workz CLAUDE.md

workz CLAUDE.md is an instructions file for coding agents from rohansx/workz. It costs 297 tokens per session, scanned B, original, MIT.

Repository instructions for integrating Workz, a tool that manages separate Git worktrees for coding tasks. A worktree is an isolated working copy of a repository, allowing tasks to use separate branches and files.

In plain words
What is it for?
They help start, list, inspect, synchronize and remove worktrees, and run independent agent tasks with separate branches, dependencies and environment settings.
Why use it?
Parallel coding work can interfere when agents share one working directory, and overlapping edits can be hard to spot. These instructions describe how to isolate tasks and check for conflicts before combining them.

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/rohansx/workz/claude-md
Clone the repo
git clone --depth 1 https://github.com/rohansx/workz

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.

agentmods badge for workz CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rohansx/workz/claude-md.svg)](https://agentmods.dev/instructions/rohansx/workz/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rohansx/workz/claude-md"><img src="https://agentmods.dev/badge/instructions/rohansx/workz/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 297 This file is loaded in full into every session.
When invoked 297 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.00297 $0.00297
Opus 5 $0.00148 $0.00148
Sonnet 5 $0.00059 $0.00059
Haiku 4.5 $0.00030 $0.00030

Measured 4d ago against content hash 904a91547a03, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

workz CLAUDE.md scanned grade B with 1 finding 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Or add manually to your Claude Code config (`~/.claude/settings.json`):
CLAUDE.md · 43 lines

What it actually says

workz MCP Integration

workz exposes all its operations as MCP tools so AI agents can manage worktrees directly.

Setup

claude mcp add workz -- workz mcp

Or add manually to your Claude Code config (~/.claude/settings.json):

{
  "mcpServers": {
    "workz": {
      "command": "workz",
      "args": ["mcp"]
    }
  }
}

Available Tools

Tool Description
workz_start Create a worktree with auto-synced deps and env
workz_list List all worktrees as JSON
workz_status Rich status: branch, dirty state, last commit
workz_sync Sync symlinks/env into an existing worktree
workz_done Remove a worktree (with optional force)
workz_conflicts Detect files modified in multiple worktrees

Parallel Agent Workflow

To run parallel agents on independent tasks:

  1. Use workz_start to create isolated worktrees for each task
  2. Each agent gets its own branch, deps, env — no interference
  3. Use workz_conflicts to check for overlapping file changes before merging
  4. Use workz_done to clean up when finished
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. 4d ago First seen · 43 lines · 297 tokens per session scan B 904a91547a03

Subscribe to this mod's changes

workz CLAUDE.md is an instructions file published in the GitHub repository rohansx/workz (83 stars, last pushed 1mo ago), licensed MIT. It adds 297 tokens to every session, about $0.0015 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.