cmux-skills / cmux-cli
AGENTS.md35 starsChanged 5 months agoMITView on GitHub
When asked to use or explain the cmux CLI, read the cmux-cli skill first. Use live CLI help and local source to verify syntax, then run the smallest scoped command that satisfies the task. Report the command run, the relevant result, and any remaining command the user should run manually only when the CLI cannot safely do it for them.
We split this AGENTS.md into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 3
When asked to use or explain the cmux CLI, read the cmux-cli skill first.
- Distinctive: line 7
Use live CLI help and local source to verify syntax, then run the smallest scoped command that satisfies the task.
- Very specific: line 11
Check cmux --help or cmux <command> --help before presenting exact syntax.
- Very specific: line 13
Use --json for automation.
- Distinctive: line 14
Avoid focus-changing commands unless explicitly requested.
≈ “Common” is an estimate: at least 1 in 5 of the 36,368 AGENTS.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
cmux CLI (Codex agent instructions)
When asked to use or explain the cmux CLI, read the cmux-cli skill first.
Role
Use live CLI help and local source to verify syntax, then run the smallest scoped command that satisfies the task.
Checklist
- Check
cmux --helporcmux <command> --helpbefore presenting exact syntax. - Target the caller workspace and surface unless the user names another target.
- Use
--jsonfor automation. - Avoid focus-changing commands unless explicitly requested.
Output
Report the command run, the relevant result, and any remaining command the user should run manually only when the CLI cannot safely do it for them.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 28,693 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository10 other files it gives its agents.
- skills/cmux-artifact/AGENTS.mdAGENTS.md
- cmux-artifactSkill
- cmux-browserSkill
- cmux-cliSkill
- cmux-cloudSkill
- cmux-configSkill
- cmux-freestyleSkill
- cmux-refSkill
- cmux-sidebar-builderSkill
- cmux-workspaceSkill
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.

