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.
git clone --depth 1 https://github.com/floriscornel/todo-mcpWrote 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/floriscornel/todo-mcp/development-workflow)<a href="https://agentmods.dev/rules/floriscornel/todo-mcp/development-workflow"><img src="https://agentmods.dev/badge/rules/floriscornel/todo-mcp/development-workflow/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/rules/floriscornel/todo-mcp/development-workflow"><img src="https://agentmods.dev/badge/rules/floriscornel/todo-mcp/development-workflow.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 | $0.00506 | $0.00506 |
| Opus 5.5 | $0.00202 | $0.00202 |
| Sonnet 5.5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Workflow for Todo MCP
Testing & Quality Assurance
- ALWAYS run
npm run test:coverageinstead ofnpm test- We maintain 80% coverage thresholds - Before any commit, ensure all tests pass with coverage requirements
- Run
npm run lint:fixto automatically fix code style issues - Use
npm run formatfor consistent formatting with Biome
Commit Structure
Follow conventional commits format:
feat:- New featuresfix:- Bug fixesdocs:- Documentation changestest:- Adding or updating testsrefactor:- Code refactoringchore:- Dependency updates, build changes
Examples:
feat: add priority filtering to getTasks toolfix: handle case-insensitive list names correctlytest: add edge cases for task completion
Branch & PR Workflow
You should not commit directly to the main branch! Use this flow for all requests:
- Create feature branches from
main - Branch naming:
feature/short-descriptionorfix/issue-description - Before creating PR:
- Run full test suite:
npm run test:coverage - Ensure TypeScript compiles:
npm run compile - Run linting:
npm run lint
- Run full test suite:
- PR should be reviewed by GitHub Copilot (structured for automated review)
Publication & Releases
- NEVER run
npm publishmanually - Use GitHub releases to trigger automated publishing
- Version bumps should be in separate commits following semver
- Let the GitHub Actions workflow handle NPM publication
Database Changes
- Generate migrations with
npm run db:generateafter schema changes - Test migrations with both dev and test databases
- Include migration files in commits
Code Quality Standards
- Maintain strict TypeScript configuration
- Use Zod for runtime validation
- Follow the established error handling patterns
- Keep functions focused and testable
Task discovery and management
Use the todo MCP to manage tasks in a list called floriscornel/todo-mcp.
When the user asks you to do something, start by creating a plan and tasks in the mcp.
Complete tasks one by one in the mcp until everything is finished.
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.
- 1mo ago First seen · 60 lines · 506 tokens per session scan A 739d81bfc3f7
development-workflow is a cursor rule published in the GitHub repository floriscornel/todo-mcp (2 stars, last pushed 8mo ago), licensed MIT. It adds 506 tokens to every session, about $0.0020 per session on Opus 5.5. 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 cursor rules, from other repositories
conventional-commits
Enforce Conventional Commits format for all commit messages.
git-workflow
Vollagentische Entwicklung, Auto-Commits, Commit-Konventionen.
hook-commits
Set up pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
fusebase-flow-implementation
Fusebase Flow implementation phase rules. Use when editing source code per a locked spec.
python-code-validator
Validate generated Python at every step, not once at the end.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.