wt

Install

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.

Token cost

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.

Security

Grade A, and why

wt 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 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.

Origin

Copies of this mod

.claude/skills/wt/SKILL.md · 45 lines

What it actually says

# Return to repo root
cd "$(git rev-parse --show-toplevel)"

# Pull latest master
git checkout master
git pull origin master

# Create worktree
git worktree add worktree/"$ARGUMENTS" -b "$ARGUMENTS"

# Initialize submodules (skills-vendor)
git -C worktree/"$ARGUMENTS" submodule update --init --recursive

# Navigate to worktree
cd worktree/"$ARGUMENTS"

# Confirm location and branch
echo ""
echo "✅ Worktree created and ready:"
echo "   Location: $(pwd)"
echo "   Branch: $(git rev-parse --abbrev-ref HEAD)"
echo ""
echo "You can now work in this isolated environment."

Changes

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.

Related

Other skills, from other repositories