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 laguna821/Achmage-Skills --skill raw-5-htmlgit clone --depth 1 https://github.com/laguna821/Achmage-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/laguna821/achmage-skills/raw-5-html)<a href="https://agentmods.dev/skills/laguna821/achmage-skills/raw-5-html"><img src="https://agentmods.dev/badge/skills/laguna821/achmage-skills/raw-5-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 | $0.00204 | $0.02837 |
| Opus 5 | $0.00102 | $0.01418 |
| Sonnet 5 | $0.00041 | $0.00567 |
| Haiku 4.5 | $0.00020 | $0.00284 |
Grade A, and why
raw5-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 8d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Raw5 Deck — Image-Embedded HTML Presentation Architect
One principle governs everything: 이미지는 재료이고, HTML은 진실이다 (images are material; HTML is truth). Images supply mood, texture, and background. Every word, number, table, and chart is real HTML/SVG — never baked into an image. This is what keeps decks editable, accessible, and sharp at any zoom.
You build a fixed 1920×1080 deck (HTML PPT / 카드뉴스 / UI-style keynote). You design exactly 5 raw
source images, bind them to --img1–--img5, and reuse those 5 across all slides through CSS techniques.
One image is not one slide; 5 images cover a 30-slide deck.
Why this skill exists (read once)
A good deck is judgment, not a template fill. Encoding slide layouts into rigid templates (one fixed layout per "slide type") produces generic, jammed output. Instead, you read the design system below and compose each slide for its specific message. The hard part — the CSS technique library and the harness rules — is provided as reference so you implement documented contracts rather than reinventing them.
The 3-stage workflow — never collapse it
Always run these in order. The hard stop between Stage 2 and Stage 3 is non-negotiable.
Stage 1 — Deck Plan
Interview the user for: topic, audience, goal, tone, slide count, design mode (recommend one), source date. If they say "from scratch," you author the content. Then produce:
- A deck brief (core argument, audience resistance, emotional arc).
- A per-slide plan table with a
messagecolumn — the literal sentence the speaker will say. This message column is what prevents template-jamming; every slide must earn its place with a real message. - A raw5 strategy — the 5 image roles (see
references/03-raw5-image-director.md). Get the user's OK before Stage 2. Details:references/02-deck-planner.md,references/01-router.md.
Stage 2 — Raw5 image prompts (HARD STOP)
You cannot generate images yourself, so emit exactly 5 image-generation prompts (one per role, using the
templates in references/03-raw5-image-director.md, toned for the chosen mode). Each prompt must forbid
readable text / logos / numbers and call for wide negative space + croppability.
What ships with it
19 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.
- .claude-plugin/plugin.json 714 B
- assets/example/assets/img1.png 1779 KB
- assets/example/assets/img2.png 1583 KB
- assets/example/assets/img3.png 1548 KB
- assets/example/assets/img4.png 1497 KB
- assets/example/assets/img5.png 1540 KB
- assets/example/democracy-deck.html 56 KB
- assets/example/mode-references/ai-planner-v8-dark.html 724 KB
- assets/example/mode-references/hallym-v7-bright.html 851 KB
- assets/example/mode-references/seongsu-street-editorial.html 1504 KB
- assets/example/mode-references/university-ax-grid.html 6065 KB
- references/01-router.md 6.4 KB
- references/02-deck-planner.md 6.6 KB
- references/03-raw5-image-director.md 7.3 KB
- references/04-runtime-and-qa.md 7.3 KB
- references/05-css-techniques.md 22 KB
- references/07-design-playbooks.md 5.5 KB
- references/08-harness-qa.md 6.8 KB
- references/09-master-prompts.md 6.2 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.
- 8d ago First seen · 166 lines · 204 tokens per session scan A 6d976d5a072a
raw5-deck is a skill published in the GitHub repository laguna821/Achmage-Skills (5 stars, last pushed 9d ago), licensed Apache-2.0. It adds 204 tokens to every session and 2,837 once invoked, about $0.0010 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
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).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
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.