agentleFS
Sign inStart free
dwsilvardwsilvar/LBaC/CLAUDE.md

LBaC

CLAUDE.md0 starsChanged 4 months agoMITView on GitHub

MANDATORY FIRST STEP: Read .agents/AGENTS.md and docs/LBAC.md before starting any task in this repository. Purpose: A methodology and repository template that turns product specs, architectural decisions, roadmaps, and QA strategies into active, versioned code documents. Acts as the Single Source of Truth (SSoT) for human developers and AI coding agents. → .agents/AGENTS.md → docs/LBAC.md

The file

We split this CLAUDE.md into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not create models, screens, classes, or database tables without verifying they don't already exist.

    line 27
  2. Very specific:

    Always format file paths as clickable links using the file:/// scheme.

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

Claude — Project Instructions (CLAUDE.md)

MANDATORY FIRST STEP: Read .agents/AGENTS.md and docs/LBAC.md before starting any task in this repository.

Project: Living Blueprint-as-Code (LBaC) — Template Repository

Purpose: A methodology and repository template that turns product specs, architectural decisions, roadmaps, and QA strategies into active, versioned code documents. Acts as the Single Source of Truth (SSoT) for human developers and AI coding agents.

Mandatory Workflow

0. TELL ME THE PROJECT → 1. READ SPECS → 2. PLAN FIRST → 3. WRITE CODE → 4. VERIFY BDD
  docs/templates/         docs/features/   docs/implementations/   branch     Verification Report
  1. Tell Me the Project — Run docs/templates/project.prompt.md with any AI to generate Feature Maps, user stories, roadmap, and business rules from scratch. Skip if Feature Maps already exist.
  2. Read the relevant Feature Map in docs/features/ to understand As-Is and To-Be.
  3. Check technical debt in docs/technical_debt.md.
  4. Create an Implementation Plan in docs/implementations/ using the template. Wait for explicit human approval.
  5. Implement in an isolated branch.
  6. Complete the Verification Report confirming all BDD scenarios pass.

Key Constraints

  • Do not create models, screens, classes, or database tables without verifying they don't already exist.
  • Provide localized edits only — never rewrite entire files.
  • Respect the documentation language policy: English for AI files, local language for business/stakeholder files.
  • Always format file paths as clickable links using the file:/// scheme.

Full Rules

→ .agents/AGENTS.md
→ docs/LBAC.md

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free