Borrowing it
Nothing to install: this file belongs to llrowat/goblin-mob-boss. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/llrowat/goblin-mob-boss/main/CLAUDE.mdgit clone --depth 1 https://github.com/llrowat/goblin-mob-bossWrote 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/llrowat/goblin-mob-boss/claude-md)<a href="https://agentmods.dev/instructions/llrowat/goblin-mob-boss/claude-md"><img src="https://agentmods.dev/badge/instructions/llrowat/goblin-mob-boss/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 5.1 | $0.02144 | $0.02144 |
| Opus 5 | $0.01072 | $0.01072 |
| Sonnet 5 | $0.00429 | $0.00429 |
| Haiku 4.5 | $0.00214 | $0.00214 |
Grade A, and why
goblin-mob-boss 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 8d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goblin Mob Boss — Agent-Based Development Workflow
Project Structure
This is a Tauri v2 + React (TypeScript) desktop application with a Rust backend. The app provides a GUI/UX layer on top of Claude Code's multi-agent capabilities — configure agents, plan features interactively, choose an execution mode (Agent Teams or Subagents), then launch Claude Code to execute.
goblin-mob-boss/
├── backend/ # Rust backend (Tauri app)
│ ├── src/
│ │ ├── lib.rs # App entry, state management, plugin setup
│ │ ├── main.rs # Binary entry point
│ │ ├── commands.rs # Tauri IPC command handlers (repos, agents, features, ideation, launch, validation, PR)
│ │ ├── models.rs # Data models (AgentFile, SkillFile, Feature, TaskSpec, Repository, Preferences, ExecutionMode, SystemMap)
│ │ ├── store.rs # JSON file-based persistence (repos, features, agents, preferences, system maps)
│ │ ├── launch.rs # Launch command builder (Teams/Subagents mode)
│ │ ├── git.rs # Git operations (branches, merge, push, diff)
│ │ ├── prompts.rs # Ideation prompt templates with execution mode heuristics
│ │ ├── validators.rs # Validator execution and result aggregation
│ │ ├── templates.rs # Built-in agent definitions and feature recipes
│ │ ├── observer.rs # Execution observability (git activity polling)
│ │ ├── analytics.rs # Post-execution analysis (plan vs reality)
│ │ ├── guidance.rs # Mid-execution guidance notes
│ │ ├── heuristics.rs # Task graph analysis and mode recommendation
│ │ ├── functional_testing.rs # Functional testing loop (proof collection, QA prompts)
│ │ ├── harness.rs # Test harness process management (start/stop app under test)
│ │ └── pty.rs # PTY session management for embedded terminal
│ └── tauri.conf.json
├── frontend/ # React frontend
│ ├── components/ # Shared UI components
│ │ ├── AddRepoModal # Repository addition dialog (with folder picker)
│ │ ├── StatusBadge # Feature status indicator
│ │ ├── Terminal # xterm.js PTY terminal emulation
│ │ ├── PersistentTerminal # Portal-based terminal with session persistence
│ │ ├── CommandDisplay # Shell command transparency display
│ │ ├── ToastContainer # Auto-dismissing toast notifications
│ │ ├── ActivityLog # Feature lifecycle timeline
│ │ └── ErrorBoundary # React error boundary with retry
│ ├── pages/ # Page components
│ │ ├── HomePage # Feature launcher (describe what to build, list active features)
│ │ ├── FeatureDetailPage # Unified feature lifecycle (ideation, execution, validation, testing, PR)
│ │ ├── feature-detail/ # Sub-components for FeatureDetailPage
│ │ │ ├── PlanningComponents # TaskTable, ExecutionModeSelector, PlanHistory
│ │ │ ├── ValidationPanel # Validator results, diff summary, push status
│ │ │ └── TestingPanel # Functional testing harness, proof collection
│ │ ├── AgentsPage # Agent + Skill CRUD (tabbed: Goblins for agents, Tricks for skills)
│ │ ├── ReposPage # Repository management (validators, base branch, PR command)
│ │ ├── SettingsPage # App preferences (shell, execution defaults, model, auto-validate, functional testing)
│ │ └── SystemMapPage # Interactive system topology map (SVG visualization)
│ ├── hooks/ # React hooks
│ │ ├── useTauri # Tauri IPC wrapper
│ │ ├── useToast # Global toast notification context
│ │ ├── useTerminalSession # PTY session lifecycle context
│ │ └── useBackgroundPlanning # Background ideation tracking and polling
│ ├── types/ # TypeScript type definitions
│ ├── test/ # Test setup
│ │ └── setup.ts # Vitest global setup (Tauri mock, jest-dom)
│ └── styles.css # Global styles (dark theme)
├── Cargo.toml # Workspace root
├── package.json # Frontend dependencies
└── vite.config.ts # Vite configuration (with vitest)
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.
- 8d ago First seen · 129 lines · 2,144 tokens per session scan A a6c1e5a2f346
goblin-mob-boss CLAUDE.md is an instructions file published in the GitHub repository llrowat/goblin-mob-boss (2 stars, last pushed 4mo ago), licensed MIT. It adds 2,144 tokens to every session, about $0.0107 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.