claude-toolkit / rules
Cursor rule4 starsChanged 3 months agoMITView on GitHub
agents-workbench workflow — worktree-based development with branch detection
We split this workbench.mdc into the rules it gives an agent
8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Before editing any source code, check: git branch --show-current
- Very specific: line 9
If output is agents-workbench → source code is READ-ONLY.
- Very specific: line 10
If inside a .worktrees/ path → you are in a worktree.
- Distinctive: line 11
If on any other branch → normal development.
- Very specific: line 20
Create from remote ref: git worktree add .worktrees/<name> -b <branch> "$BASE"
- Distinctive: line 28
NEVER modify source code directly
- Distinctive: line 33
All commits in worktrees use: git commit -s -S
- Very specific: line 36
Run ~/.claude/scripts/setup-workbench.sh in any project
≈ “Common” is an estimate: at least 1 in 5 of the 6,350 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
---
description: agents-workbench workflow — worktree-based development with branch detection
alwaysApply: true
---
# agents-workbench Workflow
## Branch Detection
Before editing any source code, check: `git branch --show-current`
- If output is `agents-workbench` → source code is READ-ONLY. Suggest a worktree.
- If inside a `.worktrees/` path → you are in a worktree. Proceed normally.
- If on any other branch → normal development. Follow project conventions.
## Branch: agents-workbench (local-only, NEVER push)
- Coordination hub: AGENTS.md, .agents/*, docs/plans/*
- Source code is READ-ONLY on this branch
- Local commits only (preserve agent state)
## Implementation: ALWAYS in worktrees
- Fetch first: `git fetch upstream 2>/dev/null && BASE="upstream/$(git symbolic-ref refs/remotes/upstream/HEAD 2>/dev/null | sed "s@^refs/remotes/upstream/@@" || echo main)" || { git fetch origin && BASE="origin/$(git symbolic-ref refs/remotes/origin/HEAD | sed "s@^refs/remotes/origin/@@")"; }`
- Create from remote ref: `git worktree add .worktrees/<name> -b <branch> "$BASE"`
- Each feature/fix gets its own worktree from the default branch
- Push feature branches from worktrees, create PRs to default branch
- Clean up after merge: `git worktree remove .worktrees/<name>`
## What is editable on agents-workbench
- OK to edit: AGENTS.md, .agents/*, docs/plans/*, CLAUDE.md, .cursor/rules/*
- OK to read: any file (for context and planning)
- NEVER modify source code directly
## Agent Teams (Cursor + Claude Code)
- Lead agent: stays on agents-workbench, coordinates via AGENTS.md
- Worker agents: each in own worktree, parallel implementation
- All commits in worktrees use: `git commit -s -S`
## Setup
Run `~/.claude/scripts/setup-workbench.sh` in any project
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 3,978 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 repository48 other files it gives its agents.
- .claude/templates/AGENTS.mdAGENTS.md
- docs/agents.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- .cursor/rules/core.mdcCursor rule
- .cursor/rules/go.mdcCursor rule
- .cursor/rules/k8s.mdcCursor rule
- .cursor/rules/node.mdcCursor rule
- .cursor/rules/python.mdcCursor rule
- .cursor/rules/rust.mdcCursor rule
- .cursor/rules/tdd.mdcCursor rule
- llms-full.txtllms.txt
- llms.txtllms.txt
- cmux-sprint-orchestratorSkill
- config-auditSkill
- doneSkill
- eurekaSkill
- goalSkill
- go-reviewSkill
- handoffSkill
- js-reviewSkill
- k8s-debugSkill
- k8s-reviewSkill
- kickoffSkill
- pr-review-ingestSkill
- pr-reviewSkill
- python-reviewSkill
- reflectionSkill
- skill-evalSkill
- tdd-protocolSkill
- team-executeSkill
- team-planSkill
- team-shutdownSkill
- test-reviewSkill
- validate-recommendationSkill
- worktree-guideSkill
- babysitSkill
- canvasSkill
- create-hookSkill
- create-ruleSkill
- create-skillSkill
- create-subagentSkill
- migrate-to-skillsSkill
- sdkSkill
- shellSkill
- split-to-prsSkill
- statuslineSkill
- update-cli-configSkill
- update-cursor-settingsSkill
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.

