calibrate-tone

calibrate-tone is a command for Claude Code from Owl-Listener/ai-design-skills. It costs 11 tokens per session (423 once invoked), scanned A, original, MIT.

A command for designing a tone matrix: a table that matches situations with the way an AI should communicate.

In plain words
What is it for?
Defining tone scales, mapping them to situations, resolving conflicts, and planning how the AI shifts between tones.
Why use it?
It provides a structured way to keep the AI's voice appropriate across tasks, user moods, sensitivity levels, and changes in context.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the system-behavior-shaping plugin — 1 command shipped together

Good fit Defining tone scales, mapping them to situations, resolving conflicts, and planning how the AI shifts between tones.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/owl-listener/ai-design-skills/calibrate-tone
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/Owl-Listener/ai-design-skills

Made for: Claude Code.

Or install system-behavior-shaping, the plugin that ships this one along with the rest of its 1 command.

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 calibrate-tone

README.md
[![agentmods](https://agentmods.dev/badge/commands/owl-listener/ai-design-skills/calibrate-tone/github.svg)](https://agentmods.dev/commands/owl-listener/ai-design-skills/calibrate-tone)
Your own site
<a href="https://agentmods.dev/commands/owl-listener/ai-design-skills/calibrate-tone"><img src="https://agentmods.dev/badge/commands/owl-listener/ai-design-skills/calibrate-tone/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 calibrate-tone

Your own site · 80×15
<a href="https://agentmods.dev/commands/owl-listener/ai-design-skills/calibrate-tone"><img src="https://agentmods.dev/badge/commands/owl-listener/ai-design-skills/calibrate-tone.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 423 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 $0.00011 $0.00423
Opus 5 $0.00005 $0.00211
Sonnet 5 $0.00002 $0.00085
Haiku 4.5 $0.00001 $0.00042

Measured 11d ago against content hash 8ff1f5354835, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

calibrate-tone 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.

claude-plugin/system-behavior-shaping/commands/calibrate-tone.md · 44 lines

What it actually says

You are developing a tone calibration system. Use only skills from the system-behavior-shaping plugin. Follow this process:

Step 1: Define Tone Dimensions

Using tone-calibration:

  • List all relevant tone dimensions for this product
  • Define the scale for each dimension (e.g., formality: 1-5)
  • Provide anchor examples at each end of each scale

Step 2: Map Contexts

Identify all contexts where the AI operates:

  • Task types (creative, analytical, administrative, learning)
  • User states (onboarding, deep work, troubleshooting, returning)
  • Emotional states (calm, frustrated, excited, anxious)
  • Content sensitivity levels (casual, professional, sensitive, critical)

Step 3: Build the Tone Matrix

Using tone-calibration:

  • For each context, set values across all tone dimensions
  • Identify conflicts (where contexts overlap with different needs)
  • Resolve conflicts with priority rules

Step 4: Design Tone Transitions

Using tone-calibration and behavioral-consistency:

  • Define how tone shifts between contexts
  • Specify transition pacing (gradual vs. immediate)
  • Identify jarring transitions to avoid
  • Design bridging language for necessary sharp shifts

Step 5: Cultural Overlay

Using cultural-adaptation:

  • Identify cultural variations that affect tone settings
  • Define how the tone matrix adapts across cultural contexts
  • Specify user controls for cultural tone preferences

Step 6: Test with Scenarios

Write 10 test scenarios spanning different contexts and verify the tone matrix produces appropriate behavior for each.

Output

Deliver a complete tone calibration system:

  1. Tone dimension definitions with scales and anchors
  2. Context inventory
  3. Full tone matrix (contexts × dimensions)
  4. Transition rules and bridging language
  5. Cultural adaptation layer
  6. 10 test scenarios with expected tone outputs
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. 11d ago First seen · 44 lines · 11 tokens per session scan A 8ff1f5354835

Subscribe to this mod's changes

calibrate-tone is a command published in the GitHub repository Owl-Listener/ai-design-skills (172 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 423 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.