Borrowing it
Nothing to install: this file belongs to archfill/tsumugi. 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/archfill/tsumugi/main/.agents/skills/drizzle-migrate-safety/SKILL.mdgit clone --depth 1 https://github.com/archfill/tsumugiWrote 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/archfill/tsumugi/drizzle-migrate-safety)<a href="https://agentmods.dev/skills/archfill/tsumugi/drizzle-migrate-safety"><img src="https://agentmods.dev/badge/skills/archfill/tsumugi/drizzle-migrate-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/archfill/tsumugi/drizzle-migrate-safety"><img src="https://agentmods.dev/badge/skills/archfill/tsumugi/drizzle-migrate-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 | $0.00082 | $0.00941 |
| Opus 5 | $0.00041 | $0.00470 |
| Sonnet 5 | $0.00016 | $0.00188 |
| Haiku 4.5 | $0.00008 | $0.00094 |
Grade A, and why
drizzle-migrate-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 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drizzle migration safety
Treat these as one migration contract:
apps/server/src/data/schema.tsapps/server/drizzle/*.sqlapps/server/drizzle/meta/*_snapshot.jsonapps/server/drizzle/meta/_journal.json- the target database's
drizzle.__drizzle_migrations
Do not declare success from drizzle-kit migrate output alone.
Establish the boundary
- Read the repository
AGENTS.mdand inspectgit status --shortbefore changing anything. - Preserve unrelated working-tree changes. Existing untracked migrations may belong to the user; inspect them before generating another migration.
- Distinguish the requested operation:
- Generate/review: repository-only changes.
- Apply: changes a confirmed database.
- Repair: changes migration history or reconciles drift.
- Never read
.env*or print credentials. Accept a caller-providedDATABASE_URLor use the documented disposable local database. - Require explicit user authorization before applying to a non-disposable database or modifying migration history manually.
Run static pre-flight checks
Before generating or applying a migration:
- Parse
_journal.jsonas JSON. - Verify
idxvalues are unique and contiguous in entry order. - Verify
whenvalues are strictly increasing in entry order. - Verify every journal
taghas a matching SQL file. - Verify generated snapshots form a valid
id/prevIdchain. Treat intentionally hand-written SQL migrations without snapshots as documented exceptions, not silent gaps. - Verify new SQL, snapshot, and journal files form a coherent set.
- Inspect the current schema and relevant diff to understand the intended state change.
Stop if ordering, numbering, tags, or generated artifacts disagree. Do not repair by guessing.
Generate a migration
Use the repository command. The Drizzle config requires DATABASE_URL even though generation should not contact the database:
DATABASE_URL=postgresql://x:x@localhost:5432/x pnpm -C apps/server db:generate
What ships with it
2 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.
- 9d ago First seen · 94 lines · 82 tokens per session scan A a6420d0442a9
drizzle-migrate-safety is a skill published in the GitHub repository archfill/tsumugi (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 82 tokens to every session and 941 once invoked, about $0.0004 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
build-with-tinybase
Scaffold, extend, and verify reactive local-first JavaScript or TypeScript applications with TinyBase. Use when choosing TinyBase for in-memory tabular or key-value state, generating an app with create-tinybase, adding schemas or UI bindings, configuring browser or database persistence, configuring MergeableStore…
tanstack-ai-memory-redis
Use when wiring redis() from @tanstack/ai-memory/redis in production — covers client setup (ioredis or node-redis via fromNodeRedis), the storage model, client-side ranking limits, and troubleshooting.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
omnigraph
Operate OmniGraph graphs and deployments. Use for .pg schemas, .gq queries, OmniGraph CLI commands, file:///s3:///az:// graph URIs, cluster.yaml, operator config, bearer-authenticated servers, graph-backed knowledge or memory, Blob values, embeddings, branches, commits, and change feeds. Apply especially before schema…
api-reference
Memoria REST API endpoints, request/response formats, auth, rate limits. Use when calling or implementing API endpoints.
architecture
Memoria codebase structure, workspace layout, key traits, database tables, config patterns, and testing conventions. Use when navigating or modifying Memoria code.