakes and how to avoid them. Read BEFORE writing source definitions, dimensions, measures, or joins. Covers reserved words, NULL checks, date functions, type casts, field management (extend except/accept/rename vs include public/internal/private), and query-based source gotchas.
malloy-model
Build Malloy semantic models with base source and joined source files. Use when creating or modifying .malloy files, user asks to "create a malloy model", "add dimensions", "add measures", "create a source", or any Malloy model authoring task.
malloy-charts
Chart selection guidance and renderer reference for Malloy views. Use when choosing visualization types, adding chart annotations, user asks "what chart should I use", "how should I visualize this", or when deciding between barchart, linechart, scatterchart, etc.
malloy-materialization
Add and debug Malloy Persistence materializations in a package - persist an expensive source so queries read a pre-built table. Read this whenever the user wants to materialize a source, add a persist annotation, speed up a slow source, or asks why a persist source isn't building.
malloy-model-as-you-go
After answering a data question, write down what the answer assumed so the next reader can trust the number. A field with a.