agentleFS
MoonshotAIMoonshotAI/kimi-cli/.agents/skills/worktree-status/SKILL.md

worktree-status

Skill11k starsChanged 41 days agoApache-2.0Archived repositoryView on GitHub

Audit all git worktrees in the current project. Use when the user asks about worktree status, which branches are merged, which have uncommitted changes, or which worktrees can be safely cleaned up.

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before batch-cleaning worktrees, to avoid losing uncommitted work

    line 15
  2. Distinctive:

    If all files are identical, the branch was squash-merged.

    line 75
  3. Very specific:

    Only run this if tmux is available and relevant (e.g.

    line 102
  4. Distinctive:

    Always present results as a Markdown table: Every worktree must appear as a row.

    line 111
  5. Distinctive:

    Add extra columns (e.g. tmux session, notes) only when relevant.

    line 126
  6. Distinctive:

    Only clean worktrees the user explicitly approves.

    line 130

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

worktree-status

Report the status of every git worktree for the current project, covering dirty state and merge status.

When to use

  • User asks "which worktrees can I clean up?"
  • User asks "what's the status of my worktrees / branches?"
  • Before batch-cleaning worktrees, to avoid losing uncommitted work

Procedure

1. Pull latest main (MANDATORY)

You MUST pull latest main before any status checks. Without this, merge detection (both ancestry and content diff) will produce stale results and you may mistakenly conclude a branch is not merged.

cd "$(git rev-parse --show-toplevel)" && git pull origin main

2. Collect worktree info

PROJECT_DIR="$(git rev-parse --show-toplevel)"

for wt in $(git worktree list --porcelain | grep "^worktree " | sed 's/^worktree //' | grep -v "$PROJECT_DIR$"); do
  branch=$(git -C "$wt" branch --show-current 2>/dev/null)
  [ -z "$branch" ] && branch="(detached)"
  name=$(basename "$wt")

  # dirty?
  if [ -z "$(git -C "$wt" status --short 2>/dev/null)" ]; then
    dirty="clean"
  else
    dirty="DIRTY"
  fi

  # merged into origin/main?
  # NOTE: This project uses squash merges exclusively. `git merge-base
  # --is-ancestor` does NOT detect squash-merged branches. Always follow
  # up with a content diff (step 3) for branches that appear "not merged".
  if [ "$branch" != "(detached)" ]; then
    if git merge-base --is-ancestor "$branch" origin/main 2>/dev/null; then
      merged="merged"
    else
      merged="not merged (verify with content diff)"
    fi
  else
    merged="n/a"
  fi

  echo ""
  echo "[$name]  branch=$branch  $dirty  $merged"
  if [ "$dirty" = "DIRTY" ]; then
    git -C "$wt" status --short 2>/dev/null | sed 's/^/  /'
  fi
done

3. Detect squash-merged branches (content diff)

For any branch that shows "not merged", check whether the branch's changes are already in main. The correct method is:

  1. Find the files the branch actually changed (relative to merge-base).
  2. For each changed file, compare the branch version with main. If all files are identical, the branch was squash-merged.

⚠️ Do NOT use git diff origin/main <branch> — that compares the two tips directly, so commits added to main after the branch diverged will show up as false differences.

BRANCH="<branch>"
BASE=$(git merge-base origin/main "$BRANCH")

# List files the branch touched
FILES=$(git diff --name-only "$BASE" "$BRANCH")

# Compare each file between branch and current main
for f in $FILES; do
  d=$(git diff "$BRANCH" origin/main -- "$f" | wc -l)
  if [ "$d" != "0" ]; then
    echo "❌ $f — differs"
  else
    echo "✅ $f — identical in main"
  fi
done
# All ✅ = squash-merged

4. (Optional) Check for associated tmux sessions

Only run this if tmux is available and relevant (e.g. worktrees were created by codex-worker or similar tooling). Skip if not applicable.

tmux ls 2>/dev/null | grep -E 'codex-worker|<other-pattern>' || true

5. Present results

Always present results as a Markdown table. Every worktree must appear as a row. Never use abbreviated or prose-only summaries.

WorktreeBranchDirtyMergedCan clean?
example-wtfeat-foo✅ clean✅ squash-merged✅
another-wtfix-bar⚠️ 3 files❌ not merged❌ dirty + not merged
detached-wt(detached)⚠️ 14 filesn/a❌ has uncommitted changes

Column definitions:

  • Dirty: ✅ clean or ⚠️ N files
  • Merged: ✅ merged / ✅ squash-merged (confirmed via content diff) / ❌ not merged / n/a
  • Can clean?: ✅ only when merged (or squash-merged) AND clean

Add extra columns (e.g. tmux session, notes) only when relevant.

6. Cleanup (only when asked)

Only clean worktrees the user explicitly approves. For each:

NAME="<worktree-name>"
git worktree remove "/path/to/$NAME"
git branch -D "<branch>"  # only if the branch is no longer needed

Download now (ZIP)

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. liferay/liferay-portal★ 2.3ksame name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository11 other files it gives its agents.

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.