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 rules/nedcodes-ok/cursorrules-collection/schema-first-workflowgit clone --depth 1 https://github.com/nedcodes-ok/cursorrules-collectionWrote 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/rules/nedcodes-ok/cursorrules-collection/schema-first-workflow)<a href="https://agentmods.dev/rules/nedcodes-ok/cursorrules-collection/schema-first-workflow"><img src="https://agentmods.dev/badge/rules/nedcodes-ok/cursorrules-collection/schema-first-workflow.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 | $0.00013 | $0.00357 |
| Opus 5 | $0.00006 | $0.00179 |
| Sonnet 5 | $0.00003 | $0.00071 |
| Haiku 4.5 | $0.00001 | $0.00036 |
Grade A, and why
schema-first-workflow 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 today.
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.
What it actually says
Schema-First Development Workflow
Follow this workflow strictly. Do not skip ahead to application code.
Phase 1: Documentation
- Write a PRD (product requirements doc) before touching any code
- Define the architecture: which services, how they communicate, what owns what
- Get the docs right first. If the docs are wrong, the code will be wrong
Phase 2: Data Models
- Define all database schemas, API contracts, and type definitions
- Use your ORM's schema definition (Prisma, Drizzle, SQLAlchemy, TypeORM)
- Every entity needs: fields, types, relationships, constraints, indexes
- Write seed data that exercises all relationships and edge cases
- Validate schemas against the PRD. If they don't match, fix the schema, not the PRD
Phase 3: Schema Validation
- Run migrations. Verify they apply cleanly
- Load seed data. Verify relationships work
- Write schema-level tests: unique constraints, cascade deletes, required fields
- Do NOT proceed until the data layer is solid
Phase 4: Application Code
- Now build features against the validated schemas
- Every feature references the existing schema types. No inline type definitions
- If a feature needs a schema change, go back to Phase 2 first
- Do NOT add columns, tables, or fields ad-hoc during feature development
Schema Changes Mid-Build
- Stop current feature work
- Update the schema definition
- Write and run the migration
- Update seed data
- Verify existing tests still pass
- Then resume feature work with the updated types
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.
- today First seen · 41 lines · 13 tokens per session scan A 88f6e6d2b2b2
schema-first-workflow is a cursor rule published in the GitHub repository nedcodes-ok/cursorrules-collection (37 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 357 once invoked, about $0.0001 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 cursor rules, from other repositories
10-feature-development
Feature implementation workflow and engineering mindset.
11-template-conventions
Reusable building blocks shipped with this template - use them instead of writing new ones.
03-ui
UI, layout, theming and localization standards.
12-new-project
Workflow for starting a new app from this template - rebranding, identity, cleanup and first feature.
13-updating-project
Workflow for updating an existing project - dependency and SDK upgrades, migrations, refactors, bug fixes.
01-tech-stack
Android tech stack and project standards.