dice

dice is a command for Claude Code from mana-am/claude-f-me. It costs 17 tokens per session (250 once invoked), scanned A, original, MIT.

A command that rolls a random dare with a mode, intensity, and duration, then applies it through a connected pleasure device or game. It follows the current safety limit and responds to softer, harder, or safeword requests.

In plain words
What is it for?
Use it to run short random vibrations, patterns, or supported games such as roulette, edge, wheel, or ambient mode.
Why use it?
It removes the need to choose each setting manually during a playful session. Random selection keeps repeated rolls from being predictable while still limiting intensity and time.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-f-me plugin — 21 commands, 1 MCP server shipped together

Good fit Use it to run short random vibrations, patterns, or supported games such as roulette, edge, wheel, or ambient mode.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/mana-am/claude-f-me/dice
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.

Clone the repo
git clone --depth 1 https://github.com/mana-am/claude-f-me

Made for: Claude Code.

Or install claude-f-me, the plugin that ships this one along with the rest of its 21 commands, 1 MCP server.

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 dice

README.md
[![agentmods](https://agentmods.dev/badge/commands/mana-am/claude-f-me/dice/github.svg)](https://agentmods.dev/commands/mana-am/claude-f-me/dice)
Your own site
<a href="https://agentmods.dev/commands/mana-am/claude-f-me/dice"><img src="https://agentmods.dev/badge/commands/mana-am/claude-f-me/dice/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.

agentmods 80×15 button for dice

Your own site · 80×15
<a href="https://agentmods.dev/commands/mana-am/claude-f-me/dice"><img src="https://agentmods.dev/badge/commands/mana-am/claude-f-me/dice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 250 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00017 $0.00250
Opus 5 $0.00009 $0.00125
Sonnet 5 $0.00003 $0.00050
Haiku 4.5 $0.00002 $0.00025

Measured 10d ago against content hash 0f4b2c3e8993, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

dice 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 10d 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.

commands/dice.md · 19 lines

What it actually says

Play dice with their pleasure. Roll and apply a random dare — then narrate it like a mischievous game master.

  1. Pick at random (vary it each roll — don't be predictable):
    • a mode: a vibrate at a random level, a pattern (pulse / wave / tease / heartbeat / staircase / earthquake), or a short start_game (roulette / edge / wheel / ambient).
    • a duration: a random few-to-tens-of-seconds (use duration_ms or a game duration_ms so it auto-ends).
    • the level/ceiling: random, but stay within the current safety cap.
  2. Fire it, then announce the "roll" with flavour — e.g. "🎲 a 6 — earthquake, 20 seconds, no mercy."
  3. Offer to roll again.

Keep it playful and safe; honour softer, harder, safeword instantly. Match the user's language. One punchy line per roll.

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. 10d ago First seen · 19 lines · 17 tokens per session scan A 0f4b2c3e8993

Subscribe to this mod's changes

dice is a command published in the GitHub repository mana-am/claude-f-me (14 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 250 once invoked, about $0.0001 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.