agentos-foundation
CLAUDE.md0 starsChanged 2 months agoMITView on GitHub
Read AGENTS.md, then START-HERE.md. This repository is a public instruction/template foundation for a user's own private local workspace. Use the relevant project playbooks in .agents/skills/ by reading their SKILL.md directly; do not assume they were installed into a client-specific native skill registry. For personal subscription use, keep authentication in the unmodified native Claude Code runtime and Anthropic's own login flow. Do not collect or proxy subscription tokens. See docs/providers.md for researched distinctions across Claude, Codex, Grok and Cursor, and for…
In this repository39 other files it gives its agents.
- AGENTS.mdAGENTS.md
- adaptSkill
- agentos-builderSkill
- agentos-verifySkill
- agent-runtimeSkill
- animateSkill
- application-integrationSkill
- arms-architectureSkill
- arrangeSkill
- auditSkill
- bolderSkill
- capability-policySkill
- capture-to-planSkill
- clarifySkill
- colorizeSkill
- composer-and-voiceSkill
- composer-designSkill
- critiqueSkill
- delightSkill
- distillSkill
- evidence-reviewSkill
- extractSkill
- frontend-designSkill
- hardenSkill
- memory-routingSkill
- normalizeSkill
- onboardSkill
- optimizeSkill
- overdriveSkill
- polishSkill
- provider-compatibilitySkill
- quieterSkill
- routine-engineeringSkill
- skill-authoringSkill
- spatial-designSkill
- teach-impeccableSkill
- typesetSkill
- widget-contractSkill
- custom-workflowSkill
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 3
Read AGENTS.md, then START-HERE.md.
- Very specific: line 7
Read docs/design/spatial.md before building the workspace and .agents/skills/composer-design/SKILL.md before building its composer.
≈ “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
Build your own AgentOS
Read AGENTS.md, then START-HERE.md. This repository is a public instruction/template foundation for a user's own private local workspace. Use the relevant project playbooks in .agents/skills/ by reading their SKILL.md directly; do not assume they were installed into a client-specific native skill registry.
For personal subscription use, keep authentication in the unmodified native Claude Code runtime and Anthropic's own login flow. Do not collect or proxy subscription tokens. See docs/providers.md for researched distinctions across Claude, Codex, Grok and Cursor, and for separate API endpoint support.
Read docs/design/spatial.md before building the workspace and .agents/skills/composer-design/SKILL.md before building its composer. Inspect the actual domain and capabilities, then complete one source-to-reviewed-result workflow. Keep private runtime data out of this public repository.
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.