KoroqeKoroqe/claude-code-sdlc/templates/CLAUDE.md

claude-code-sdlc / templates

CLAUDE.md52 starsChanged 20 days agoMITView on GitHub

TODO: One-line description of the project. Frontend: - TODO: List frontend technologies (e.g., React 18 + TypeScript, Vue 3, etc.) Backend: - TODO: List backend technologies (e.g., Express.js + TypeScript, Django, etc.) Database: - TODO: List database and ORM (e.g., PostgreSQL + Drizzle ORM, MongoDB + Mongoose, etc.) /merge-ready reads this section to decide whether to publish after a feature passes its gates. With no section here it is a visible no-op and never invents a process. If you DO…

Reads credentials

In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- src/claude.mdCLAUDE.md
- bootstrap-featureSkill
- context-refreshSkill
- design-foundationSkill
- develop-featureSkill
- implement-sliceSkill
- merge-readySkill
- sdlc-fastSkill
- sdlc-quickSkill

The file

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

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
If you DO publish, the ordering matters more than the commands.
line 34
Distinctive:
Verify: <command proving the bump landed in every source>
line 45
Distinctive:
NEVER add "Co-Authored-By" lines to commit messages
line 92
Distinctive:
NEVER mention Claude, AI, or any AI assistant in commits
line 93
Distinctive:
Commit messages should only contain the change description
line 94
Distinctive:
No AI attribution in any form
line 95
Distinctive:
Prefer minimal diffs; no broad refactors unless requested
line 100
Distinctive:
Always commit after completing implementation — do NOT push unless explicitly requested
line 101

≈ “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

Project: TODO_PROJECT_NAME

TODO: One-line description of the project.

Tech Stack

Frontend:

TODO: List frontend technologies (e.g., React 18 + TypeScript, Vue 3, etc.)

Backend:

TODO: List backend technologies (e.g., Express.js + TypeScript, Django, etc.)

Database:

TODO: List database and ORM (e.g., PostgreSQL + Drizzle ORM, MongoDB + Mongoose, etc.)

Commands

# TODO: Fill in your project's actual commands
npm run dev      # Start development server
npm run build    # Production build
npm run test     # Run tests
npm run check    # TypeScript type checking (if applicable)

Release

<!-- OPTIONAL. Delete this section entirely if this project publishes nothing.

     /merge-ready reads this section to decide whether to publish after a
     feature passes its gates. With no section here it is a visible no-op and
     never invents a process.

     If you DO publish, the ordering matters more than the commands. Consumers
     receive whatever your distribution channel ADVERTISES — a package version,
     an image tag, a manifest field. Bump that first, verify it landed, then
     publish. Merging is not shipping: a merge that leaves the advertised
     version unchanged reaches nobody while every check stays green.

     Name the field that actually gates delivery — it is often not the one that
     looks canonical — and how to confirm consumers can now receive it.
-->

Bump: <the version field consumers' tooling compares against>
Verify: <command proving the bump landed in every source>
Publish: <command>
Confirm: <command showing what consumers now receive>

Project Structure

# TODO: Document your actual project file structure
/src/
  /routes/       # API endpoints
  /services/     # Business logic
  /models/       # Data models / schema
  /middleware/    # Auth, validation, etc.

/tests/          # Test files

/docs/
  PRD.md         # Product requirements document
  /qa/           # QA test case documentation
  /use-cases/    # Business analyst use case documents

Architecture Overview

TODO: Describe key architectural patterns:

How is data accessed? (ORM, data access layer, etc.)
How is authentication handled?
How are external services integrated?
What's the request lifecycle?

Environment Variables

# TODO: List required environment variables
DATABASE_URL          # Database connection string
# API_KEY             # External service keys

Design Guidelines

TODO: Describe visual design conventions (if applicable):

Theme / aesthetic
Typography
Component patterns

Git Commit Rules (MANDATORY)

NEVER add "Co-Authored-By" lines to commit messages
NEVER mention Claude, AI, or any AI assistant in commits
Commit messages should only contain the change description
No AI attribution in any form

Working Rules

Explore code before making changes
Prefer minimal diffs; no broad refactors unless requested
Always commit after completing implementation — do NOT push unless explicitly requested

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