Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Git Worktree

ASecurity

Create Git branches, worktrees, or isolated snapshots of uncommitted work.

10 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentsrustgogitdatabasesecuritydocumentation

Security Analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned 10/6/2026

$npx -y skills add fmind/dot --skill git-worktree --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Git Worktree?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Git Worktree
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fmind-git-worktree/badge)](https://www.skillsdirectory.com/skills/fmind-git-worktree)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: git-worktree
description: "Create Git branches, worktrees, or isolated snapshots of uncommitted work."
license: MIT
metadata:
  kind: task
  author: Médéric HURIER (Fmind)
  source: github.com/fmind/dot/tree/main/skills/git-worktree
  created: "2026-09-09"
  updated: "2026-10-05"
---

# Git Worktree

Choose a branch in the current checkout or an isolated workspace according to the task. A branch-only request needs no extra checkout and follows the [branches](references/branches.md) guide; isolation, candidate identity, and cleanup follow the workflow below.

## Workflow

1. **Record the source**: inspect `git status --short`, `git diff`, `git diff --cached`, `git rev-parse HEAD`, and `git worktree list --porcelain`. Identify whether the candidate is a commit, the index, or selected working-tree changes.
1. **Choose isolation**: use a linked worktree for a committed revision or new branch. Use the [dirty candidate procedure](references/dirty-candidate.md) when validation must include uncommitted files, or when checks must not share Git refs or hooks with the source.
1. **Create a fresh destination**: choose a new sibling or temporary path outside the source. For a read-only review of committed code, use `git worktree add --detach <destination> <revision>`; for implementation, use `git worktree add -b <new-branch> <destination> <base>`.
1. **Inspect execution inputs**: read the destination's tasks and hooks before running them; isolate virtual environments, build output, coverage, ports, databases, and caches that tests mutate. Do not copy credentials or reuse a live database to make a fixture pass.
1. **Run the owning gate**: invoke the project's commands from the destination. Formatter output changes the tested candidate; compare it with the intended source before transferring proof or applying any resulting edits.
1. **Return only intended changes**: review the destination diff, transfer task-owned changes when authorized, and preserve the source index. Commits, pushes, and merges follow the user's requested delivery flow.
1. **Clean up deliberately**: inspect destination status and recover useful artifacts first. Use `git worktree remove <destination>` for an owned clean linked worktree; retain a dirty one until its changes are accounted for. Remove only the recorded disposable clone for a copied candidate.
1. **Report identity**: revision, included dirty changes, executed gate, source-versus-tested differences, and any retained workspace.

## Task guides

<!-- guides:start -->

- [branches](references/branches.md): Create and switch to a conventional `<type>/<slug>` branch in the current checkout.

<!-- guides:end -->

## Gotchas

- **A clean HEAD is a different candidate**: a passing worktree does not validate uncommitted edits in the source.
- **Worktrees share Git state**: linked worktrees have separate indexes but share objects, refs, and usually repository configuration and hooks. They are not a security sandbox; do not run untrusted code merely because it is in a worktree.
- **No forced reuse**: do not use force, stash, reset, or broad clean commands to make a busy branch or dirty destination available.
- **Neutralize external symlinks**: inspect and replace writable links into the source with safe fixture data or stop that test; a copied symlink can defeat isolation.

## Documentation

- [Git worktree](https://git-scm.com/docs/git-worktree) · [Git clone](https://git-scm.com/docs/git-clone)
- Companion skills: [mise](../mise/SKILL.md) (gates), [resolve-conflicts](../resolve-conflicts/SKILL.md) (integration conflicts).

Attribution

fmindfmind
View sourceSee grades on GitHubMore from fmind →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →