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/dyoshikawa/rulesync/git-worktree-runnernpx skills add dyoshikawa/rulesync --skill git-worktree-runnergit clone --depth 1 https://github.com/dyoshikawa/rulesyncWhat 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 | $0.00075 | $0.01419 |
| Opus 5 | $0.00037 | $0.00709 |
| Sonnet 5 | $0.00015 | $0.00284 |
| Haiku 4.5 | $0.00007 | $0.00142 |
Grade A, and why
git-worktree-runner scanned grade A with 0 findings 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 2d ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Worktree Runner (gtr)
git-worktree-runner (gtr) is a CLI tool that wraps git worktree with quality-of-life features for modern development workflows including editor and AI tool integration.
Quick Start
# Create a new worktree
git gtr new feature-branch
# Create from a remote branch
git gtr new my-branch --from origin/feature-branch
# Open editor in the worktree
git gtr editor feature-branch
# Start AI tool (claude, codex, etc.) in the worktree
git gtr ai feature-branch
# Remove a worktree
git gtr rm feature-branch
Commands
Creating Worktrees
# Create a new worktree with a new branch
git gtr new feature-name
# Create from a specific ref (remote branch, tag, commit)
git gtr new my-branch --from origin/main
git gtr new hotfix --from v1.2.3
# Create and immediately open in editor
git gtr new feature -e
# Create and immediately start AI tool
git gtr new feature -a
# Create with both editor and AI tool
git gtr new feature -e -a
Opening Editor / AI Tool
# Open the configured editor for a worktree
git gtr editor feature-branch
# Start configured AI tool in a worktree
git gtr ai feature-branch
Running Commands
# Run an arbitrary command in a worktree
git gtr run feature-branch npm test
git gtr run feature-branch pnpm build
Navigation
# Navigate to a worktree directory
cd "$(git gtr go feature-branch)"
Listing and Managing
# List all worktrees
git gtr list
# Remove a worktree
git gtr rm feature-branch
# Rename a worktree
git gtr mv old-name new-name
Configuration
# Set default editor (cursor, vscode, zed, etc.)
git gtr config set gtr.editor.default cursor
# Set default AI tool (claude, codex, opencode, aider, etc.)
git gtr config set gtr.ai.default claude
# Configure files to copy into new worktrees
git gtr config add gtr.copy.include "**/.env"
git gtr config add gtr.copy.include "**/.env.local"
git gtr config add gtr.copy.include "**/.env.example"
# View current configuration
git gtr config list
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.
- 2d ago First seen · 226 lines · 75 tokens per session scan A 5495a15ee514
git-worktree-runner is a skill published in the GitHub repository dyoshikawa/rulesync (1,362 stars, last pushed 2d ago), licensed MIT. It adds 75 tokens to every session and 1,419 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
deep-clean
Full-spectrum consolidation of AI agent configuration files. Goes beyond memory-only dream skills: audits and optimizes context files (AGENTS.md/AGENTS.md/GEMINI.md/.cursorrules), rules, skills, and memory. Detects stale references, dead file paths, duplicated rules, stack mismatches, contradictions, vague directives…
turborepo
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines…
skill-creator-openai
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…
skill-creator-anthropic
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states.…