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 davekindl/skills --skill content-atomizergit clone --depth 1 https://github.com/davekindl/skillsWrote 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/davekindl/skills/content-atomizer)<a href="https://agentmods.dev/skills/davekindl/skills/content-atomizer"><img src="https://agentmods.dev/badge/skills/davekindl/skills/content-atomizer.svg" alt="Measured on agentmods" 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 | $0.00163 | $0.01797 |
| Opus 5 | $0.00081 | $0.00898 |
| Sonnet 5 | $0.00033 | $0.00359 |
| Haiku 4.5 | $0.00016 | $0.00180 |
Grade A, and why
content-atomizer 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 6d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CONTENT ATOMIZER
One piece in, ten pieces out. Platform-native, not copy-pasted. Quality-gated.
Platform Specs (hard constraints per format)
| # | Format | Length | Structure Rule | Engagement Driver |
|---|---|---|---|---|
| 1 | 1,300-1,900 chars sweet spot | Hook in first 140 chars (mobile). Short paragraphs. End with question. | Dwell time + comment depth | |
| 2 | X Thread | 280/tweet, 6-8 tweets | Tweet 1 = hook. Each tweet = one idea. Final = CTA + link in reply. | Saves + follows. 6-9 tweets = 3.1x saves |
| 3 | Newsletter | 300-600 words | Headline + 2-3 para summary + key takeaway bullet + CTA | Click-through rate |
| 4 | IG Carousel | 8-10 slides, <30 words/slide | Slide 1 = hook (<10 words). 1080x1350 portrait. Last = "save this" CTA | Swipe-through + saves |
| 5 | Quote Graphics | <150 chars/graphic | 1080x1080 square. Text <20% of area. High contrast. Attribution. | Saves + shares |
| 6 | Video Script | 15-30 sec (75 words for 30s) | Hook 2-3 sec. Hook > Problem > Solution > CTA. 9:16 vertical. | Completion rate |
| 7 | Podcast Notes | 300-600 words | Title with keyword. Summary. Numbered takeaways. Timestamps. Resources. | SEO discovery |
| 8 | Email Sequence | 3-5 emails, 200-400 words each | E1: hook. E2: evidence. E3: framework. E4: proof. E5: CTA. | Open rate + clicks |
| 9 | Infographic | 6-8 sections | Title > Problem stat > Key findings > Framework > Data > CTA. 1080px wide. | Saves + backlinks |
| 10 | Blog Summary | 150-160 chars meta, 1,000-1,500 words post | H2 every 200-300 words. TL;DR at top. Bullets. Internal links. | Organic search |
3-Pass Extraction Pipeline
Pass 1: Skeleton Extraction
Parse source into argument map: thesis, supporting claims (3-7), evidence per claim, counterarguments, conclusion/CTA.
Pass 2: Moment Mining
Scan for 6 types of scroll-stopping content:
- Contrarian takes -- challenges conventional wisdom
- Data points -- specific numbers, percentages, findings
- Frameworks -- step-by-step processes, matrices, models
- Stories -- anecdotes, case studies, transformations
- Quotable lines -- standalone sentences (<150 chars)
- Questions -- rhetorical or provocative
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.
- 6d ago First seen · 139 lines · 163 tokens per session scan A 290e09f03d2a
content-atomizer is a skill published in the GitHub repository davekindl/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 163 tokens to every session and 1,797 once invoked, about $0.0008 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…