Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/jeremydev87/codingbuddy/using-git-worktreesnpx skills add JeremyDev87/codingbuddy --skill using-git-worktreesgit clone --depth 1 https://github.com/JeremyDev87/codingbuddyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jeremydev87/codingbuddy/using-git-worktrees)<a href="https://agentmods.dev/skills/jeremydev87/codingbuddy/using-git-worktrees"><img src="https://agentmods.dev/badge/skills/jeremydev87/codingbuddy/using-git-worktrees.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00038 | $0.03049 |
| Opus 5 | $0.00019 | $0.01524 |
| Sonnet 5 | $0.00008 | $0.00610 |
| Haiku 4.5 | $0.00004 | $0.00305 |
Grade C, and why
using-git-worktrees scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| **Bad** | `rm -rf .worktrees/my-feature` | Leaves orphaned metadata — breaks `git worktree list` and blocks branch ops | How it starts
The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Git Worktrees
Overview
Git worktrees provide isolated working directories sharing a single .git repository. They enable parallel development without stashing, branch-switching conflicts, or duplicate clones.
Core principle: EVERY worktree operation must be verified before and after. Unverified worktrees cause lost work, orphaned branches, and corrupted state.
The Iron Law
NO WORKTREE CREATION WITHOUT SAFETY CHECKS.
NO WORKTREE REMOVAL WITHOUT UNCOMMITTED CHANGE VERIFICATION.
If you skip the safety checks, you will lose work. There are no exceptions.
When to Use
- Parallel execution: Running multiple tasks simultaneously (taskMaestro waves)
- Feature isolation: Working on a feature without disrupting main branch state
- Plan implementation: Creating a dedicated workspace before implementing a plan
- Exploration: Trying an approach without affecting current work
- Code review: Checking out a PR branch while keeping your current work intact
Use this ESPECIALLY when:
- You need to work on multiple issues simultaneously
- You want to preserve your current branch state while exploring something else
- A brainstorming session has produced a design ready for implementation
- You are about to run
/taskmaestro wave-transition
Don't skip when:
- "It's just a quick branch switch" (worktrees prevent accidental stash loss)
- "I'll remember to clean up later" (stale worktrees accumulate silently)
- "The repo is small, cloning is fine" (clones don't share history; worktrees do)
Phase 1: Assessment
BEFORE creating any worktree, answer these questions:
1.1 Determine the Purpose
| Purpose | Directory Convention | Branch Convention |
|---|---|---|
| Parallel execution (taskMaestro) | .taskmaestro/wt-N |
taskmaestro/<epoch>/pane-N |
| Tool-managed isolation | Tool-specific (e.g., .claude/worktrees/) |
Auto-managed by the tool |
| Standalone / manual | .worktrees/<descriptive-name> |
wt/<description> or feat/<issue>-<slug> |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 369 lines · 38 tokens per session scan C bfc2dcad6aa8
using-git-worktrees is a skill published in the GitHub repository JeremyDev87/codingbuddy (31 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 3,049 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…
ring:auditing-dependency-security
Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…
ring:checking-frontend-quality
Checking frontend quality against changed UI via ring:qa-frontend in accessibility, visual, e2e, or performance mode and aggregating pass/fail verdicts. Use when a frontend change needs standalone a11y, visual-snapshot, Playwright e2e, or Lighthouse/Core-Web-Vitals validation outside the dev cycle. Skip for…
bzdesignprompt
为前端或网页设计任务选择并下载合适的 DESIGN.md 模板。当用户需要网页设计模板、UI 风格参考、设计系统、落地页或前端界面设计时，浏览长亭百智云 UI 设计模板库，根据产品场景和视觉偏好匹配模板，并将完整 DESIGN.md 保存到项目中。.
verify-quality
Verify code quality including naming conventions, organization, documentation, and general best practices. Use when asked to "verify quality", "check code quality", or "review code organization".