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 kalyvask/winning-writing --skill rhythm-killergit clone --depth 1 https://github.com/kalyvask/winning-writingWrote 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/kalyvask/winning-writing/rhythm-killer)<a href="https://agentmods.dev/skills/kalyvask/winning-writing/rhythm-killer"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/rhythm-killer/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/kalyvask/winning-writing/rhythm-killer"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/rhythm-killer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00124 | $0.02417 |
| Opus 5 | $0.00062 | $0.01208 |
| Sonnet 5 | $0.00025 | $0.00483 |
| Haiku 4.5 | $0.00012 | $0.00242 |
Grade A, and why
rhythm-killer 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 10d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rhythm killer
Source: points/ai-writing-rules.md (the "Choppy short-sentence stacks" entry) and live critiques on cold-email and personal-essay drafts where the model's rhythm gave it away even after surface tells were scrubbed.
What this skill does
Two passes behind one skill. Each pass fixes a different sentence-rhythm tell:
| Target | What it flags | When to run alone |
|---|---|---|
| fragment-chain | three or more short sentences/fragments back-to-back (each under ~6 words) | When the draft has a visible staccato run ("Same apartment. Finally. Tax law travels.") |
| uniform-length | two or more consecutive sentences within ~2 words of each other in length, especially with parallel syntactic structure ("You X. You Y. You Z.") | When sentences are different in content but march at the same tempo |
Default --target all runs both passes in order: fragment-chain first (more obvious), then uniform-length (subtler, often surfaces after the chain is fixed).
How to invoke
/rhythm-killer "draft text"
/rhythm-killer --target fragment-chain "draft text"
/rhythm-killer --target uniform-length "draft text"
/rhythm-killer --target all "draft text"
Without --target, default to all.
Target 1 — fragment-chain
Three or more short sentences (under ~6 words each) in a row read as AI rhythm. The model defaults to staccato when it doesn't know how to develop a thought, so it chops the thought into fragments that look "punchy" but pattern-match to LLM output.
The trigger pattern (verbatim from a live draft):
Next year I want you here. California. Same apartment, finally. Tax law works from anywhere.
Four short sentences. Each lands. The chain doesn't — it reads as a list of beats, not a thought.
How to fix
| Pattern | Rewrite move |
|---|---|
| 3+ shorts in a row | Keep one short (the strongest, usually first or last). Absorb the others into a longer surrounding sentence. |
| Opening with a fragment + immediate restatement | Cut the restatement; the fragment carries. |
| Closing with three short summary beats | Combine into one sentence with the final beat punching. |
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.
- 10d ago First seen · 181 lines · 124 tokens per session scan A 29024916659a
rhythm-killer is a skill published in the GitHub repository kalyvask/winning-writing (13 stars, last pushed 4d ago), licensed MIT. It adds 124 tokens to every session and 2,417 once invoked, about $0.0006 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 skills, from other repositories
project-memory
Generate a project-specific context file from a brief so an AI assistant remembers your editorial constraints, voice, audience, and quality bar across sessions.
project-retrospective
Generate a LESSONS.md from a finished project: what worked, what didn't, what to reuse, what to retire — formatted for next-project carry-over.
template-selector
Recommend the right skill bundle, agent, and workflow sequence for a new project — so media professionals can start producing instead of browsing a 394-skill library.
jargon-flagger
Scans a draft and flags every instance of technical jargon, unexplained acronyms, and insider language that a general-audience reader would not understand — with a plain-language alternative for each.
multi-author-harmonizer
Reviews a text written or assembled by multiple authors and produces a detailed inconsistency report — flagging voice shifts, terminology mismatches, tonal clashes, and formatting discrepancies — with specific harmonisation recommendations for each.
passive-voice-checker
Identifies every passive-voice construction in a draft, assesses whether each weakens or serves the prose, and offers active-voice alternatives for those that should be changed — while leaving justified passives alone.