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 insta-cardnewsgit 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/insta-cardnews)<a href="https://agentmods.dev/skills/laguna821/achmage-skills/insta-cardnews"><img src="https://agentmods.dev/badge/skills/laguna821/achmage-skills/insta-cardnews/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/laguna821/achmage-skills/insta-cardnews"><img src="https://agentmods.dev/badge/skills/laguna821/achmage-skills/insta-cardnews.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 | $0.00098 | $0.02261 |
| Opus 5 | $0.00049 | $0.01130 |
| Sonnet 5 | $0.00020 | $0.00452 |
| Haiku 4.5 | $0.00010 | $0.00226 |
Grade A, and why
insta-cardnews 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
insta-cardnews — Instagram 3:4 photo card-news
Make an Instagram-feed card-news series: 1080×1440 px, 3:4 portrait, up to 20 cards (cover included). Every card is one dedicated, full-bleed photo with a single legibility filter and Korean text laid on top as real HTML/SVG. Output = an editable HTML proof plus carousel-ready per-card PNGs.
The one principle (inherited, then inverted)
이미지는 재료이고, HTML은 진실이다 — images are material; HTML is truth. Photos supply mood, texture, and background. Every word, number, and chart is real HTML/SVG — never baked into the image. This keeps cards editable, sharp at any zoom, and legible.
The inversion from raw5-deck: raw5-deck reuses 5 images across 30 landscape slides by cutting each into circles/arches/frames. This skill does the opposite — one purpose-built image per card. Because each image already fills its own card, the entire "cut an image into shapes" half of the design library is dropped. All that remains is the legibility-treatment family: lay a photo full-bleed, put one filter over it, and set Korean text so it reads. That makes the pattern much simpler than a deck.
What each card is (3 layers, always)
[ bg image ] one photo, background-size:cover, filling 1080×1440
[ filter/scrim ] ONE treatment from the kept family (wash / tone / blend / material / luma / halftone / paper-grain)
[ content ] Korean headline + short body + footer — real HTML/SVG, padded, inside the safe zone
The 3 presets (pick ONE per series — this is what makes the carousel look like a set)
- A · Dark Wash — full-bleed photo + dark scrim (
material-image-card/ dark tone / paper-grain), white text, one coral/red accent, dark LUT grade. Dramatic, impactful. Default. - B · Brand Tone — full-bleed photo + brand-color
multiplyoverlay (tone-scene / neon), white text, brand accent, LUT toward the brand hue. Cohesive branded series. - C · Light Editorial — photo washed / luma-masked into a light text zone, navy/ink text on light, coral accent, light LUT. Report/editorial feel.
What ships with it
26 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 1.0 KB
- examples/placeholder-proof.html 11 KB
- examples/summer-night/cardnews-proof.html 10 KB
- examples/summer-night/cards/card01.png 1867 KB
- examples/summer-night/cards/card02.png 1998 KB
- examples/summer-night/cards/card03.png 1845 KB
- examples/summer-night/cards/card04.png 1853 KB
- examples/summer-night/cards/card05.png 1756 KB
- examples/summer-night/cards/card06.png 1799 KB
- examples/summer-night/cards/card07.png 1826 KB
- examples/summer-night/cards/card08.png 1884 KB
- examples/summer-night/export/card01.png 1097 KB
- examples/summer-night/export/card02.png 1092 KB
- examples/summer-night/export/card03.png 1046 KB
- examples/summer-night/export/card04.png 910 KB
- examples/summer-night/export/card05.png 936 KB
- examples/summer-night/export/card06.png 1015 KB
- examples/summer-night/export/card07.png 1243 KB
- examples/summer-night/export/card08.png 1168 KB
- export-cards.ps1 3.1 KB runs code
- references/01-card-planner.md 3.6 KB
- references/02-image-prompts.md 4.2 KB
- references/03-filter-presets.md 3.5 KB
- references/04-card-runtime-css.md 11 KB
- references/05-export-and-qa.md 3.8 KB
- references/06-master-prompts.md 2.4 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.
- 11d ago First seen · 109 lines · 98 tokens per session scan A 86ee15763987
insta-cardnews is a skill published in the GitHub repository laguna821/Achmage-Skills (5 stars, last pushed 12d ago), licensed Apache-2.0. It adds 98 tokens to every session and 2,261 once invoked, about $0.0005 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
imagegen-frontend-web
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not…
brandkit
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…
sandbase
Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval. Use sandbasediscover before building custom integrations or declaring external data inaccessible; prefer an existing dedicated tool or API key when the…
video-frames
Extract a single frame from a local video at the first frame, a timestamp, or a zero-based frame index using FFmpeg.
openclaw-brand
Apply OpenClaw visual identity to logos, typography, imagery, voice, documents, presentations, social graphics, and launch materials. Use when the task changes brand identity rather than ordinary product UI or public-page composition.
image-gen
Generate images from text prompts via DashScope/Qwen. Use when creating, drawing, or illustrating images.