claude-life-agent / 40_SYSTEMS
CLAUDE.md2 starsChanged 4 months agoMITView on GitHub
The tools you've built and the automation that runs your life. Scripts, collectors, hooks, servers. This is the one ring that is developer-ish — but you only touch it if you want to automate. The workspace works fully without anything here. 당신이 만든 도구와 라이프 OS를 돌리는 자동화. 스크립트·수집기·훅·서버. 이 링만 개발 성격이지만, 자동화하고 싶을 때만 손대면 됩니다. 여기 아무것도 없어도 워크스페이스는 완전히 작동합니다.
- Reads credentials
In this repository9 other files it gives its agents.
- 00_SELF/CLAUDE.mdCLAUDE.md
- 10_WORK/CLAUDE.mdCLAUDE.md
- 20_DOMAINS/CLAUDE.mdCLAUDE.md
- 30_KNOWLEDGE/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
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
- Very specific: line 24
Always-on automation should say how it's kept alive (a launchd/systemd/cron entry).
- Distinctive: line 25
Prefer structured, modular code over one-off glue.
≈ “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
40_SYSTEMS — code, automation, infrastructure
The tools you've built and the automation that runs your life. Scripts, collectors, hooks, servers. This is the one ring that is developer-ish — but you only touch it if you want to automate. The workspace works fully without anything here.
당신이 만든 도구와 라이프 OS를 돌리는 자동화. 스크립트·수집기·훅·서버. 이 링만 개발 성격이지만, 자동화하고 싶을 때만 손대면 됩니다. 여기 아무것도 없어도 워크스페이스는 완전히 작동합니다.
Suggested layout
40_SYSTEMS/
├── scripts/ # one-off and utility scripts
├── automation/ # scheduled jobs, hooks, always-on services
└── data/ # local data stores the systems read/writeRules
- Secrets go in
.env, never in code or.md. (.envis gitignored.) - Note where each thing runs (this machine? a server? a schedule?).
- Always-on automation should say how it's kept alive (a launchd/systemd/cron entry).
- Prefer structured, modular code over one-off glue. Future-you maintains this.
Data placement
| Data kind | Where |
| I/O-heavy, frequent writes | fast local disk |
| large, archival, infrequent | bulk/network storage |
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.

