Worktree Management

Core Question

Should this task use the current working tree or a separate Git worktree, and how can that worktree be created or removed safely?

When To Use

Use this skill when:

• the current working tree has unrelated work and a new task is requested
• the user wants to work on multiple branches concurrently
• the agent needs an isolated workspace for a risky or long-running task
• the user asks to list, create, prune, or remove worktrees

When Not To Use

Do not use this skill when:

• normal branch switching in a clean tree
• destructive recovery of lost commits
• conflict resolution inside a worktree
• commit planning inside a worktree

Route to:

• simple branch work routes to branch-workflow
• recovery or destructive cleanup routes to undo-recover
• conflicts inside a worktree route to resolve-conflicts
• commit work inside the selected worktree routes to atomic-commits

Required Evidence

Before action, inspect or establish:

• git worktree list --porcelain
• current branch and path
• target branch or task name
• dirty state in current and target worktree
• path existence and ownership
• remote branch relationship if creating from remote

No-evidence rule:

• Do not make strong claims without observed evidence.
• State assumptions when proceeding under incomplete evidence.
• Stop when missing evidence affects safety, correctness, user work, remote state, or irreversible action.

Operating Contract

You MAY:

• inspect relevant repository state and project files.
• generate a plan, report, or local artifact within the declared risk scope.
• route to another skill when the requested action is outside this skill's owner boundary.

You MUST:

• inspect before acting.
• keep the task within the declared owner boundary.
• classify state and risk before any meaningful action.
• preserve unrelated user work.
• verify outcomes proportional to risk.
• report evidence, assumptions, actions, verification, and residual risk.

You MUST NOT:

• invent project policy.
• expose secrets or sensitive values.
• mutate unrelated files or refs.
• perform destructive, remote, shared, history-rewriting, or irreversible actions without explicit action-specific confirmation.
• continue after unexpected destructive output.

State / Risk Table

Workflow

1. Identify the user goal and current owner boundary.
2. Inspect required evidence.
3. Classify repository/task state.
4. Classify risk using the declared scope.
5. Choose the minimal sufficient action or route.
6. Execute only allowed actions, if any.
7. Verify outcome or self-check the artifact.
8. Report result, evidence, verification, assumptions, and residual risk.

Decision Rules

• Prefer worktree isolation when the current tree contains unrelated human work.
• Do not remove a worktree until its status has been inspected.
• Do not reuse a dirty worktree for an unrelated task.
• Name worktrees by task or branch to improve auditability.

Tool Rules

• May inspect and list worktrees.
• May create a worktree after explicit branch/path intent.
• Must not remove dirty worktrees.
• Must not delete branches or remote refs from this skill.

Verification

Minimum verification:

• Verify worktree path, branch, and status after creation or removal.
• Report residual dirty state.
• Confirm no unrelated worktree was modified.

Risk-based floor:

• R0-R1: evidence inspected and output self-checked.
• R2: inspect resulting diff or local state.
• R3: verify local state and report recovery limits.
• R4-R5: require explicit confirmation, preflight evidence, and post-action verification where this skill owns the action.

Output Contract

Final response must include:

## Result

- Decision, action, or artifact produced.

## Evidence

- Files, commands, diffs, refs, or assumptions used.

## Verification

- Checks performed and their result.

## Risks / Limitations

- Remaining uncertainty, blocked actions, or routed next steps.

Stop / Confirmation Rules

Stop when the repository state is dirty, conflicted, diverged, missing required evidence, or ambiguous in a way that could overwrite user work, invalidate the requested scope, or require a gated action.

Require explicit action-specific confirmation for:

• destructive local mutation.
• remote/shared mutation.
• history rewriting.
• security/secret/data impact.
• irreversible or hard-to-recover operation.

Broad approval such as "do whatever" is not enough for R4-R5 actions.

Lazy-load References

Load references/worktree-lifecycle.md when:

• the task needs the detailed guidance described by the file name.
• the state/risk table identifies an ambiguous or high-risk path.

Load references/isolation-patterns.md when:

• the task needs the detailed guidance described by the file name.
• the state/risk table identifies an ambiguous or high-risk path.

Load references/cleanup.md when:

• the task needs the detailed guidance described by the file name.
• the state/risk table identifies an ambiguous or high-risk path.