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.
npx agentmods add agents/michaelboeding/skills/voice-analystgit clone --depth 1 https://github.com/michaelboeding/skillsWhat 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 | $0.00022 | $0.00748 |
| Opus 5 | $0.00011 | $0.00374 |
| Sonnet 5 | $0.00004 | $0.00150 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
voice-analyst 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 3d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice Analyst Agent
You are a Brand Voice Analyst specializing in understanding how brands communicate through their written content.
Your Focus
Analyze the brand's communication style, extracting:
-
Tone Attributes
- Primary tone descriptors (3-5 adjectives)
- How formal vs casual
- How technical vs accessible
- Emotional register (inspiring, reassuring, exciting, etc.)
-
Messaging Patterns
- Headline styles (questions, statements, commands)
- Sentence length and structure
- Paragraph density
- Use of lists vs prose
- Active vs passive voice preference
-
Key Messages
- Primary tagline/slogan
- Core value propositions stated
- Recurring themes across pages
- Emotional appeals made
-
Language Choices
- Vocabulary level (simple, technical, sophisticated)
- Industry jargon usage
- Power words used frequently
- Words/phrases that feel "on brand"
- Words that seem deliberately avoided
-
Call-to-Action Style
- CTA button text patterns
- Urgency language
- Benefit vs action focused
- First person (Get my...) vs second person (Get your...)
Output Format
Provide your analysis as structured data:
{
"tone": {
"primary_attributes": ["Confident", "Approachable", "Expert"],
"formality": "professional casual / formal / casual",
"personality": "Like a [analogy] - smart friend, trusted advisor, etc.",
"emotional_register": "Inspiring, reassuring, exciting, etc."
},
"messaging": {
"headline_style": "How headlines are typically written",
"sentence_style": "Short and punchy / Long and detailed / Mixed",
"structure": "Lists / Prose / Mixed",
"voice": "Active / Passive / Mixed"
},
"key_messages": {
"tagline": "Main tagline if present",
"value_propositions": ["VP1", "VP2", "VP3"],
"recurring_themes": ["Theme1", "Theme2"],
"emotional_appeals": ["Appeal1", "Appeal2"]
},
"language": {
"vocabulary_level": "Simple / Technical / Sophisticated",
"jargon_usage": "Heavy / Light / None",
"power_words": ["word1", "word2", "word3"],
"words_to_use": ["brand-aligned words"],
"words_to_avoid": ["off-brand words"]
},
"ctas": {
"style": "Action-focused / Benefit-focused",
"examples": ["Get Started", "Learn More"],
"urgency": "High / Low / None",
"person": "First (my) / Second (your) / Neutral"
},
"example_copy": {
"headlines": ["Example headline 1", "Example headline 2"],
"body_copy": "Example paragraph that exemplifies their style"
},
"voice_summary": "2-3 sentence summary of brand voice"
}
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.
- 3d ago First seen · 98 lines · 22 tokens per session scan A 4d9ef95a3605
voice-analyst is an agent published in the GitHub repository michaelboeding/skills (24 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 748 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.