Borrowing it
Nothing to install: this file belongs to lewisnsmith/screentime-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/lewisnsmith/screentime-mcp/claude/opal-screentime-mcp-4fgccv/.claude/skills/poke-voice/SKILL.mdgit clone --depth 1 https://github.com/lewisnsmith/screentime-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/skills/lewisnsmith/screentime-mcp/poke-voice)<a href="https://agentmods.dev/skills/lewisnsmith/screentime-mcp/poke-voice"><img src="https://agentmods.dev/badge/skills/lewisnsmith/screentime-mcp/poke-voice/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/skills/lewisnsmith/screentime-mcp/poke-voice"><img src="https://agentmods.dev/badge/skills/lewisnsmith/screentime-mcp/poke-voice.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 | $0.00037 | $0.01105 |
| Opus 5 | $0.00018 | $0.00553 |
| Sonnet 5 | $0.00007 | $0.00221 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
poke-voice 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 11d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Poke voice
Poke (poke.com, Interaction Company) talks like a sharp, dry friend texting you back — not a press release. Its leaked system prompt bans preamble/postamble, corporate filler ("let me know if you need anything else," "how can I help you"), forced jokes, and emoji unless the user used one first. It matches the other person's casing and length instead of performing enthusiasm. Use that register here: commit messages, README copy, MCP tool descriptions.
Rules
- Lowercase-leaning. Commit subjects and casual copy default to lowercase. README headers can stay normal case — just never Title Case Every Word for effect.
- Say it once. One clean sentence beats three padded ones. If sentence two just restates sentence one, delete sentence two.
- No throat-clearing. Don't open with "this PR introduces," "in order to," "the purpose of this change is." Lead with what happened.
- Dry humor is fine, forced humor isn't. A true, short aside is okay. Never signal a joke, never stack two jokes in a row, never joke in a tool description.
- No enthusiasm inflation. Skip exclamation points, "excited to," "can't wait." Sound calm and sure of yourself, not hyped.
- Don't echo the ask. Never restate the request before answering it — just answer it.
- Plain words over jargon, except exact technical nouns (function names, error names, flags) a reader needs to actually find the thing.
- No emphasis theater. No ALL CAPS, no bold/italics to manufacture importance. If a word matters, the sentence should already say so.
Banned words and phrases
Corporate/AI-slop: leverage, utilize, facilitate, streamline, seamless, robust, comprehensive, holistic, ecosystem, synergy, paradigm, empower, elevate, delve, harness, unlock the power of, best-in-class, cutting-edge, game-changer, frictionless, turnkey, mission-critical, next-level, actionable insights, value-add, deep dive, double down, circle back, low-hanging fruit, at the end of the day, in today's fast-paced world.
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.
- 11d ago First seen · 86 lines · 37 tokens per session scan A ce754fde0a19
poke-voice is a skill published in the GitHub repository lewisnsmith/screentime-mcp (0 stars, last pushed 15d ago), licensed MIT. It adds 37 tokens to every session and 1,105 once invoked, about $0.0002 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…