clawock
CLAUDE.md23 starsChanged 3 months agoMITView on GitHub
Follow AGENTS.md. It is the single instruction file for this repository; this file adds only what is specific to Claude Code. - Keep the coding-agent identity. SOUL.md, IDENTITY.md, USER.md, MEMORY.md and INVESTMENT_SOP.md configure the OpenClaw investment assistant; read them only when the task is about that assistant's behaviour. - Skill and tool routing is in TOOLS.md. Read portfolio.json only when the task needs positions or prices. - Durable memory stays in Claude Code's own store outside this repository. Do not…
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- site/llms.txtllms.txt
- daily-deep-briefSkill
- earnings-reviewSkill
- entry-gateSkill
- hk-stock-analysisSkill
- openclaw-tuneSkill
- openclaw-upgradeSkill
- portfolio-risk-reviewSkill
- portfolio-swarm-reviewSkill
- scraplingSkill
- serenity-skillSkill
- tavilySkill
- us-stock-analysisSkill
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
- Distinctive: line 3
Follow AGENTS.md. It is the single instruction file for this repository.
- Very specific: line 6
Keep the coding-agent identity.
≈ “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.md
Follow AGENTS.md. It is the single instruction file for this repository; this file adds
only what is specific to Claude Code.
- Keep the coding-agent identity.
SOUL.md,IDENTITY.md,USER.md,MEMORY.mdandINVESTMENT_SOP.mdconfigure the OpenClaw investment assistant; read them only when the task is about that assistant's behaviour. - Skill and tool routing is in
TOOLS.md. Readportfolio.jsononly when the task needs positions or prices. - Durable memory stays in Claude Code's own store outside this repository. Do not write
notes under
memory/, and do not add a second startup scan or memory pipeline on top of Claude Code's auto-memory and compaction. - OpenClaw's claude-cli backend starts Claude with
--setting-sources user, so this file is not loaded in WeChat or Telegram chat. A rule for that assistant belongs inAGENTS.mdor the file it injects.
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.

