agent-kit / templates
CLAUDE.md0 starsChanged 3 months agoMITView on GitHub
Instructions for Claude Code in this repository. Read SOURCE.md first — in every chat, before inferring from code or conversation. SOURCE.md is the persistent project record; chat history is not project memory. When you learn or change durable project facts (stack, architecture, decisions, deferrals, focus), update SOURCE.md. Append to Decisions and Deferred; rewrite Current focus when it shifts. Do not duplicate project facts in chat or in this file. Prefer SOURCE.md over this file or codebase inference when they conflict.
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/source/templates/AGENTS.mdAGENTS.md
- sourceSkill
The file
We split this CLAUDE.md into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Read SOURCE.md first — in every chat, before inferring from code or conversation.
- Distinctive: line 11
When you learn or change durable project facts (stack, architecture, decisions, deferrals, focus), update SOURCE.md.
- Distinctive: line 13
Prefer SOURCE.md over this file or codebase inference when they conflict.
- Distinctive: line 18
Prefer editing existing files over creating new ones unless the task requires it.
- Distinctive: line 19
Ask before credential-related changes.
- Distinctive: line 34
Follow AGENTS.md Boundaries when present.
≈ “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
Claude
Instructions for Claude Code in this repository.
Project context
@SOURCE.md
Read SOURCE.md first — in every chat, before inferring from code or conversation. SOURCE.md is the persistent project record; chat history is not project memory.
When you learn or change durable project facts (stack, architecture, decisions, deferrals, focus), update SOURCE.md. Append to Decisions and Deferred; rewrite Current focus when it shifts. Do not duplicate project facts in chat or in this file.
Prefer SOURCE.md over this file or codebase inference when they conflict.
Agent behavior
- Stay aligned with AGENTS.md when present for workflow, boundaries, and code-change expectations.
- Prefer editing existing files over creating new ones unless the task requires it.
- Ask before credential-related changes.
Claude-specific
<!-- Optional: slash commands, skills, MCP servers, tool permissions -->| Item | Location |
| Commands | .claude/commands/ |
| Skills | .claude/skills/ |
Boundaries
<!-- source: boundaries-default -->Follow AGENTS.md Boundaries when present.
<!-- /source: boundaries-default --><!-- Project-specific additions below -->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.