claude-life-agent / 00_SELF
CLAUDE.md2 starsChanged 4 months agoMITView on GitHub
This is who you are. The agent reads this hub, then opens only the one file it needs. 여기가 중심입니다. 에이전트는 이 허브를 읽고 필요한 파일 하나만 엽니다. Before generating any answer, pass context_router.md. It decides which principle layers apply to this request. This is not optional — it's what keeps the agent from answering a personal question with a work rulebook.
In this repository9 other files it gives its agents.
- 10_WORK/CLAUDE.mdCLAUDE.md
- 20_DOMAINS/CLAUDE.mdCLAUDE.md
- 30_KNOWLEDGE/CLAUDE.mdCLAUDE.md
- 40_SYSTEMS/CLAUDE.mdCLAUDE.md
- 50_LIFE/CLAUDE.mdCLAUDE.md
- 90_SHARED/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- addSkill
- sttSkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 45
Before generating any answer, pass context_router.md.
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 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
00_SELF — the center
This is who you are. The agent reads this hub, then opens only the one file it needs. 여기가 중심입니다. 에이전트는 이 허브를 읽고 필요한 파일 하나만 엽니다.
Session entry order
memory/agent_brain/MEMORY.md— core facts about the owner + environmentmemory/agent_brain/USER.md— how the owner likes to communicatememory/shared_memory.md— recent cross-session context- (on demand) the specific file the request calls for, from the tables below
Subfolders
| Folder | Holds | Key file |
identity/ | who the owner is + patterns the agent notices | character.md |
decisions/ | confirmed decisions + rejection filters | decisions_log.md |
people/ | everyone the agent should recognize | people.md |
memory/ | global / project / session memory | MEMORY_RULES.md |
| — | the answer gate | context_router.md |
identity/ — when to read what
| File | Contents | Read when |
character.md | owner's personality, thinking, taste [OWNER] | any taste / judgment / proposal call |
character_ai_mirror.md | patterns the agent has observed [AI] | reasoning about the owner's tendencies |
decisions/ — when to read what
| File | Contents | Read when |
decisions_log.md | confirmed decisions [OWNER] | before proposing anything strategic |
feedback_patterns.md | rejected patterns + rules [OWNER] | before proposing anything at all |
Source discipline
[OWNER]= the owner said it. Lives indecisions/. Highest authority.[AI]= the agent inferred it. Lives incharacter_ai_mirror.md/30_KNOWLEDGE/.- On conflict,
[OWNER]wins.
The answer gate
Before generating any answer, pass context_router.md. It decides which principle
layers apply to this request. This is not optional — it's what keeps the agent from
answering a personal question with a work rulebook.
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.

