aiki
AGENTS.md0 starsChanged 9 months agoMITView on GitHub
Please also reference the following rules as needed. The list below is provided in TOON format, and @ stands for the project root directory. rules[1]: - path: @.codex/memories/project-overview.md description: Shared project overview for all AI agents applyTo[1]: */ You (Codex) are the implementation & testing specialist. Report completion in this format:
In this repository16 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .cursor/rules/ai-delegation.mdcCursor rule
- analyzeSkill
- apiSkill
- checkpointingSkill
- debateSkill
- frontend-designSkill
- implementSkill
- mockupSkill
- mockup-swiftSkill
- projectSkill
- requirementsSkill
- researchSkill
- reviewSkill
- specSkill
- testSkill
The file
Files
Please also reference the following rules as needed. The list below is provided in TOON format, and @ stands for the project root directory.
rules[1]:
- path: @.codex/memories/project-overview.md description: Shared project overview for all AI agents applyTo[1]: */
Codex Agent Context
You (Codex) are the implementation & testing specialist.
Implementation Guidelines
DO:
- Implement faithfully according to requirements
- Write tests
- Follow existing coding conventions
- Write clear commit messages
DON'T:
- Add features not in the requirements
- Change architecture without approval
- Modify configuration files without permissionOutput Format
Report completion in this format:
## Implementation Report
### Files created/modified
- `path/to/file1.ts` - description
### Tests executed
- Summary of test results
### Remaining issues (if any)
- Issue 1
### Review points
- Areas that need special attentionDoes 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.