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 instructions/eqms/claude-workbench/claude-mdgit clone --depth 1 https://github.com/eqms/claude-workbenchWrote 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.
[](https://agentmods.dev/instructions/eqms/claude-workbench/claude-md)<a href="https://agentmods.dev/instructions/eqms/claude-workbench/claude-md"><img src="https://agentmods.dev/badge/instructions/eqms/claude-workbench/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.07804 | $0.07804 |
| Opus 5 | $0.03902 | $0.03902 |
| Sonnet 5 | $0.01561 | $0.01561 |
| Haiku 4.5 | $0.00780 | $0.00780 |
Grade A, and why
claude-workbench CLAUDE.md 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 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.
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 — 619 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
A Rust-based TUI (Terminal User Interface) multiplexer called "claude-workbench" that provides an integrated development environment with:
- File browser with preview pane
- Multiple embedded PTY terminals (Claude Code, LazyGit, User Terminal)
- Mouse and keyboard navigation
- Scrollback support for terminal panes
Built with Ratatui (TUI framework), Crossterm (terminal handling), and portable-pty (pseudo-terminal).
Git Push Strategy
IMPORTANT: This repository uses dual-remote push strategy. Always push to both remotes:
git push origin main # GitLab: gitlab.ownerp.io
git push upstream main # GitHub: github.com/eqms/claude-workbench.git
Both repositories must be kept in sync for all commits. This ensures the project is available as Open Source on GitHub with pre-built binaries via GitHub Actions.
Remotes:
| Remote | URL | Purpose |
|---|---|---|
| origin | [email protected]:ki/workbench.git | Primary development |
| upstream | [email protected]:eqms/claude-workbench.git | Open Source distribution |
Development Commands
Build and Run
# Build the project
cargo build
# Run in development mode
cargo run
# Build release version
cargo build --release
# Run release version
cargo run --release
# Run with custom config
cargo run -- --config path/to/config.yaml
Testing
# Run all tests
cargo test
# Run specific test
cargo test test_name
# Run tests with output
cargo test -- --nocapture
Code Quality
# Check code without building
cargo check
# Run clippy linter
cargo clippy
# Format code
cargo fmt
# Check formatting
cargo fmt -- --check
Architecture
Core Components
App State (src/app.rs)
- Main application struct holding all state
- Manages 5 panes: FileBrowser, Preview, Claude, LazyGit, Terminal
- Event loop with 16ms polling for responsive UI
- Mouse and keyboard event routing based on active pane
- PTY synchronization: syncs
cdcommands to Terminal and Claude panes when directory 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.
- 4d ago First seen · 619 lines · 7,804 tokens per session scan A 7b0f840b7431
claude-workbench CLAUDE.md is an instructions file published in the GitHub repository eqms/claude-workbench (2 stars, last pushed 1mo ago), licensed MIT. It adds 7,804 tokens to every session, about $0.0390 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.
Other instructions, from other repositories
jmux CLAUDE.md
Claude Code instructions for jarredkenny/jmux, covering claude.md, project, commands, architecture and the two-channel tmux model.
agent-of-empires AGENTS.md
AGENTS.md instructions for agent-of-empires/agent-of-empires, covering repository guidelines, where to look, commands, code rules and tests.
vibeyard CLAUDE.md
Claude Code instructions for elirantutia/vibeyard, covering claude.md, what this is, build & run, testing and architecture.
terminal-browser AGENTS.md
AGENTS.md instructions for zenbu-labs/terminal-browser, a project described as: A browser inside your terminal.
liney AGENTS.md
AGENTS.md instructions for everettjf/liney, covering liney repository collaboration guide, 交流语言 / communication language, project overview, repository layout and build and test.
superset AGENTS.md
AGENTS.md instructions for superset-sh/superset, covering superset monorepo, project structure, exception: shadcn/ui components, database and releases.