agentleFS
Sign inStart free
GabrieleDattileGabrieleDattile/agent-superpowers/skills/workflow/git-worktree-sandbox/SKILL.md

git-worktree-sandbox

Skill1 starsChanged 15 days agoMITView on GitHub

Ephemeral git worktree sandbox isolation. Guarantees that agent experiments, aggressive refactoring, and test suites run in isolated worktrees without corrupting the primary working branch.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All file reads, edits, test runs, and commits take place strictly inside .worktrees/<task-name>.

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

📦 Skill: Git Worktree Sandbox (Workspace Isolation)

1. When to Trigger (Routing)

  • TRIGGER WHEN:
    • The agent begins a complex feature, invasive refactoring, or multi-file architectural change.
    • The user requests: "work in a sandbox", "use an isolated branch", or "don't break my current working tree".
  • DO NOT TRIGGER WHEN:
    • The workspace is not a Git repository.
    • The edit is a trivial single-line typo fix in a documentation markdown file.

2. Fundamental Philosophy

"Coding agents often modify files prematurely, leaving half-finished edits, untracked garbage, or broken builds in the user's active editor. Git Worktree Sandbox forces all experimental work into a parallel, isolated workspace directory."

3. Operational Protocol

Phase 1: Create Isolated Sandbox

Execute the worktree helper:

python skills/workflow/git-worktree-sandbox/scripts/worktree.py create <task-name>

This automatically:

  1. Creates a new branch worktree/<task-name>.
  2. Checks it out in .worktrees/<task-name>.
  3. Ensures your primary working tree remains 100% clean and untouched.

Phase 2: Execute Work in Sandbox

  • All file reads, edits, test runs, and commits take place strictly inside .worktrees/<task-name>.

Phase 3: Finish & Clean Up

Once tests pass and the user confirms:

  • To merge and finish:
    python skills/workflow/git-worktree-sandbox/scripts/worktree.py merge <task-name>
  • To discard on failure:
    python skills/workflow/git-worktree-sandbox/scripts/worktree.py discard <task-name>

4. Guardrails & Negative Constraints

  • ❌ NEVER leave temporary .worktrees/ directories checked into git (ensure .gitignore ignores .worktrees/).
  • ❌ NEVER force-delete an active worktree without user consent if uncommitted changes exist.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free