agentleFS
Sign inStart free
roronoazoroshao369roronoazoroshao369/vibe-coding-os/CLAUDE.md

vibe-coding-os

CLAUDE.md1 starsChanged 5 months agoMITView on GitHub

Quick start: git clone, then cp CLAUDE.md commands/ skills/ templates/ /your-project/. See docs/QUICKSTART.md. Prime directive: Build software quickly while preserving clarity, correctness, verification, and attribution hygiene. Intent → Spec → Plan → Implement → Test → Review → Memory → Merge skills/*/*/SKILL.md for procedures, commands/*.md for prompts, templates/*.md for specs/plans/tasks/reviews/memory. Combine as needed; don't over-orchestrate simple work. Coding before understanding, scope creep, large rewrites without plan, faking tests, hiding uncertainty, storing secrets, copying content without attribution. npm run validate for…

The file

Create a free account to mount
Files
CLAUDE.md

Claude Code Instructions — Vibe Coding OS

Quick start: git clone, then cp CLAUDE.md commands/ skills/ templates/ /your-project/. See docs/QUICKSTART.md.

Prime directive: Build software quickly while preserving clarity, correctness, verification, and attribution hygiene.

Workflow

Intent → Spec → Plan → Implement → Test → Review → Memory → Merge

LayerWhenKey commands
DefaultEvery sessionall vibe-*
SuperpowersBrainstorming, explorationvibe-brainstorm, vibe-flow
Spec-DrivenMulti-file featuresvibe-spec → vibe-plan → vibe-tasks
Real EngineeringDebugging, legacy codevibe-diagnose, TDD

Quick reference

CommandWhen
vibe-specRequirements or edge cases matter
vibe-planSpec → file-oriented plan
vibe-implementFocused edits
vibe-reviewBefore task-complete
vibe-mergeFinal readiness

Skills & commands

skills/*/*/SKILL.md for procedures, commands/*.md for prompts, templates/*.md for specs/plans/tasks/reviews/memory. Combine as needed; don't over-orchestrate simple work.

Anti-patterns

Coding before understanding, scope creep, large rewrites without plan, faking tests, hiding uncertainty, storing secrets, copying content without attribution.

Verification

npm run validate for structure. Targeted tests first, broader checks when feasible. Report honestly: passed, failed, or not run (with reason). Merge-ready: diff reviewed, criteria satisfied, verification clear, attribution clean.

On-demand deep dives

  • Superpowers: docs/workflows/superpowers-inspired-workflow.md
  • Spec-driven: commands/vibe-spec.md
  • Memory rules: skills/memory/memory-ingestion/SKILL.md
  • Reference intelligence: docs/workflows/runtime-mcp-server.md
  • Proficiency levels: commands/vibe-proficiency.md

Ghi chú tiếng Việt

Làm theo lớp spec-driven: constitution → specify → plan → tasks → implement, "cái gì" trước "làm thế nào". Coi github/spec-kit là cảm hứng, không vendor. Bộ nhớ: nạp vừa đủ, lọc dữ liệu nhạy cảm, ghi rõ trích dẫn.

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