worktrunk CLAUDE.md

Project instructions for developing Worktrunk, a command-line tool for managing Git worktrees so several AI-agent tasks can use separate working directories.

In plain words
What is it for?
Use them when making changes to Worktrunk or trying to understand how its repository and worktree workflow are organized.
Why use it?
They give the agent the project’s development rules, current status, terminology, and starting guidance in one place.

Instructions file

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 instructions/max-sixty/worktrunk/claude-md
Clone the repo
git clone --depth 1 https://github.com/max-sixty/worktrunk
Per session 6,896 This file is loaded in full into every session.
When invoked 6,896 The same file — it is already loaded in full.
Security scan C 2 findings. Scan, not verified.
Origin unknown 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 $0.06896 $0.06896
Opus 5 $0.03448 $0.03448
Sonnet 5 $0.01379 $0.01379
Haiku 4.5 $0.00690 $0.00690

Measured yesterday against content hash ed9b06055204, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

worktrunk CLAUDE.md scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

**Why:** the gate is the only thing between `git clone && wt switch` and a `post-switch` hook running `curl … | sh`. A "we already validated the operation, so run the hooks too" shortcut turns every command that touches

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Why:** the gate is the only thing between `git clone && wt switch` and a `post-switch` hook running `curl … | sh`. A "we already validated the operation, so run the hooks too" shortcut turns every command that touches
CLAUDE.md · 220 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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 · 220 lines · 6,896 tokens per session scan C ed9b06055204

Subscribe to this mod's changes

worktrunk CLAUDE.md is an instructions file published in the GitHub repository max-sixty/worktrunk (6,757 stars, last pushed yesterday), with no licence file. It adds 6,896 tokens to every session, about $0.0345 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.