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 agentmods add skills/pawel-kica/claude-code-100/htmlnpx skills add Pawel-Kica/claude-code-100 --skill htmlgit clone --depth 1 https://github.com/Pawel-Kica/claude-code-100Wrote 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/pawel-kica/claude-code-100/html)<a href="https://agentmods.dev/skills/pawel-kica/claude-code-100/html"><img src="https://agentmods.dev/badge/skills/pawel-kica/claude-code-100/html.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 | $0.00015 | $0.00598 |
| Opus 5 | $0.00008 | $0.00299 |
| Sonnet 5 | $0.00003 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
html 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 5d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A single .html in the browser beats a wall of markdown. (After Thariq Shihipar's html-effectiveness.)
30+ pages to crib in examples/: decision trees, comparisons, code reviews, dashboards, SVG scenes, decks, animations, live editors. Gallery: examples/index.html.
Explicit trigger only. Read context, pick a category, ship. Don't ask what they want.
Categories
| Category | Use for |
|---|---|
| Exploration / Planning | Decision trees, option matrices |
| Code Review | Diff annotations, risk callouts |
| Design | Visual comparisons |
| Prototyping | Throwaway UI |
| Diagrams | Architecture, flows, state machines |
| Decks | Slide-style sections |
| Research | Multi-source synthesis, comparisons |
| Reports | Summaries, metrics, dashboards |
| Custom editors | One-off data tools |
Out of scope: production app UI, page redesigns. Route to a design skill.
Rules
Self-contained .html, inline CSS/JS, no build. CDN libs only when earned (Chart.js, D3, Mermaid). Mock data inline as a JS const. Throwaway by default.
Style
Minimal: cream #F6F2EA, near-black text, accent #C8553D sparingly, max-width 720-900px. No shadows, gradients, emoji. "Make it pop" → go bolder.
System sans everywhere, -apple-system,BlinkMacSystemFont,"Inter","Segoe UI",Helvetica,Arial,sans-serif, with -webkit-font-smoothing:antialiased. Headlines are the same face, weight 650, letter-spacing:-.02em. Mono (ui-monospace,Menlo,monospace) only for small-caps labels: section headers, IDs, badges, status words. No serif, no webfonts.
Stuck? Crib from examples/.
Unleashed
Trigger: "unleashed", "go wild", "make it wild".
The user often fires this just to see the power of HTML. So show them.
Mine the whole examples/ library, combine whatever fits the subject: SVG, animation, interaction, decks, live editors, motion.
Keep the cream/serif taste as the base, break any Style rule the subject earns.
Really show what HTML can do.
What ships with it
37 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/architecture-diagram.html 4.0 KB
- examples/blindspot-pass.html 27 KB
- examples/change-quiz.html 32 KB
- examples/churn-brainstorm.html 29 KB
- examples/code-review-pr.html 26 KB
- examples/code-review.html 3.7 KB
- examples/code-understanding.html 18 KB
- examples/color-grading-explainer.html 27 KB
- examples/comparison.html 3.4 KB
- examples/component-variants.html 16 KB
- examples/dashboard.html 3.1 KB
- examples/decision-tree.html 5.0 KB
- examples/design-directions.html 40 KB
- examples/design-system.html 18 KB
- examples/editor-feature-flags.html 19 KB
- examples/editor-prompt-tuner.html 21 KB
- examples/editor-triage-board.html 18 KB
- examples/exploration-code-approaches.html 14 KB
- examples/exploration-visual-designs.html 14 KB
- examples/flowchart-diagram.html 15 KB
- examples/implementation-notes.html 26 KB
- examples/implementation-plan.html 28 KB
- examples/incident-report.html 15 KB
- examples/index.html 7.2 KB
- examples/interview.html 27 KB
- examples/pitch-doc.html 29 KB
- examples/pr-writeup.html 24 KB
- examples/prototype-animation.html 12 KB
- examples/prototype-interaction.html 11 KB
- examples/reference-port.html 36 KB
- examples/research-concept-explainer.html 13 KB
- examples/research-feature-explainer.html 12 KB
- examples/slide-deck.html 16 KB
- examples/status-report.html 16 KB
- examples/svg-illustrations.html 18 KB
- examples/toolbar-mock.html 35 KB
- examples/tweakable-plan.html 36 KB
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.
- 5d ago First seen · 59 lines · 15 tokens per session scan A eff88d77035c
html is a skill published in the GitHub repository Pawel-Kica/claude-code-100 (2 stars, last pushed 12d ago), licensed MIT. It adds 15 tokens to every session and 598 once invoked, about $0.0001 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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
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…