07-development-workflow

Project rules for developing a TypeScript codebase that uses modern modules and strict type checking.

In plain words
What is it for?
Use them when changing the project to follow its required commands, write tests, run type checks, keep concerns separate, and maintain MCP compliance.
Why use it?
They give contributors a shared workflow for building, testing, formatting, linting, documenting, and checking code before committing it.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/gargoyle92/agentify-mcp/07-development-workflow
Clone the repo
git clone --depth 1 https://github.com/gargoyle92/agentify-mcp

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 2,171 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02171
Opus 5 $0.00000 $0.01086
Sonnet 5 $0.00000 $0.00434
Haiku 4.5 $0.00000 $0.00217

Measured yesterday against content hash c1f1fea8e5b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

07-development-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 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.

.cursor/rules/07-development-workflow.mdc · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

07-Development-Workflow

Development Environment Setup

The project uses TypeScript with ESNext modules and strict type checking as configured in tsconfig.json.

Required Tools and Scripts

  • Development: npm run dev - Uses tsx for hot reloading
  • Building: npm run build - TypeScript compilation
  • Testing: npm run test - Jest test runner
  • Linting: npm run lint - ESLint with TypeScript rules
  • Formatting: npm run format - Prettier code formatting

CRITICAL DEVELOPMENT RULES - MUST FOLLOW

✅ ALWAYS DO:

  1. Run type checking: Use npm run typecheck before committing
  2. Follow code formatting: Use npm run format to maintain consistency
  3. Write tests first: Implement tests alongside or before implementation
  4. Validate MCP compliance: Test all tools and resources against MCP standards
  5. Update documentation: Keep README and code comments current

❌ NEVER DO:

  1. Commit without linting: Never commit code that fails ESLint checks
  2. Skip type checking: Never ignore TypeScript errors or warnings
  3. Commit failing tests: All tests must pass before committing
  4. Mix concerns: Keep tools, resources, and server logic separate
  5. Ignore deprecation warnings: Address all deprecation warnings immediately

Pre-commit Checklist

✅ REQUIRED Before Every Commit:

# 1. Format code
npm run format

# 2. Lint and fix issues
npm run lint:fix

# 3. Type check
npm run typecheck

# 4. Run all tests
npm run test

# 5. Check coverage
npm run test:coverage

# 6. Build verification
npm run build

Git Commit Standards

# Use conventional commit format
feat: add new tool for Gemini CLI client status
fix: resolve session cleanup memory leak
docs: update MCP protocol documentation
test: add integration tests for state tracker
refactor: extract common client validation logic

Code Review Guidelines

✅ REVIEW CHECKLIST:

  1. Type Safety: All types properly defined and used
  2. Error Handling: Proper try-catch blocks and error emission
  3. Logging: Appropriate use of Logger instead of console
  4. Testing: Adequate test coverage for new functionality
  5. MCP Compliance: Tools and resources follow MCP protocol
  6. Documentation: Code is self-documenting with clear comments
  7. Performance: No obvious performance bottlenecks
  8. Security: No sensitive data exposure in logs

Read the full file on GitHub · 322 lines

Changes

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.

  1. yesterday First seen · 322 lines · 0 tokens per session scan A c1f1fea8e5b6

Subscribe to this mod's changes

07-development-workflow is a cursor rule published in the GitHub repository gargoyle92/agentify-mcp (1 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,171 tokens. 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.