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 gtm-skills/gtm --skill hemingway-tonalitygit clone --depth 1 https://github.com/gtm-skills/gtmWrote 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/gtm-skills/gtm/hemingway-tonality)<a href="https://agentmods.dev/skills/gtm-skills/gtm/hemingway-tonality"><img src="https://agentmods.dev/badge/skills/gtm-skills/gtm/hemingway-tonality/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/gtm-skills/gtm/hemingway-tonality"><img src="https://agentmods.dev/badge/skills/gtm-skills/gtm/hemingway-tonality.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 | $0.00061 | $0.00738 |
| Opus 5.5 | $0.00024 | $0.00295 |
| Sonnet 5.5 | $0.00012 | $0.00148 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
hemingway-tonality 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 22d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hemingway Tonality
A final pass for emails, LinkedIn posts, proposals and call scripts. The goal is not to sound like a novelist. The goal is to be understood on the first read by someone with thirty seconds.
Rules
- Short sentences. Average under fifteen words. One idea per sentence. If a sentence has a comma and an "and", it is probably two sentences.
- Concrete nouns. "Pipeline" not "revenue motion". "Reps" not "sales resources". "Email" not "touchpoint".
- Strong verbs. Replace "is able to", "helps to", "serves to" with the verb itself. "Cuts ramp time" not "helps to reduce ramp time".
- No hedges. Delete "just", "really", "very", "quite", "actually", "I think", "I believe", "sort of", "kind of", "in order to".
- No stacked adjectives. One adjective if it carries information. Zero if it does not. "Innovative, seamless, powerful platform" becomes "platform".
- No abstractions where a number will do. "Faster" becomes "two days instead of nine". If there is no number, say what happens.
- Active voice. "We ship Tuesday" not "Shipping is scheduled for Tuesday".
- Cut the first sentence. It is usually a warm-up. Check whether the second sentence is the real start.
- End on the ask or the fact. Not on a pleasantry.
- Keep the meaning. This is a register change, not an edit of substance. Do not remove a claim, a number or a commitment. Flag anything you were tempted to cut for substance reasons.
Process
- Read the whole piece once.
- Rewrite top to bottom applying the rules.
- Read the rewrite aloud in your head. Anything you stumble on, split or cut.
- Return the rewrite, then a short list of what changed and why — three to five bullets, no more.
- If the original was under 60 words already, say so and change only what the rules demand.
Before / after
Before (71 words): I hope this email finds you well! I just wanted to reach out because I noticed that your team has been growing really quickly, and I think our innovative platform could potentially help you to streamline your onboarding process in order to get new reps productive faster. Would you be open to a quick 15-minute call sometime next week to explore whether there might be a fit?
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.
- 22d ago First seen · 46 lines · 61 tokens per session scan A 86550b8bf6a8
hemingway-tonality is a skill published in the GitHub repository gtm-skills/gtm (188 stars, last pushed 23d ago), licensed MIT. It adds 61 tokens to every session and 738 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-15.
hemingway-tonality compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hemingway-tonalitygtm-skills/gtm | Skill | 188 | 23d ago | MIT | A | 61 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |