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/toolprint/vibe-workspace/claude-mdgit clone --depth 1 https://github.com/toolprint/vibe-workspaceWrote 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/toolprint/vibe-workspace/claude-md)<a href="https://agentmods.dev/instructions/toolprint/vibe-workspace/claude-md"><img src="https://agentmods.dev/badge/instructions/toolprint/vibe-workspace/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 | $0.01570 | $0.01570 |
| Opus 5 | $0.00785 | $0.00785 |
| Sonnet 5 | $0.00314 | $0.00314 |
| Haiku 4.5 | $0.00157 | $0.00157 |
Grade A, and why
vibe-workspace 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 5d 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 — 146 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.
Core Commands
Development Workflow
# Build and development
just build # Debug build
just build-release # Release build with optimization
just install # Install from zigbuild release artifacts
just run -- [args] # Run with arguments (e.g., just run -- --help)
# Testing and validation
just test # Run all tests
just test-mcp # Run MCP-specific tests
just pre-commit # Full validation (check, format, clippy, tests)
# Code quality
just check # Cargo check (fast compilation check)
just fmt # Format code
just clippy # Run clippy linter
just clean # Clean build artifacts
Cross-Platform Release
# Build all platform binaries
just zigbuild-release # Build for Linux x86_64, macOS x86_64/ARM64/Universal2
# Complete release workflow
just release-all # Full release: validation → GitHub → cargo publish
just validate-artifacts # Validate built binaries
just create-github-release # Create GitHub release + upload artifacts
just cargo-publish # Publish to crates.io
MCP Development
# Interactive MCP testing
just mcp-inspector # Launch Inspector UI for visual testing
just mcp-inspector-cli # CLI mode testing
just mcp-validate # Validate MCP-CLI consistency
Architecture Overview
Core Entry Point
src/main.rs- CLI argument parsing using Clap, command routing, and application orchestration- Binary name:
vibe(defined inCargo.toml) - Uses async runtime (Tokio) with full feature set
Module Structure
Workspace Management (src/workspace/)
manager.rs- CoreWorkspaceManagerstruct that coordinates all operationsconfig.rs- Configuration structures for repositories, apps, and workspace settingsconstants.rs- Paths and configuration directories (~/.toolprint/vibe-workspace/)discovery.rs- Repository discovery and scanning logicoperations.rs- Git operations (status, sync, execute commands)templates.rs- Template management for app integrationsinstall.rs- Installation and setup workflows
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.
- 5d ago First seen · 146 lines · 1,570 tokens per session scan A 4c19fc593135
vibe-workspace CLAUDE.md is an instructions file published in the GitHub repository toolprint/vibe-workspace (9 stars, last pushed 1y ago), licensed MIT. It adds 1,570 tokens to every session, about $0.0078 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
cco-mcp CLAUDE.md
Instructions for toolprint/cco-mcp, covering claude.md, project overview, development commands, build commands and build everything (backend + ui).
ratel AGENTS.md
AGENTS.md instructions for ratel-ai/ratel, covering agents.md — working in the ratel repo, build & test, rust, ts and python (from src/sdk/python/; needs uv).
OpenKB AGENTS.md
AGENTS.md instructions for VectifyAI/OpenKB, covering agents.md — openkb map for coding agents, read next, dev commands, module map (openkb/) and hard invariants.
mastra AGENTS.md
AGENTS.md instructions for mastra-ai/mastra: Unless asked, don't inspect reference or modify examples. Use the most-specific AGENTS.md; for package work, read packages/ /AGENTS.md first.
ACCESSIBILITY.md AGENTS.md
AGENTS.md instructions for mgifford/ACCESSIBILITY.md, covering repository instructions for ai coding agents, scope, when each instruction file is useful, project mission and status and required project context.
fastagent AGENTS.md
AGENTS.md instructions for fastagent-sh/fastagent, covering fastagent — agent guide, what this is, source of truth, repo map and devx principle stack.