LBaC / rules
Cursor rule0 starsChanged 4 months agoMITView on GitHub
Living Blueprint-as-Code (LBaC) — Project Rules for Cursor AI
In this repository4 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- requirements-elicitationSkill
The file
Files
--- description: Living Blueprint-as-Code (LBaC) — Project Rules for Cursor AI globs: ["**/*.md", "**/*.js", "**/*.ts", "**/*.py", "**/*.java", "**/*.dart"] alwaysApply: true --- # LBaC Project Rules > **MANDATORY:** Before starting any task, read [`.agents/AGENTS.md`](../../.agents/AGENTS.md) and [`docs/LBAC.md`](../../docs/LBAC.md). ## Mandatory Workflow 0. **TELL ME THE PROJECT** — Run `docs/templates/project.prompt.md` with any AI to generate Feature Maps, user stories, roadmap, and business rules. Tracks progress in `docs/planning/tmtp_session.md`. Skip if Feature Maps already exist. 1. **READ** the relevant Feature Map in `docs/features/` (As-Is / To-Be / BDD criteria). 2. **CHECK** `docs/technical_debt.md` for related cleanup items. 3. **PLAN** — Create an Implementation Plan in `docs/implementations/` using the template. Present it and **wait for explicit approval before writing code**. 4. **CODE** in an isolated branch. 5. **VERIFY** — Complete the Verification Report in `docs/implementations/` confirming all BDD scenarios pass. ## Hard Constraints - ❌ Never create files, models, or database schemas that already exist in the project. - ❌ Never rewrite entire files — provide localized diff-style edits only. - ❌ Never skip the Implementation Plan step. - ✅ Use English for all AI-consumed files (`docs/features/`, `docs/LBAC.md`, `docs/technical_debt.md`, `.agents/AGENTS.md`). - ✅ Use local language (e.g., Español) for stakeholder files (`docs/business/`, `docs/adr/`, `docs/planning/*_qa.md`). - ✅ Format all file paths as clickable `file:///` links in responses. ## Reference → [`.agents/AGENTS.md`](../../.agents/AGENTS.md) → [`docs/LBAC.md`](../../docs/LBAC.md)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

