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 agentmods add skills/christopherlouet/claude-base/dev-prismanpx skills add christopherlouet/claude-base --skill dev-prismagit clone --depth 1 https://github.com/christopherlouet/claude-baseWrote 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/christopherlouet/claude-base/dev-prisma)<a href="https://agentmods.dev/skills/christopherlouet/claude-base/dev-prisma"><img src="https://agentmods.dev/badge/skills/christopherlouet/claude-base/dev-prisma.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 | $0.00051 | $0.00636 |
| Opus 5 | $0.00026 | $0.00318 |
| Sonnet 5 | $0.00010 | $0.00127 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
dev-prisma 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 yesterday.
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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prisma ORM (pointer)
Prisma publishes the canonical agent skill at prisma/skills — maintained by the Prisma team, in sync with v7 (ESM-only, driver adapters, prisma.config.ts). The vendor reference stays current with every release; the prior foundation skill (418 lines) drifted on each Prisma version bump.
Delegate to the vendor skill
# Prisma's preferred path (verify on their README):
npx skills add prisma/skills
# Fallback — clone and copy:
git clone --depth 1 https://github.com/prisma/skills ~/dev/vendor-skills/prisma
# Skill content lives in CLAUDE.md / AGENTS.md per their convention.
Recipe entry: docs/recipes/recommended-vendor-skills.md §"Prisma — prisma/skills". Reduction rationale: specs/foundation-positioning-review/spec.md Wave 1.
Foundation-unique angle preserved: cross-cutting discipline
The vendor covers the Prisma API surface. The foundation enforces version-agnostic conventions that survive across releases:
- Security: never
select: { passwordHash: true }or any sensitive column without explicit need; default toselectoverincludefor security + perf — cross-ref.claude/rules/security.md. - TDD with a real DB: integration tests hit a real test database (Docker Compose pattern), never a Prisma mock — cross-ref the
dev-tddskill. - Postgres interop: if the stack uses Supabase, Prisma operates against the same Postgres — cross-ref the
dev-supabaseskill (Supabase RLS coexists with Prisma queries).
Foundation rules preserved
- NEVER use
prisma migrate devin production. Alwaysprisma migrate deploy. prisma generateMUST run after every schema change. Add it to the CI build step.- Singleton PrismaClient (HMR-safe
globalThispattern in dev) — avoid connection leaks. - YOU MUST add an index on every foreign key and on every column in frequent WHERE clauses.
- YOU MUST use
selectinstead ofincludewhen you know the fields (security + perf). - NEVER commit
.envwithDATABASE_URL. Always.env.examplewith placeholders. - NEVER rename a field in one migration. Two steps: add new column → backfill → remove old column (avoids prod downtime).
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.
- yesterday First seen · 49 lines · 51 tokens per session scan A ff221eca760e
dev-prisma is a skill published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 636 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
db-migration-safety
Review database migrations for safety: locking, rollback, data loss, and performance risks. Triggers on "review migration", "check migration", "migration safety".
postgres
Use this skill for any PostgreSQL database work — table design, indexing, data types, constraints, extensions (pgvector, PostGIS, TimescaleDB), search, and migrations. Trigger when user asks to: Design or modify PostgreSQL tables, schemas, or data models Choose data types, constraints, indexes, or partitioning…
transactional-patterns
Use when working with @Transactional, multi-step database operations, distributed transactions, or any code that needs atomicity guarantees. Covers propagation rules, isolation levels, read-only optimization, and common pitfalls.
postgres-idioms
PostgreSQL best practices — schema design, query performance, indexing, connection management, RLS, concurrency, monitoring, and migrations. Load when writing SQL, designing schemas, or optimizing PostgreSQL queries.
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
drizzle-orm
Use when modeling data or querying with Drizzle ORM in TypeScript — pgTable schema in .ts, type-safe select/insert/relational queries, drizzle-kit migrations. NOT Prisma Client or schema.prisma (that is prisma-orm), NOT ORM-agnostic migration strategy (that is db-migrations), NOT Postgres engine tuning or EXPLAIN…