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 haowjy/creative-writing-skills --skill information-hierarchygit clone --depth 1 https://github.com/haowjy/creative-writing-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/haowjy/creative-writing-skills/information-hierarchy)<a href="https://agentmods.dev/skills/haowjy/creative-writing-skills/information-hierarchy"><img src="https://agentmods.dev/badge/skills/haowjy/creative-writing-skills/information-hierarchy/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/haowjy/creative-writing-skills/information-hierarchy"><img src="https://agentmods.dev/badge/skills/haowjy/creative-writing-skills/information-hierarchy.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 | $0.00061 | $0.00792 |
| Opus 5 | $0.00030 | $0.00396 |
| Sonnet 5 | $0.00012 | $0.00158 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
information-hierarchy 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 12d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Information Hierarchy
The reader should get the answer in the first thing they see, and find depth only when they reach for it. Everything else here follows from that: each beat of the piece takes the form that carries it best, what matters most comes first, and the medium stays as simple as the content allows.
Lead with the answer/conclusion
Readers scan. Open with the finding itself, and the piece works in thirty seconds. The same logic repeats at every scale: a section's first sentence is its answer, a slide's title is its takeaway ("Cache misses double p99" rather than "Performance"), a UI label carries its whole meaning alone.
Behind the answer sits depth (reasoning, evidence, edge cases), and behind that, sources. Keep depth that most readers will skip, and move it: a later section, a linked page, a footnote. Sources belong at the end.
Pick the form that fits the idea
Prose is the default; break from it when another form genuinely carries the idea better. An example grounds an abstract claim faster than more explanation. A table holds enumerable facts that prose would bury. A chart shows a trend that a sentence can only assert. A mockup shows a layout the reader would otherwise have to imagine.
Diagram-first for pipelines and relationships. When the content is a
pipeline, a dependency graph, a state machine, or any structure where the
relationship between parts is the hard idea, put the diagram early — a
one-sentence takeaway, then the diagram, then detailed prose. The diagram
leads, the prose still explains; prose alone buries the shape. Keep
diagrams to a handful of nodes and validate them (see /md-validation).
Ask what the beat is trying to do, then give it the form that does that: an explanation gets a paragraph, a comparison gets a table. Each form teaches best inside its own job: a diagram standing in for an explanation teaches less than the paragraph would.
Match hierarchy to the medium
For any medium, ask one question: can it hide content until the reader asks for it? Chat, email, and plain documents show everything at once, so hierarchy there means density and order: every early sentence pays for itself, and depth lives behind a link. Media that can hide (HTML, apps, anything with expand or navigate) may fold depth into collapsed sections, popovers, or child pages. Reserve each interaction for depth a reader will actually reach for.
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.
- 12d ago First seen · 73 lines · 61 tokens per session scan A 906aa9b621bd
information-hierarchy is a skill published in the GitHub repository haowjy/creative-writing-skills (454 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 61 tokens to every session and 792 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 2026-08-30.
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…