plan-with-wt

A command for approving an implementation plan that uses an isolated Git worktree and creates a pull request. A worktree is a separate working directory for another branch of the same repository.

In plain words
What is it for?
Use it when a planned fix, feature, or maintenance task should run in its own worktree and end with a GitHub pull request.
Why use it?
It provides a repeatable path for handling issues in isolation, committing the result, and opening the corresponding pull request.

Command

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.

agentmods
npx agentmods add commands/bengous/claude-code-plugins/plan-with-wt
Clone the repo
git clone --depth 1 https://github.com/bengous/claude-code-plugins
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 148 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00010 $0.00148
Opus 5 $0.00005 $0.00074
Sonnet 5 $0.00002 $0.00030
Haiku 4.5 $0.00001 $0.00015

Measured yesterday against content hash 8d159475dfee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-with-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.

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.

archive/git-legacy/commands/plan-with-wt.md · 12 lines

What it actually says

Yes, enter plan mode.

This work will run in an isolated worktree so multiple issues can be handled in parallel. Include these steps in the plan:

  1. Create a worktree using git-wt <type>/<issue-number>-<slug> where type is fix, feat, or chore based on the issue, and slug is 2-3 words from the title (e.g., fix/292-playwright-caching)
  2. Change to the worktree directory before implementing any changes
  3. After implementation, commit with a message that references the issue, then create a pull request using gh pr create
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.

  1. yesterday First seen · 12 lines · 10 tokens per session scan A 8d159475dfee

Subscribe to this mod's changes

plan-with-wt is a command published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 2d ago), licensed MIT. It adds 10 tokens to every session and 148 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 2026-08-31.