mainframe
CLAUDE.md44 starsChanged 3 months agoMITView on GitHub
AI development environment for orchestrating coding agents. Use pnpm for TypeScript packages and Cargo for Rust. Read only what the current task needs. Keep information used in fewer than roughly 75% of repository tasks in conditional references, not this file.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- assistant-uiSkill
- changelog-watchSkill
- claude-protocol-debuggerSkill
- codex-protocol-debuggerSkill
- mainframe-design-systemSkill
- radix-ui-design-systemSkill
- release-downloadsSkill
- shadcnSkill
- tauri-v2Skill
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Every PR needs an appropriate changeset, including an empty one for changes without a changelog entry.
- Distinctive: line 20
Read only what the current task needs.
≈ “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
Mainframe
AI development environment for orchestrating coding agents. Use pnpm for TypeScript packages and Cargo for Rust.
packages/core-rs: Rust daemon, API, adapters, and SQLite storage.packages/ui: shared React/Tailwind UI.packages/types: shared TypeScript contracts.packages/app-tauri/src-tauri: Tauri desktop shell;packages/e2e: Playwright tests.packages/mobile: mobile app in a separate repository, mounted as a git submodule.
Working in this repository
- Reuse the assigned branch/worktree. Never commit to
main; check the current branch before committing or running reset, rebase, or force-push. - Preserve other sessions' changes. Stage only your own files by name; never restore, discard, or stash changes you did not create.
- Every PR needs an appropriate changeset, including an empty one for changes without a changelog entry.
- Fill the PR template for every PR, including CLI-created ones; keep its headings, order, and checklist, and put pipeline context in comments.
Task-specific references
Read only what the current task needs. Keep information used in fewer than roughly 75% of repository tasks in conditional references, not this file.
- Code changes, commands, and validation: development reference.
- Cargo configuration, packaging paths, or disk cleanup: Rust build constraints.
- UI styling and component conventions: Mainframe design skill.
- Module ownership and runtime boundaries: architecture.
- CLI protocol work: adapter references; use the relevant protocol-debugger skill for live behavior.
- Tracker work: issue tracker and triage labels.
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.

