agentleFS
sodejmsodejm/portable-agent-repository-kit/.claude/skills/resumable-worktree-run/SKILL.md

resumable-worktree-run

Skill1 starsChanged 3 months agoApache-2.0View on GitHub

Plan and hand off issue-sized work in an isolated Git worktree with an evidence-bearing checkpoint and safe cleanup boundary.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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
  1. Distinctive:

    Use for substantial or interruptible Git work when worktree isolation is helpful.

    line 8
  2. Distinctive:

    Create one clearly named branch and worktree for one workstream only when the user or project workflow authorizes it.

    line 11
  3. Distinctive:

    Keep a concise checkpoint containing outcome, scope, branch/worktree, base and head commits, completed validation, current step, blocker, …

    line 13
  4. Distinctive:

    Before resuming, recheck that the worktree and hosted state still match the checkpoint.

    line 15
  5. Distinctive:

    Never remove a worktree or branch with unique or uncommitted work.

    line 20

≈ “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

Resumable worktree run

Use for substantial or interruptible Git work when worktree isolation is helpful.

  1. Inspect existing branches, worktrees, changes, and the intended base revision.
  2. Create one clearly named branch and worktree for one workstream only when the user or project workflow authorizes it.
  3. Keep a concise checkpoint containing outcome, scope, branch/worktree, base and head commits, completed validation, current step, blocker, and next action.
  4. Before resuming, recheck that the worktree and hosted state still match the checkpoint; treat drift as new evidence.
  5. At handoff, include exact paths and commands without private machine details in public artifacts.

Never remove a worktree or branch with unique or uncommitted work. Cleanup requires fresh verification and the authority specified by the project workflow.

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.