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 jonZlotnik/how-to-agent --skill one-idea-per-sentencegit clone --depth 1 https://github.com/jonZlotnik/how-to-agentWrote 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/jonzlotnik/how-to-agent/one-idea-per-sentence)<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/one-idea-per-sentence"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/one-idea-per-sentence/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/jonzlotnik/how-to-agent/one-idea-per-sentence"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/one-idea-per-sentence.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 | $0.00058 | $0.00561 |
| Opus 5 | $0.00029 | $0.00280 |
| Sonnet 5 | $0.00012 | $0.00112 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
one-idea-per-sentence 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
One Idea Per Sentence
A sentence that carries two ideas makes the reader hold both while parsing the join. Technical readers are already holding the system in their head; spend their attention on the content, not the syntax. Short declarative sentences are the cheapest way to be understood.
When to use
- A sentence runs past ~25 words or stacks clauses with "and", "which", "while", or dashes
- A reader must re-read a sentence to parse it
- A paragraph discusses more than one topic
- A doc review comment says "unclear" without pointing to a specific error
Protocol
- Flag the overloaded sentences. Look for length past ~25 words, two or more conjunctions, or nested subordinate clauses.
- Split at the clause boundaries, preserving the logical relation. Give each new sentence its own subject and verb. "The parser reads the header, which contains the version, and rejects unknown versions" → "The parser reads the version from the header. It rejects unknown versions." If splitting would detach a condition or cause from what it governs ("unless", "because"), keep that join.
- Keep one topic per paragraph. The first sentence names the topic. Move stray sentences to the paragraph where they belong.
- Re-read for parse cost. If any sentence still takes two readings, split it again. Stop when each sentence parses on the first pass.
Example
Before: The exporter, which runs nightly and is configured in cron.yaml,
writes CSVs to the bucket while also pruning files older than
30 days, unless pruning is disabled.
After: The exporter runs nightly; see cron.yaml. It writes CSVs to the
bucket. It also prunes files older than 30 days unless pruning
is disabled.
Red flags (rationalizations to reject)
- "Short sentences feel choppy." — Choppy beats ambiguous. Rhythm is not a goal of reference prose.
- "The ideas are related." — Related ideas belong in the same paragraph, not the same sentence.
- "Joining shows sophistication." — It shows the reader a puzzle. Sophistication is being understood once.
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 · 45 lines · 58 tokens per session scan A a675000e0fa7
one-idea-per-sentence is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 561 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…