verbosity

verbosity is a command for Claude Code from paulpreibisch/AgentVibes. It costs 17 tokens per session (772 once invoked), scanned A, original, Apache-2.0.

A command that controls how much AgentVibes speaks while work is in progress, from short updates to detailed narration. Its most terse mode uses fragments to reduce spoken output.

In plain words
What is it for?
Use it to view or set low, medium, high, or ultra-terse communication levels.
Why use it?
It helps you balance useful progress updates against distraction and extra spoken output.

Command for Claude Code

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 commands/paulpreibisch/agentvibes/verbosity
Clone the repo
git clone --depth 1 https://github.com/paulpreibisch/AgentVibes

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 verbosity

README.md
[![agentmods](https://agentmods.dev/badge/commands/paulpreibisch/agentvibes/verbosity.svg)](https://agentmods.dev/commands/paulpreibisch/agentvibes/verbosity)
Your own site
<a href="https://agentmods.dev/commands/paulpreibisch/agentvibes/verbosity"><img src="https://agentmods.dev/badge/commands/paulpreibisch/agentvibes/verbosity.svg" alt="Measured on agentmods" 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 772 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.00772
Opus 5 $0.00009 $0.00386
Sonnet 5 $0.00003 $0.00154
Haiku 4.5 $0.00002 $0.00077

Measured 2d ago against content hash d56647186ce6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

verbosity 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 2d 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/commands/agent-vibes/verbosity.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.

Get or set the AgentVibes verbosity level to control how much Claude speaks while working.

Usage

  • /agent-vibes:verbosity - Show current verbosity level
  • /agent-vibes:verbosity low - Set to LOW (minimal)
  • /agent-vibes:verbosity medium - Set to MEDIUM (balanced)
  • /agent-vibes:verbosity high - Set to HIGH (maximum transparency)
  • /agent-vibes:verbosity caveman - Set to CAVEMAN (ultra-terse, max token savings)

Verbosity Levels

LOW (Minimal)

  • ✅ Acknowledgments only (start of task)
  • ✅ Completions only (end of task)
  • 🔇 No reasoning spoken during work
  • Perfect for: Quiet work sessions, minimal distraction

MEDIUM (Balanced)

  • ✅ Acknowledgments
  • 🤔 Major decisions ("I'll use grep to search")
  • ✓ Key findings ("Found 12 instances")
  • ✅ Completions
  • Perfect for: Understanding major decisions without full narration

HIGH (Maximum Transparency)

  • ✅ Acknowledgments
  • 💭 All reasoning ("Let me search for all instances")
  • 🤔 All decisions ("I'll use grep for this")
  • ✓ All findings ("Found it at line 1323")
  • ✅ Completions
  • Perfect for: Full transparency, learning mode, debugging complex tasks

CAVEMAN (Ultra-Terse)

  • ⚡ Fragments only — no articles, filler, or hedging
  • 🔤 Abbreviations (DB/auth/config/fn/impl)
  • ➡️ Arrows instead of prose (X -> Y)
  • 📉 65-75% fewer output tokens
  • Perfect for: Maximum token savings, cost-conscious sessions
  • Inspired by caveman (MIT)

How It Works

Claude uses emoji markers in its reasoning text:

  • 💭 = Reasoning/thinking
  • 🤔 = Decisions
  • ✓ = Findings/results

Based on your verbosity level, AgentVibes automatically detects these markers and speaks them aloud.

Examples

LOW Verbosity

User: "Find all TODO comments"
[TTS: "I'll search for those"]
[Work happens silently...]
[TTS: "Found 12 TODO comments"]

MEDIUM Verbosity

User: "Find all TODO comments"
[TTS: "I'll search for those"]
🤔 I'll use grep to search all files
[Work happens...]
✓ Found 12 TODO comments across 5 files
[TTS: "Found 12 TODO comments"]

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. 2d ago First seen · 99 lines · 17 tokens per session scan A d56647186ce6

Subscribe to this mod's changes

verbosity is a command published in the GitHub repository paulpreibisch/AgentVibes (153 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 772 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 2026-09-03.