design-factory-app
CLAUDE.md4 starsChanged 5 months agoApache-2.0View on GitHub
Claude Code loads .claude/CLAUDE.md from the project root. This file is a thin adapter — the canonical agent contract lives in docs/agent-contract.md. Read that contract first. It defines: - The project workspace layout (projects/{slug}/) - The output channel rules (file gets code, chat gets prose) - The surgical-edit-first discipline (no full regen unless necessary) - The ::question inline protocol for discrete decisions - The language contract (match the user's language, don't translate their copy) - Anti-patterns (Lorem ipsum, decorative emoji,…
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- baseline-uiSkill
- brandkitSkill
- emil-design-engSkill
- frontend-designSkill
- frontend-guidelinesSkill
- make-interfaces-feel-betterSkill
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
- Distinctive: line 7
Read that contract first. It defines:
- Very specific: line 19
When DF spawns the Project Agent it runs via claude --prompt, NOT the full interactive harness.
≈ “Common” is an estimate: at least 1 in 5 of the 28,029 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
DesignFactory — Claude Code adapter
Claude Code loads .claude/CLAUDE.md from the project root. This file is
a thin adapter — the canonical agent contract lives in
docs/agent-contract.md.
Read that contract first. It defines:
- The project workspace layout (
projects/{slug}/) - The output channel rules (file gets code, chat gets prose)
- The surgical-edit-first discipline (no full regen unless necessary)
- The
::questioninline protocol for discrete decisions - The language contract (match the user's language, don't translate their copy)
- Anti-patterns (Lorem ipsum, decorative emoji, AI-shimmer haze, etc.)
Claude-specific notes
- When DF spawns the Project Agent it runs via
claude --prompt, NOT the full interactive harness. Tools likeAskUserQuestionandToolSearcherror on call — never use them. For decisions with discrete options, use the::questioninline protocol from the contract. - Tools you do have:
Read,Write,Edit,Bash(scoped to the workspace root),Glob,Grep. - The
::questionprotocol is rendered by the DF app as clickable buttons. Emit it inline in chat text, NOT in a code fence.
That's it. The contract in docs/agent-contract.md covers the rest.
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.

