Borrowing it
Nothing to install: this file belongs to paztek/twinkly-mcp. 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/paztek/twinkly-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/paztek/twinkly-mcpWrote 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/paztek/twinkly-mcp/claude-md)<a href="https://agentmods.dev/instructions/paztek/twinkly-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/paztek/twinkly-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/paztek/twinkly-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/paztek/twinkly-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.05998 | $0.05998 |
| Opus 5.5 | $0.02399 | $0.02399 |
| Sonnet 5.5 | $0.01200 | $0.01200 |
| Haiku 4.5 | $0.00600 | $0.00600 |
Grade A, and why
twinkly-mcp CLAUDE.md scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- [x] **Phase 7 — Optional extras.** ✅ `src/transport/http.ts` `startHttpTransport({ port, logger, createMcpServer })` hosts the server over the SDK's `StreamableHTTPServerTransport` on a single `/mcp` endpoint with per- How it starts
The opening of the file, as written. The whole thing — 118 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
twinkly-mcp is a Model Context Protocol (MCP) server that exposes control of Twinkly smart lights to AI agents. It wraps the @twinklyjs/twinkly library and surfaces a curated, agent-friendly set of MCP tools.
Current state: Phase 8 complete (functionally done; only Phase 9 npm-publishing remains). TypeScript toolchain + CI (Phase 0), the config layer (
src/config.ts, 37 tests), the device manager (src/twinkly/device-manager.ts+src/errors.ts, 26 tests), the MCP bootstrap (src/server.ts+src/index.ts+src/tools/+src/logger.ts), the read tools (src/twinkly/format.ts+src/tools/status.ts+discover_devices), the control tools (src/tools/power.ts+color.ts+effects.ts+movies.ts), the safety layer (read-only / tool-group / admin gating viasrc/tools/shared.ts+ gatedsrc/tools/device-admin.ts), the optional extras (Streamable HTTP transportsrc/transport/http.ts+ gated realtimesrc/tools/realtime.ts), and the docs + guarded real-device smoke test (src/integration.test.ts,README.md) are in place — 137 tests (1 skipped without hardware), ~98% coverage. The server runs over stdio or Streamable HTTP (TWINKLY_TRANSPORT=http,/mcpon loopback) and exposes the full everyday surface (list_devices,discover_devices,get_device_details,get_summary,get_state,set_power,set_mode,set_color,set_brightness,set_saturation,list_effects,set_effect,list_movies,set_movie) plus the gated admin tools (set_name,set_timer, realtimesend_frame), all filterable byTWINKLY_READONLY/TWINKLY_TOOLS/TWINKLY_ALLOW_ADMIN. Only Phase 9 (npm publish / frictionless install) remains. The plan below tracks the build — update the checkboxes as phases land.
Underlying library: @twinklyjs/twinkly (v0.0.8)
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.
- 2mo ago First seen · 118 lines · 5,998 tokens per session scan A 7b4e6d634982
twinkly-mcp CLAUDE.md is an instructions file published in the GitHub repository paztek/twinkly-mcp (0 stars, last pushed 3mo ago), licensed ISC. It adds 5,998 tokens to every session, about $0.0240 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
twinkly-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| twinkly-mcp CLAUDE.mdpaztek/twinkly-mcp | Instructions file | 0 | 3mo ago | ISC | A | 5,998 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | today | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |