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 pledgeandgrow/pledge-skills --skill prismagit clone --depth 1 https://github.com/pledgeandgrow/pledge-skillsWrote 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/pledgeandgrow/pledge-skills/prisma)<a href="https://agentmods.dev/skills/pledgeandgrow/pledge-skills/prisma"><img src="https://agentmods.dev/badge/skills/pledgeandgrow/pledge-skills/prisma/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/pledgeandgrow/pledge-skills/prisma"><img src="https://agentmods.dev/badge/skills/pledgeandgrow/pledge-skills/prisma.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 | $0.00030 | $0.07311 |
| Opus 5 | $0.00015 | $0.03655 |
| Sonnet 5 | $0.00006 | $0.01462 |
| Haiku 4.5 | $0.00003 | $0.00731 |
Grade A, and why
prisma-docs 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 — 560 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prisma ORM Documentation Skill
Prisma changes frequently — verify against the changelog and current docs before implementing. Do not rely on training data for Prisma features. APIs, configuration, and conventions can change between versions.
Metadata
- Official Docs: https://www.prisma.io/docs
- LLMs Index: https://www.prisma.io/docs/llms.txt
- Changelog: https://www.prisma.io/changelog.md
- Version: 7.x (current), 6.x (legacy)
- Runtime: Node.js, Bun, Deno
- Supported Databases: PostgreSQL, MySQL, SQLite, MongoDB, SQL Server, CockroachDB, PlanetScale, Turso (libSQL), Cloudflare D1
- GitHub: https://github.com/prisma/prisma
Quick Reference
| File | Topics |
|---|---|
| getting-started.md | Prisma ORM overview, installation, quickstart (PostgreSQL, MySQL, SQLite, MongoDB, SQL Server, CockroachDB, PlanetScale, Prisma Postgres), prisma.config.ts, Prisma schema overview, data sources, generators, models, fields, attributes, enums, relations (1-1, 1-n, m-n, self), referential actions, indexes, views, composite types, introspection, multi-schema, environment variables, editor setup, supported databases, connection URLs, connection management, connection pooling, PgBouncer, driver adapters |
| api.md | Prisma Client CRUD (create, createMany, createManyAndReturn, findUnique, findFirst, findMany, update, updateMany, updateManyAndReturn, upsert, delete, deleteMany), filtering (where, OR, AND, NOT, relation filters), sorting (orderBy, case-insensitive, sort by relation, null ordering), pagination (offset, cursor), select/include, relation queries (nested reads, nested writes, fluent API, connect/disconnect, connectOrCreate), aggregation/grouping/count/distinct, transactions ($transaction array, interactive, nested writes, batch, isolation levels), raw SQL ($queryRaw, $executeRaw, $executeRawUnsafe, TypedSQL), client extensions (client, model, query, result, shared), special fields (JSON, scalar lists, composite IDs, null/undefined, omit), Prisma CLI commands (init, generate, migrate dev/deploy/status/reset/resolve/diff, db pull/push/execute/seed, format, validate, version, studio, debug), Prisma Studio, error reference |
| guides.md | Deployment (Vercel, Netlify, AWS Lambda, Azure Functions, Cloudflare Workers/Pages, Deno Deploy, Fly.io, Heroku, Railway, Render, Koyeb, Sevalla, Docker, Turborepo, pnpm/bun workspaces), frameworks (Next.js, Nuxt, SvelteKit, Astro, Hono, NestJS, Elysia, SolidStart, TanStack Start, React Router 7), authentication (Auth.js, Better Auth, Clerk), integrations (AI SDK, Datadog, GitHub Actions, Permit.io, pgfence, Shopify, Vercel deployment, embedded Studio), database guides (multiple databases, schema changes in teams, data migration expand-and-contract), migrations (baselining, customizing, squashing, patching, generating down migrations, native DB functions/types, unsupported features, prototyping with db push, shadow database, troubleshooting), testing (unit, integration), best practices, comparisons (Drizzle, Mongoose, Sequelize, TypeORM), upgrade guides (v1-v7), Prisma Postgres (setup, local dev, connection pooling, backups, extensions, serverless driver, IaC with Terraform/Pulumi/Alchemy), Prisma Compute, AI tools (MCP server, Cursor, Windsurf, Copilot, Codex, ChatGPT, Tabnine, agent skills), troubleshooting (bundler issues, Next.js, Nuxt, TypeScript performance, GraphQL autocompletion, raw SQL comparisons, check constraints, many-to-many relations) |
