agentmods.dev

Rubber-Duck: Instructions file for Claude Code

CLAUDE.md

Rubber-Duck CLAUDE.md is an instructions file for Claude Code from ideo/Rubber-Duck. It costs 1,515 tokens per session, scanned A, original, MIT.

Repository instructions for Rubber Duck, a project where a physical duck watches coding-agent sessions and reacts through voice, animations, and hardware controls. The instructions describe its scoring service, hooks, and main architecture.

In plain words
What is it for?
Use them when working on the scoring system, SwiftUI duck widget, voice commands, automatic hooks, or hardware reactions.
Why use it?
They explain how prompts, responses, permissions, and session events connect to the duck. This helps contributors change the project without breaking its feedback and voice behavior.

Instructions file for Claude Code

Written for Claude Code: UserPromptSubmit hook event. Also seen: reads .claude/ paths; mentions Claude Code.

This is ideo/Rubber-Duck's own configuration. It tells Claude Code how to work on Rubber-Duck itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Rubber-Duck configures →

not rated 25repo 2mo ago A scan 1,515 tokens original MIT
View source ↗ ideo/Rubber-Duck
Reuse

Borrowing it

Nothing to install: this file belongs to ideo/Rubber-Duck. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ideo/Rubber-Duck/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ideo/Rubber-Duck

Made for: Claude Code.

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 Rubber-Duck CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ideo/rubber-duck/claude-md.svg)](https://agentmods.dev/instructions/ideo/rubber-duck/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ideo/rubber-duck/claude-md"><img src="https://agentmods.dev/badge/instructions/ideo/rubber-duck/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,515 This file is loaded in full into every session.
When invoked 1,515 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01515 $0.01515
Opus 5 $0.00758 $0.00758
Sonnet 5 $0.00303 $0.00303
Haiku 4.5 $0.00152 $0.00152

Measured 8d ago against content hash 77621831e8fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Rubber-Duck 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.

CLAUDE.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rubber Duck — Claude Code Context

You are running inside the Rubber Duck project. A physical rubber duck companion is watching this session, evaluating your work, and reacting with opinions via voice, animations, and hardware actuators.

What's happening

  • Every prompt you receive and every response you generate is scored on creativity, soundness, ambition, elegance, and risk. By default this uses Apple Foundation Models on-device (~3B, free, sub-second). Optionally switches to Anthropic API (Claude Haiku) for higher-quality scoring.
  • The duck widget (a liquid glass SwiftUI duck floating on the desktop) animates based on those scores and speaks gut reactions out loud.
  • If you are running in a tmux session named "duck", the user can speak voice commands to you by saying "ducky [command]".

Hooks active in this project

These fire automatically for your session:

  • UserPromptSubmit (scripts/on-user-prompt.sh) — sends the user's prompt to the eval service
  • Stop (scripts/on-claude-stop.sh) — sends your response to the eval service
  • PermissionRequest (scripts/on-permission-request.sh) — blocks and asks the user via voice whether to allow the action. The duck will speak the question and listen for "yes" or "no". You don't need to do anything special — just proceed normally and the hook handles approval.

Architecture overview

Widget (SwiftUI, macOS 26) — owns everything: eval server, speech, serial, duck UI
    |
    HTTP+WebSocket (localhost:3333, MiniServer — zero-dep Network.framework)
    |
    hooks (shell scripts POST to /evaluate, /permission)
    |
You (Claude Code) — this session

Key files

  • widget/Sources/RubberDuckWidget/ — SwiftUI app (DuckServer, MiniServer, LocalEvaluator, ClaudeEvaluator, SpeechService, SerialManager, DuckView)
  • widget/Sources/RubberDuckWidget/MiniServer.swift — zero-dependency HTTP+WebSocket server (Network.framework + CryptoKit)
  • widget/Sources/RubberDuckWidget/DuckView.swift — liquid glass duck face with .glassEffect(), exclamation mark permission eyes
  • widget/Sources/RubberDuckWidget/ExpressionEngine.swift — maps eval scores to visual state (eye shape, hue shift, glow)
  • widget/Sources/RubberDuckWidget/DuckTheme.swift — design tokens (colors, sizes, animation constants)
  • widget/assets/duckIcon.icon — Apple Icon Composer icon bundle (compiled via actool in Makefile)
  • scripts/ — hook scripts that connect Claude Code to the eval service
  • firmware/rubber_duck_teensy40/ — Teensy 4.0 firmware for servo/LED/piezo
  • widget/Sources/RubberDuckWidget/Resources/dashboard.html — browser dashboard at localhost:3333
  • widget/Sources/RubberDuckWidget/Resources/viewer.html — Three.js 3D viewer at localhost:3333/viewer

Read the full file on GitHub · 99 lines

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. 8d ago First seen · 99 lines · 1,515 tokens per session scan A 77621831e8fb

Subscribe to this mod's changes

Rubber-Duck CLAUDE.md is an instructions file published in the GitHub repository ideo/Rubber-Duck (25 stars, last pushed 2mo ago), licensed MIT. It adds 1,515 tokens to every session, about $0.0076 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 2026-08-30.

Building agentsHardware and IoT
Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens