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 skills add LeeJuOh/claude-code-zero --skill worktree-setupgit clone --depth 1 https://github.com/LeeJuOh/claude-code-zeroWrote 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/leejuoh/claude-code-zero/worktree-setup)<a href="https://agentmods.dev/skills/leejuoh/claude-code-zero/worktree-setup"><img src="https://agentmods.dev/badge/skills/leejuoh/claude-code-zero/worktree-setup.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 5.1 | $0.00097 | $0.03009 |
| Opus 5 | $0.00048 | $0.01504 |
| Sonnet 5 | $0.00019 | $0.00602 |
| Haiku 4.5 | $0.00010 | $0.00301 |
Grade C, and why
worktree-setup 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 yesterday.
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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
When the user wants to link a per-branch dependency directory (`node_modules/`, `.venv/`, `target/`), don't refuse — explain and let them choose. A symlink makes every worktree share one directory, so an install on a bra How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
worktree-plus Setup
Two jobs live here, and a user usually wants one of them:
- Settings — git config under the
worktreeplus.*namespace (plugin-custom) plus oneworktree.guessRemote(git-native). No env vars. Start at Settings. - Which gitignored files follow a worktree — the
.worktreeinclude(copy) and.worktreelink(symlink) files at the repo root. Start at Set up .worktreeinclude / .worktreelink.
If the user's ask is vague ("set up worktree-plus"), show the current settings first — it's cheap and orients both of you — then offer the include/link scan.
Settings
| Key | Default | Scope guidance |
|---|---|---|
worktreeplus.baseBranch |
HEAD |
Per-repo typical (different repos have different default branches) |
worktreeplus.branchPrefix |
worktree- |
Global typical (personal naming convention); per-repo for team rules |
worktreeplus.dirBase |
.claude/worktrees |
Per-repo typical |
worktree.guessRemote |
true (plugin override; git default is false) |
Global typical |
View current settings
Always start by showing what's active. Run:
git config --get-regexp '^worktreeplus\.|^worktree\.guessRemote'
If nothing prints, the user is on defaults. State that explicitly — don't leave them guessing.
For layered view (local vs global vs system):
git config --local --get-regexp worktreeplus
git config --global --get-regexp worktreeplus
Change a setting
Ask scope before writing. "Just this repo" (--local, default) vs "all repos for me" (--global).
git config [--local|--global] worktreeplus.baseBranch develop
git config [--local|--global] worktreeplus.branchPrefix "feat-"
git config [--local|--global] worktreeplus.dirBase ".worktrees"
git config [--local|--global] worktree.guessRemote false
Writes take effect on the next EnterWorktree / claude -w. Existing worktrees are not affected.
Reset / unset
Destructive. Confirm with the user first before running — name exactly what will be removed.
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.
- yesterday First seen · 194 lines · 97 tokens per session scan C 253361b531d6
worktree-setup is a skill published in the GitHub repository LeeJuOh/claude-code-zero (51 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 3,009 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other skills, from other repositories
autoship
Runs a changesets npm release through the version PR, CI publish, and registry verification. Use when asked to "release this package", "autoship", "merge Version Packages", or diagnose a release that did not publish. For feature PRs use pr-creator or pr-babysitter.
pr-creator
Creates or updates GitHub PRs with house-style titles and bodies, issue linking, repository templates, and draft state. Use when asked to "create a PR", "rewrite the PR description", or "polish this PR". For code fixes use tidy; for CI and review threads use pr-babysitter; for npm releases use autoship.
pypi-release
This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.
conventional-commit
Use this skill any time the user asks for a git commit. Writes messages in Conventional Commit format.
pr-description
Generate a PR description from git diff. Use when the user asks for a PR description, summary of changes, or "what changed".
agent-merge-conflict-arbiter
Neutral arbiter for merge conflicts between two agents.