Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/larashero3-dotcom/lieflat-html-designnpx agentmods add skills/larashero3-dotcom/lieflat-html-design/lieflat-html-deckWrote 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/larashero3-dotcom/lieflat-html-design/lieflat-html-deck)<a href="https://agentmods.dev/skills/larashero3-dotcom/lieflat-html-design/lieflat-html-deck"><img src="https://agentmods.dev/badge/skills/larashero3-dotcom/lieflat-html-design/lieflat-html-deck/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/larashero3-dotcom/lieflat-html-design/lieflat-html-deck"><img src="https://agentmods.dev/badge/skills/larashero3-dotcom/lieflat-html-design/lieflat-html-deck.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 | $0.00070 | $0.00951 |
| Opus 5 | $0.00035 | $0.00476 |
| Sonnet 5 | $0.00014 | $0.00190 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
lieflat-html-deck 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lieflat HTML Deck
What This Skill Does
Create a self-contained horizontal HTML deck. The deck should feel designed, paced, and argued, not like a template with pasted text.
This skill contains 12 deck style families. Before choosing one, read:
assets/catalog.jsonreferences/style-understanding.md
Use assets/templates/<template-id>/<language>.html as a starter. Copy it into the user's workspace before editing. Do not edit bundled templates directly.
Core Rules
- Choose one primary style for the deck. Do not make a style sampler.
- Style mixing is not a goal. If a neighboring style has a useful structure, borrow only the structural idea and restyle it back into the primary style's typography, color, spacing, material, and motion.
- Do not mechanically preserve demo tables, scorecards, image slots, timelines, or KPI blocks. Use them only when the user's content needs that structure.
- Every slide needs a role: hook, context, claim, proof, comparison, process, example, transition, or closing.
- Prefer fewer strong slides over many thin slides.
- Remove all sample names, sample dates, placeholder copy, and demo-specific metadata.
- Keep navigation,
?slide=N, keyboard controls, and canvas/WebGL fallbacks when the starter provides them.
Style Selection
If the user names a Chinese style, map it directly:
Y2K 手册->y2k-brand极客风格->geek-report镭射网格->shiny-tiles黑底闪光->pixel-report点阵编辑风->dot-matrix-lightordot-matrix-dark杂志风->editorial咨询报告->consulting-report简约测评->clean-review日光->sunrise雨天手记->rain-notes作品集->studio-photo故事集->story-field
If the user says 点阵编辑风 without specifying light or dark, choose dot-matrix-dark for technical drama and dot-matrix-light for report-like clarity.
Use consulting-report only when the deck is genuinely chart/data-heavy and centered on market, industry, competitive, investor, or business analysis. If the content is mostly text, opinion, narrative, or a strategy memo without substantial charts/tables/evidence blocks, choose a better fit such as editorial, clean-review, geek-report, rain-notes, or sunrise.
What ships with it
46 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.
- assets/catalog.json 16 KB
- assets/templates/clean-review/en.html 33 KB
- assets/templates/clean-review/zh.html 32 KB
- assets/templates/consulting-report/en.html 45 KB
- assets/templates/consulting-report/zh.html 44 KB
- assets/templates/dot-matrix-dark/en.html 40 KB
- assets/templates/dot-matrix-dark/zh.html 40 KB
- assets/templates/dot-matrix-light/en.html 40 KB
- assets/templates/dot-matrix-light/zh.html 40 KB
- assets/templates/editorial/en.html 39 KB
- assets/templates/editorial/zh.html 39 KB
- assets/templates/geek-report/en.html 35 KB
- assets/templates/geek-report/zh.html 36 KB
- assets/templates/pixel-report/en.html 48 KB
- assets/templates/pixel-report/zh.html 54 KB
- assets/templates/rain-notes/en.html 20 KB
- assets/templates/rain-notes/zh.html 22 KB
- assets/templates/shiny-tiles/en.html 44 KB
- assets/templates/shiny-tiles/zh.html 44 KB
- assets/templates/story-field/asterion_assets/apollo16_earthrise.jpg 260 KB
- assets/templates/story-field/asterion_assets/artemis_rollout.jpg 183 KB
- assets/templates/story-field/asterion_assets/artemis_sls.jpg 156 KB
- assets/templates/story-field/asterion_assets/earthrise.jpg 155 KB
- assets/templates/story-field/asterion_assets/launch_spectators.jpg 359 KB
- assets/templates/story-field/asterion_assets/moon_far_side.jpg 51 KB
- assets/templates/story-field/asterion_assets/moon_rover.jpg 518 KB
- assets/templates/story-field/asterion_assets/payload_moon.jpg 164 KB
- assets/templates/story-field/en.html 33 KB
- assets/templates/story-field/zh.html 40 KB
- assets/templates/studio-photo/en.html 32 KB
- assets/templates/studio-photo/zh.html 32 KB
- assets/templates/sunrise/en.html 53 KB
- assets/templates/sunrise/zh.html 53 KB
- assets/templates/y2k-brand/en.html 59 KB
- assets/templates/y2k-brand/zh.html 66 KB
- references/agent-workflow.md 958 B
- references/qa-checklist.md 1.5 KB
- references/style-understanding.md 6.2 KB
- scripts/audit-assets.mjs 1.9 KB runs code
- scripts/audit-languages.mjs 2.6 KB runs code
- scripts/capture-screenshots.mjs 1.4 KB runs code
- scripts/capture-template-previews.mjs 6.7 KB runs code
- scripts/capture-xhs-card.mjs 2.8 KB runs code
- scripts/capture-xhs-carousel.mjs 4.2 KB runs code
- scripts/create-design.mjs 2.3 KB runs code
- scripts/list-templates.mjs 1.1 KB runs code
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 · 82 lines · 70 tokens per session scan A dd597fdeaa8c
lieflat-html-deck is a skill published in the GitHub repository larashero3-dotcom/lieflat-html-design (86 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 951 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.