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 commands/davila7/claude-code-templates/worktree-initgit clone --depth 1 https://github.com/davila7/claude-code-templatesWhat 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 | $0.00012 | $0.00831 |
| Opus 5 | $0.00006 | $0.00415 |
| Sonnet 5 | $0.00002 | $0.00166 |
| Haiku 4.5 | $0.00001 | $0.00083 |
Grade A, and why
worktree-init 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worktree Parallel Init
Create multiple git worktrees for parallel development: $ARGUMENTS
Instructions
You are setting up parallel worktrees so the user can work on multiple tasks simultaneously in separate Ghostty terminal panels, each running its own Claude instance.
Step 1: Validate Environment
- Check this is a git repository:
git rev-parse --is-inside-work-tree - Get the repo name:
basename $(git rev-parse --show-toplevel) - Get the main branch name (check for
mainormaster):git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@'— if that fails, default tomain - Ensure working tree is clean:
git status --porcelain. If dirty, warn the user and ask if they want to continue. - Fetch latest:
git fetch origin
Step 2: Parse Tasks
Parse tasks from $ARGUMENTS. Tasks are separated by | (pipe character).
If $ARGUMENTS is empty, use AskUserQuestion to ask the user to describe their tasks (they can provide multiple separated by |).
For each task description:
- Trim whitespace
- Generate a kebab-case branch name:
claude/<kebab-case-task>(max 50 chars, alphanumeric and hyphens only) - Generate a worktree directory path:
../worktrees/<repo-name>/claude-<kebab-case-task>
Step 3: Create Worktrees
For each task:
- Create the parent directory if needed:
mkdir -p ../worktrees/<repo-name> - Create the worktree:
git worktree add -b claude/<name> ../worktrees/<repo-name>/claude-<name> origin/<main-branch> - Write a
.worktree-task.mdfile inside the new worktree with this content:# Worktree Task **Branch:** claude/<name> **Task:** <original task description> **Created:** <ISO date> **Source repo:** <path to main repo>
Step 4: Check for Dependencies
If a package.json exists in the repo root, note that each worktree may need npm install (or the appropriate package manager).
Check for:
package-lock.json→ npm installyarn.lock→ yarn installpnpm-lock.yaml→ pnpm installbun.lockb→ bun install
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 · 89 lines · 12 tokens per session scan A 32a29d3468a2
worktree-init is a command published in the GitHub repository davila7/claude-code-templates (30,476 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 831 once invoked, about $0.0001 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 commands, from other repositories
README
Git workflow and quality assurance commands for the claude-skills repository.
become
Agent crystallization command. Studies a tool, role, or person and produces a portable 9-section agent that inhabits the domain - with beliefs, scar tissue, and instincts.
cycle-start
Activate a cycle and start implementing its stories.
research-verify
Verify existing research findings against independent primary sources. Upgrades confidence from 'sources agree' to 'independently verified.'.
story-continue
Resume an interrupted story from where you left off.
story-archive
Move a story from a cycle back to the backlog.