Files
holocron/plugins/git/.apm/skills/git-worktrees/SKILL.md
Defame1297 5e232503c4 feat(kyberforge): execute plugin-to-apm marketplace conversion
Why:
ADR-0015 established that Microsoft APM (apm.yml + .apm/) should replace
this repo's hand-authored plugin.json/marketplace.json model, with those
files becoming compiled output of `apm pack` instead of files edited by
hand via the (now-retired) plugin-author/marketplace-author skills.
Issue #90 was the deferred execution of that decision, gated on #88
(apm tooling) and #89 (apm-native agent-author/skill-author routing).

Implementation notes:
- All six plugins (bin, core, git, gitea, kyberforge, lint) now carry
  apm.yml + .apm/{skills,agents,hooks} as their authoring source. Skills
  moved with a plain git mv (content-identical across targets). Agents
  were re-authored, not moved: per ADR-0016, .apm/agents/*.agent.md
  compiles verbatim to both Claude and Copilot, so plugin-scope agents
  now carry only name/description/model/source_keys -- no tools: field,
  no Claude-only knobs (isolation, maxTurns, effort, memory,
  permissionMode).
- Root apm.yml registers all 7 marketplace packages (6 local plus
  mattpocock-skills as a remote entry) under versioning: per_package,
  matching this repo's existing independent-plugin-versioning practice.
- .claude-plugin/marketplace.json and every plugin's plugin.json are now
  apm-pack-compiled output, verified against the prior hand-maintained
  content: same names/descriptions/versions/licenses/authors, only
  cosmetic serialization differences (JSON key order, owner email vs.
  url, Unicode escaping).
- plugin-author and marketplace-author are retired now that apm-based
  authoring fully replaces their job; kyberforge bumped 1.3.1 -> 1.4.0
  for that removal, and the root marketplace catalog bumped
  0.3.1 -> 0.3.2 to match, per the version-bump convention now
  documented in apm-workflow's reference docs instead of a dedicated
  script (apm has no native version-bump automation).
- Fixed hardcoded pre-.apm/ path assumptions across
  .pre-commit-config.yaml, .pre-commit-hooks.yaml,
  scripts/check-scope-walkup-sync.sh, scripts/sync-vale-styles.sh,
  scripts/check-vale-style-sync.sh, six plugins' root plugin.json
  (stale skills/hooks/agents pointer fields that check-manifests.sh
  validates), and several tests/*.bats and tests/*.sh fixtures --
  including a bats REPO_ROOT relative-path depth bug (10 files, one
  extra .apm/ directory level to walk up) and a vale probe-path
  isolation regression introduced mid-fix.
- Corrected empirically-wrong assumptions surfaced this session in
  apm-workflow/apm-install's own reference docs: `apm marketplace
  package add` does not accept local paths (only owner/repo remote
  shorthand -- local packages are registered by editing apm.yml's
  marketplace.packages[] directly); `apm compile` is a consumer-side
  AGENTS.md/CLAUDE.md generator, not the plugin.json producer, and
  hard-fails on skill/agent-only packages without --clean; `apm plugin
  init <name>` nests a stray subdirectory when run with a positional
  name arg from inside a same-named directory; no native Copilot
  marketplace output profile exists; .mcp.json is merged into the
  compiled plugin.json content-aware and target-scoped, with no
  dependencies.mcp entry needed for simple passthrough; pipx is the
  correct pip fallback on externally-managed Python environments.
- Renamed agent-author's copilot.agent.md template asset to
  copilot.agent.md.template so apm compile's recursive *.agent.md glob
  stops misparsing the placeholder template as a real agent primitive.

Impact:
plugin.json and marketplace.json are compiled artifacts from here on --
editing them by hand is no longer the workflow; edit apm.yml/.apm/ and
run apm pack. CONTEXT.md's Plugin/Plugin marketplace glossary entries
reflect this. ADR-0001 is marked superseded, ADR-0006 moot, and
ADR-0010 updated for the new .apm/agents/ path (project/user scope
unaffected, per ADR-0016). Full local verification: claude plugin
validate --strict on all 6 plugins, apm audit --ci, apm marketplace
check, check-manifests.sh, and the full test suite (165/165 bats,
13/13 shell scripts) all pass clean.

