What is tingly-box CLAUDE.md?

A set of project instructions for Tingly-Box, a technical product that connects language models to remote controls and safety checks. It puts user experience first when designing features, reviewing changes, and building the frontend.

Use it when adding or changing Tingly-Box features, reviewing pull requests, or working on its frontend and icons. It also points agents to the project's user-experience principles before they begin work.

It gives coding agents the product context and design rules they need to make consistent decisions. This reduces the risk of technically correct changes that make the product harder to use.

tingly-box CLAUDE.md — Instructions file for coding agents by tingly-dev: A set of project instructions for Tingly-Box, a technical…

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/tingly-dev/tingly-box/claude-md

Clone the repo

git clone --depth 1 https://github.com/tingly-dev/tingly-box

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tingly-dev/tingly-box/claude-md.svg)](https://agentmods.dev/instructions/tingly-dev/tingly-box/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/tingly-dev/tingly-box/claude-md"><img src="https://agentmods.dev/badge/instructions/tingly-dev/tingly-box/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 819 This file is loaded in full into every session.

When invoked 819 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00819	$0.00819
Opus 5	$0.00409	$0.00409
Sonnet 5	$0.00164	$0.00164
Haiku 4.5	$0.00082	$0.00082

Measured 4d ago against content hash bbd48534fd85, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tingly-box 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.

CLAUDE.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tingly-Box

An Intelligence Orchestrator including LLM gateway, remote control and guard rails.

Guideline

UX-First (highest priority)

Tingly-Box is a technical product, but the product itself is the core — UX always comes first. Technology has to be implemented sensibly, and sometimes it must yield. When UX conflicts with implementation convenience, the direction of compromise is always to push UX further, not to dilute it.

Before building a new feature or changing an existing one, read .design/ux-principles.md. It distills 12 judgment criteria from real work (organize information architecture around user questions; eliminate mode pickers; split name collisions; separate orthogonal axes; show concrete values instead of aliases; smart defaults over toggles; diagnostics must traverse the real path; embed education in the product; reduce visual noise; "done" ≠ locked; surface the artifact for the next action; scope side effects to the current surface), and includes a checklist usable directly in PR review.

New feature design and PR review should be explicitly checked against these principles; deviations require a clear justification.

Frontend

API related code is generated by swagger. For each new feature, use a placeholder function for api (if not support for current version).

use MUI for new frontend component.
take care of layout while add new pages.

Icons

General UI icons come from @/components/icons (Tabler icons adapted to MUI via tablerMui()). Do not import @mui/icons-material directly.

Prefer the predefined, MUI-named icons: import { Close, Add, Delete, Search } from '@/components/icons' (same API as MUI — fontSize / color semantic colors all work).
When one isn't predefined, use the generic factory: const Foo = tablerMui(IconFoo) (IconFoo from @tabler/icons-react), and add it to index.tsx if it's worth reusing.
Brand / provider logos still go through BrandIcons.tsx / ProviderIcon.tsx (Lobehub + custom SVG).
See .design/icon-hierarchy.md for details.

Read the full file on GitHub · 61 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.

4d ago First seen · 61 lines · 819 tokens per session scan A bbd48534fd85

Subscribe to this mod's changes

tingly-box CLAUDE.md is an instructions file published in the GitHub repository tingly-dev/tingly-box (346 stars, last pushed today), licensed MPL-2.0. It adds 819 tokens to every session, about $0.0041 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.

Design and UX Frontend LLM claude-code dsh dsh-plugin gateway remote-control

superdesign-skill AGENTS.md

Instructions for superdesigndev/superdesign-skill, covering project agent memory, what this repo is, skill flow invariant: two entry paths, ground truth for cli behavior and plugin packaging & release.

superdesigndev/superdesign-skill · 1,698 tokens

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.

mgifford/ACCESSIBILITY.md · 6,270 tokens

causal-memory CLAUDE.md

Claude Code instructions for JingxuanC/causal-memory, covering causal memory mcp integration, causal memory integration, after acting on a decision and observing the result, when something fails unexpectedly and when a recorded lesson turns out to be wrong.

JingxuanC/causal-memory · 680 tokens

tingly-box CLAUDE.md