claude-code-manager
CLAUDE.md4 starsChanged 7 days agoMITView on GitHub
Before handing a change to the user for verification: Never run make dev or make dev-guided, or otherwise launch the user's own window; the CM_AGENT copy is the only instance you start.
In this repository3 other files it gives its agents.
- verify-uiSkill
- session-harvestSkill
- session-surgerySkill
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 5
Before handing a change to the user for verification:
- Very specific: line 12
Never run make dev or make dev-guided, or otherwise launch the user's own window.
≈ “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
claude-manager
Definition of done
Before handing a change to the user for verification:
cargo test,bash scripts/tests/guided_test.sh(both run bymake test) and, for frontend changes,npm --prefix crates/app/frontend testand(cd crates/app/frontend && npx tsc --noEmit).- For anything the UI shows, use the
verify-uiskill: exercise the change in the hidden agent app (scripts/agent-app.sh,scripts/ui), look at the screenshots, checkscripts/ui logs, and fix what you find. - Report what you exercised and attach the final screenshot paths; list only what the agent app cannot check.
- Hand off to the user in the guided dev window per the
verify-uiskill ("Hand off to the user"): sandbox, prepared sessions, one step per message. Skip it for backend-only changes; for real-data-only changes give plainmake devsteps instead.
Never run make dev or make dev-guided, or otherwise launch the user's own window; the CM_AGENT copy is the only instance you start.
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.