Fixes: #90
Refs: #88, #89
ADR: 0015
ADR: 0016

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ub96PyaSRD9BHPktotj1pC
2026-08-12 18:21:24 +00:00

6.0 KiB

name, description, metadata
name description metadata
git-worktrees Manage Git worktrees to enable multi-branch parallel development across isolated directories. Use when the user needs to work on multiple branches simultaneously without stashing, switch between feature/hotfix/experimental work, or coordinate code reviews alongside ongoing development. Handles creation, listing, locking, moving, removal, pruning, and repair of worktrees. Provides structured results (paths, branches, lock status) for agent composition in git orchestration workflows. Do not use when only inspecting a single branch or when the user needs standard checkout/stash workflows.
category source_keys
git
git-scm-worktree-docs

Concept

A worktree lets you check out multiple branches simultaneously from one repository, each in its own directory. All worktrees share the same objects, config, and most refs (refs/). Each worktree has its own HEAD, index, and per-worktree metadata (ORIG_HEAD, MERGE_HEAD, refs/bisect/, refs/worktree/, refs/rewritten/) stored at $GIT_DIR/worktrees/<name>/. The main worktree (from git init/git clone) is exactly one per repo and cannot be removed; linked worktrees are the additional ones created via git worktree add.

Gotchas

  • A branch can only be checked out in one worktree at a time. Attempting git worktree add for an already-checked-out branch fails unless you pass --force. Use --force only when intentional.
  • Submodules are unsupported and block operations. Repos with submodules have incomplete worktree support. Worktrees containing submodules cannot be moved and require --force to remove.
  • Never manually rm -rf a worktree directory. This leaves stale metadata in $GIT_DIR/worktrees/. Always use git worktree remove. If already deleted, run git worktree prune to clean up.
  • Manual moves break bidirectional pointers. If a worktree directory is moved outside of git worktree move, run git worktree repair to fix connections.
  • Force-flag escalation with locks. Removing or moving a locked worktree requires -ff (two flags), not just -f.
  • Worktree identification is by full path, unique basename, or unique partial path. Ambiguous names error. Use git worktree list to see available identifiers.
  • --lock on add is atomic; create-then-lock has a race window. Use --lock directly on git worktree add when consistency matters.
  • extensions.worktreeConfig = true is a one-way door. It enables per-worktree config (git config --worktree ...) but makes the repo refuse to open in older Git versions. Once set, core.bare/core.worktree must live in config.worktree, not config. Don't enable it unless per-worktree config is actually needed.

Common Operations

Create and switch to a new worktree — default approach:

git worktree add -b <new-branch> <path>
cd <path>

This creates a new branch and checks it out in a new directory. Other branches cannot be checked out elsewhere simultaneously.

Create-or-reset a branch: git worktree add -B <branch> <path> — like -b but resets the branch to HEAD if it already exists.

Create a worktree for an existing remote branch:

git worktree add <path> <remote>/<branch>

For ambiguous names across remotes, disambiguate via checkout.defaultRemote config or --guess-remote. Full flag table and detail: references/worktrees.md.

Throwaway experiment in detached HEAD:

git worktree add -d ../experiment   # or --detach
# experiment freely, no branch created
git worktree remove ../experiment

List all worktrees with state:

git worktree list -v        # human-readable with lock/prune reasons
git worktree list --porcelain -z  # machine-readable, NUL-terminated

Move a worktree to a new path:

git worktree move <current-path> <new-path>
# Cannot move: main worktree, worktrees with submodules
# To override safeguards: -f; to override locked state too: -ff

Remove a worktree:

git worktree remove <path>        # only if clean
git worktree remove -f <path>     # force-remove unclean
git worktree remove -ff <path>    # force-remove even if locked

Prune stale metadata:

git worktree prune --dry-run        # preview what would be removed
git worktree prune                  # clean up orphaned metadata

Also triggered by git gc, controlled by gc.worktreePruneExpire config.

Repair broken connections (after a manual move):

git worktree repair  # from main worktree or after it was moved
git worktree repair <path>  # reconnect a specific linked worktree

Sparse-checkout worktrees, locking for removable media, the full add flag table, and the config key reference: references/worktrees.md.

Worked Examples

Emergency fix without disrupting current work — no stashing needed, ongoing work in the main worktree is untouched:

git worktree add -b emergency-fix ../temp main
cd ../temp
# fix, commit
git commit -a -m "fix: critical production bug"
cd -
git worktree remove ../temp

Review a PR branch alongside your current work — no context switch, both branches stay checked out:

git worktree add ../review-pr-123 origin/feature-xyz
# open ../review-pr-123 in a second editor window or terminal

Return Format for Agents

When invoking worktree operations, return structured results:

worktrees:
  - path: <directory-path>
    branch: <branch-name>
    commit: <short-hash>
    locked: <true/false>
    lock_reason: <reason or empty>
  - ...

Derive these fields from git worktree list --porcelain -z — its worktree/branch/HEAD/locked lines map directly to path/branch/commit/locked+lock_reason.

For single operations, include the operation result (e.g., created: true, removed: true, moved: true).

For multi-step flows spanning branch strategy plus worktree setup, compose with the git-workflow skill — it handles the broader orchestration, this skill handles the worktree mechanics.