vibeusage
CLAUDE.md130 starsChanged 7 months agoMITView on GitHub
This project uses OpenSpec for spec-driven development. Before making significant changes: Create a proposal (openspec/changes/<id>/) for: Skip proposals for:
1 other project uses a version of this.
Adopted by
Most recently taken up by
- victorGPT/vibescoreword for word, first seen Oct 9, 2026
Other versions1 project uses a version of this.
Word for word · 1
- victorGPT/vibescore★ 130100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- openspec/AGENTS.mdAGENTS.md
- find-skillsSkill
- insforge-cliSkill
- insforgeSkill
- vibeusage-designSkill
- frontend-ui-functionalSkill
The file
We split this CLAUDE.md into the rules it gives an agent
7 rules. About 0 are common, 1 is distinctive, and 6 are 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.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
Read openspec/project.md for project conventions
- Very specific: line 8
Check openspec/AGENTS.md for the full OpenSpec workflow
- Very specific: line 9
Run openspec list to see active changes
- Very specific: line 10
Run openspec list --specs to see existing specifications
- Very specific: line 14
Create a proposal (openspec/changes/<id>/) for:
- Very specific: line 70
All user-facing text managed in dashboard/src/content/copy.csv
- Distinctive: line 72
Use UTC for all timestamps
≈ “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.
Files
Project Guidelines for Claude Code
OpenSpec Workflow
This project uses OpenSpec for spec-driven development. Before making significant changes:
- Read
openspec/project.mdfor project conventions - Check
openspec/AGENTS.mdfor the full OpenSpec workflow - Run
openspec listto see active changes - Run
openspec list --specsto see existing specifications
When to Create a Proposal
Create a proposal (openspec/changes/<id>/) for:
- New features or capabilities
- Breaking changes (API, schema)
- Architecture or pattern changes
- Security-related changes
Skip proposals for:
- Bug fixes (restore intended behavior)
- Typos, formatting, comments
- Dependency updates (non-breaking)
OpenSpec Commands
openspec list # List active changes
openspec list --specs # List specifications
openspec show <item> # View change or spec details
openspec validate <id> --strict # Validate a change proposal
openspec archive <id> --yes # Archive after deploymentProposal Structure
openspec/changes/<change-id>/
├── proposal.md # Why and what
├── tasks.md # Implementation checklist
├── design.md # Technical decisions (optional)
└── specs/
└── <capability>/
└── spec.md # ADDED/MODIFIED/REMOVED requirementsProject Structure
src/- CLI source code (Node.js, CommonJS)bin/- CLI entry pointsdashboard/- React dashboard (Vite)insforge-src/- Backend Edge Functions sourceinsforge-functions/- Built backend functions (generated)openspec/- Specifications and change proposals
Key Commands
npm test # Run tests
npm run build:insforge # Build backend functions
npm run dashboard:dev # Start dashboard dev server
npm run validate:copy # Validate copy registryConventions
- Platform: macOS-first
- All user-facing text managed in
dashboard/src/content/copy.csv - Token data only - never store or upload conversation content
- Use UTC for all timestamps
- Half-hour buckets for aggregation
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.

