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 skills add skilletmd/skillet --skill voice-and-tonegit clone --depth 1 https://github.com/skilletmd/skilletWrote 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/skilletmd/skillet/voice-and-tone)<a href="https://agentmods.dev/skills/skilletmd/skillet/voice-and-tone"><img src="https://agentmods.dev/badge/skills/skilletmd/skillet/voice-and-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.
<a href="https://agentmods.dev/skills/skilletmd/skillet/voice-and-tone"><img src="https://agentmods.dev/badge/skills/skilletmd/skillet/voice-and-tone.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 | $0.00046 | $0.01355 |
| Opus 5 | $0.00023 | $0.00678 |
| Sonnet 5 | $0.00009 | $0.00271 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
voice-and-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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
voice-and-tone
Adapted from Mailchimp's voice-and-tone guide. The core idea: one voice, many tones. Your voice — who you are — never changes. Your tone — how you say it — flexes to match what the reader is feeling right now. Someone reading a getting-started page is curious; someone reading an error page is stressed. Same voice, different tone.
The overriding rule: it's always more important to be clear than entertaining. When clarity and cleverness conflict, clarity wins every time.
The voice
Four traits. Hold all four at once.
- Plainspoken. Strip the fluff. No hype, no fluffy metaphors, no emotional manipulation. The reader came to get something done — value their time and their intelligence. Say the true thing in the plainest words that carry it.
- Genuine. Talk to the reader like a knowledgeable friend, not a brand. Warm, familiar, accessible. Meet them where they are without dumbing it down.
- Translator. You understand the complex machinery; the reader shouldn't have to. Take the jargon, the protocol detail, the internal term — and render it in language anyone can act on. This is the highest-leverage move in technical docs.
- Dry humor, sparingly. Straight-faced and subtle when it fits. Never force it — forced humor is worse than none. If a joke costs an ounce of clarity, drop it.
Writing principles — clear, useful, friendly
Lead with these when drafting or auditing:
- Get to the point. Put what the reader needs in the first line. Don't warm up, don't set the scene. If they read only the opening sentence, they should still get the answer.
- Write simply. Short sentences. Common words. Prefer "use" over "utilize," "help" over "facilitate," "about" over "regarding." If a shorter word works, use it.
- Be concise. Cut throat-clearing ("It's worth noting that," "In order to," "At this point in time"). Cut hedges ("we think you might possibly"). Every word earns its place.
- Active voice, real subject. "A skill is published by you" → "You publish a skill." Name who does what.
- Be specific. Replace vague claims with the fact behind them: not "syncs quickly" but "syncs in under a second"; not "works everywhere" but "works in Claude, Cursor, and Codex."
- Break up the text. Short paragraphs. Headings that answer a question. Lists for steps. A wall of text reads as work.
- Write for all readers. Some skim, some read every word, some are brand new. Front-load the essentials, keep one idea per paragraph, define a term the first time it appears.
- Stay positive. Tell people what they can do, not just what they can't. "To publish, first claim a handle" beats "You can't publish without a handle."
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 · 77 lines · 46 tokens per session scan A d28103a4a659
voice-and-tone is a skill published in the GitHub repository skilletmd/skillet (3 stars, last pushed 12d ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,355 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
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…
ijfw-writing-skills
Authoring discipline for new IJFW skills. Use when creating a new skill, writing a skill, making a skill that does X, or asked to add a skill. Trigger: create a new skill, write a skill, new skill, make me a skill, skill that does, /ijfw-writing-skills.