| prisma-next.md | Prisma Next — next-gen ORM rewrite, data contracts, PSL and TypeScript schema authoring, fundamentals (reading/writing data, relations, transactions, advanced queries), migrations, middleware, extensions, CLI reference, framework guides, data modeling |
| platform.md | Prisma Console, Management API (OAuth 2.0, service tokens, TypeScript SDK), Prisma Compute (projects, branches, apps, deployments, environment variables, GitHub integration, domain management, CLI), Query Insights (slow query analysis, AI suggestions), error codes, known limitations, FAQ |
| orm-supplement.md | API patterns (REST, GraphQL, fullstack), data modeling concepts, supported databases overview, schema location (multi-file), table inheritance (STI vs MTI), external tables (Preview), unsupported database features, troubleshooting relations, read replicas, debugging, ORM releases and maturity levels, dev environment, SafeQL, Permit RBAC extension, AWS deployment caveats, shared extensions and examples |
| postgres-ai-supplement.md | Prisma Postgres FAQ (pricing, operations, caching, connection pooling limits, Query Insights), troubleshooting, error reference (P6009, P6004, P6008, P5011), import from existing database, create-db CLI, best Postgres for AI apps (pooling, RAG caching, edge driver, pgvector, MCP), AI prompt for Next.js + Prisma v7, AI tutorial (TweetSmith with Ollama) |
| prisma-next-reference-supplement.md | Prisma Next detailed reference — ORM client methods (first, all, count, select, include, where, orderBy, take, skip, cursor, variant, create, createAll, update, updateAll, delete, deleteAll, upsert, aggregate, groupBy, having), filter operators (PostgreSQL and MongoDB), field update operations, AsyncIterableResult, SQL query builder (select, joins, grouped queries, raw SQL, build, ResultType), pipeline builder (match, group, sort, lookup, replaceRoot, count, sortByCount, updateMany, out, merge, rawCommand), raw queries (PostgreSQL raw SQL, MongoDB raw commands), transactions and runtime (client lifecycle, db.transaction, withTransaction, manual control, prepared statements, execution options, telemetry), data modeling (relational, MongoDB, embed vs reference, polymorphic), contract authoring (capabilities, artifacts, content hashes), middleware (five hooks, authoring custom, built-in budgets/cache/lints), migrations (workflow, graph, rollbacks, recovery) |
What ships with it
8 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 · 560 lines · 30 tokens per session scan A ddeab6088fe6
prisma-docs is a skill published in the GitHub repository pledgeandgrow/pledge-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 7,311 once invoked, about $0.0002 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
prisma-orm
Use when modeling data or writing type-safe queries with Prisma ORM in TypeScript — schema.prisma, prisma.config.ts, the generated Prisma Client, and Prisma Migrate, including the v6 to v7 upgrade. NOT schema-as-TS with a SQL builder (that is drizzle-orm), NOT ORM-agnostic zero-downtime migration (that is…
triage-contributor-pr
Triage open pull requests from external contributors to prisma/prisma and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming contributor PRs, to decide whether a fork PR is safe to run CI on, to check whether a PR is in scope for its version…
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
review-triage-phase
Produces canonical review actions from fetched review state and renders action markdown. Use when the user wants only triage/action-planning for the review-framework workflow.
no-bare-casts
Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.
Drizzle ORM Testing
Testing patterns for Drizzle ORM covering migration testing, query builder testing, transaction testing, and database integration testing with PostgreSQL, SQLite, and MySQL.