aiki / rules
Cursor rule0 starsChanged 9 months agoMITView on GitHub
AI delegation rules for 4-AI collaborative development
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,144 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- analyzeSkill
- apiSkill
- checkpointingSkill
- debateSkill
- frontend-designSkill
- implementSkill
- mockupSkill
- mockup-swiftSkill
- projectSkill
- requirementsSkill
- researchSkill
- reviewSkill
- specSkill
- testSkill
The file
We split this ai-delegation.mdc 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 38
Always check for existing design docs before implementing:
- Very specific: line 45
Write requirements with Claude → docs/requirements/
≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule 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
--- description: AI delegation rules for 4-AI collaborative development globs: alwaysApply: true --- # AI Delegation Rules This project uses 4-AI collaborative development (Claude + Codex + Gemini). ## When to Delegate ### Delegate to Codex (Implementation) - New file creation (3+ files) - Large refactoring (10+ files) - Test generation - Boilerplate code generation Command: `bash scripts/delegate.sh codex implement "<task>"` ### Delegate to Gemini (Research) - Multi-source research - Technology comparisons - Trend analysis - Large codebase analysis (1M token context) Command: `bash scripts/delegate.sh gemini research "<query>"` ### Keep in Claude (Design & Review) - Architecture decisions - Requirements writing - Code review - Small edits (< 5 lines) - Security-sensitive code ## Design Documents Always check for existing design docs before implementing: - `docs/requirements/` - Requirements definitions - `docs/specs/` - UI specifications - `docs/api/` - API designs ## Workflow 1. Write requirements with Claude → `docs/requirements/` 2. Design API with Claude → `docs/api/` 3. Delegate implementation to Codex → `src/` 4. Delegate tests to Codex → `tests/` 5. Review with Claude → `docs/reviews/`
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.