A command that prepares a separate worktree for a planned coding task. A worktree is an additional project directory with its own branch, so work can be isolated from other changes.

Use it to create a task file, choose a branch, run `wtcraft new`, and report where the executor should continue.

It records the task details and creates the workspace an executor needs without asking for extra confirmation.

How zywkloo/wtcraft configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to zywkloo/wtcraft. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/zywkloo/wtcraft/main/.claude/commands/planwt.md

Clone the repo

git clone --depth 1 https://github.com/zywkloo/wtcraft

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/zywkloo/wtcraft/planwt/github.svg)](https://agentmods.dev/commands/zywkloo/wtcraft/planwt)

Your own site

<a href="https://agentmods.dev/commands/zywkloo/wtcraft/planwt"><img src="https://agentmods.dev/badge/commands/zywkloo/wtcraft/planwt/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/zywkloo/wtcraft/planwt"><img src="https://agentmods.dev/badge/commands/zywkloo/wtcraft/planwt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 293 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00293
Opus 5.5	$0.00000	$0.00117
Sonnet 5.5	$0.00000	$0.00059
Haiku 4.5	$0.00000	$0.00029

Measured 2mo ago against content hash b1c7a3af4c7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

planwt 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 2mo 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.

.claude/commands/planwt.md · 31 lines

What it actually says

You are the orchestrator for a bounded worktree task.

Read .agent-harness/planner.md before proceeding.

Task

$ARGUMENTS

Steps (execute in order, no confirmation needed)

Infer a branch name from the task description. Format: <type>/<short-slug> (e.g. feat/oauth-login, fix/null-check, docs/readme-update).
Read the template at templates/worktrees/.worktree-task.md to understand the expected file format and frontmatter fields.
Write .worktree-task.md in the repo root following the template structure:
- Frontmatter: fill in branch (from step 1), created (today's date), base (default develop, or main if WTCRAFT_BASE_BRANCH=main), agent, status: ready, and priority.
- Body: fill Scope, Steps, Off-limits, Context, and Verification per .agent-harness/planner.md rules.
Create the worktree by running:
```
wtcraft new <branch-name>
```
This will move the .worktree-task.md you wrote into the new worktree automatically.
Report the worktree path and the next action for the executor.

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.

2mo ago First seen · 31 lines · 0 tokens per session scan A b1c7a3af4c7e

Subscribe to this mod's changes

planwt is a command published in the GitHub repository zywkloo/wtcraft (2 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 293 tokens. 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 2026-08-31.

Claude Code Git and workflow Planning agent codex harness-engineering skills vibe-coding

wtcraft: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Task

Steps (execute in order, no confirmation needed)

What this file has done since we first saw it

Other commands, from other repositories

release

release

rclone_gitannex

rclone_test_changenotify

rclone_convmv

checklist