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 vidhunnan/agentic-skills --skill post-cardgit clone --depth 1 https://github.com/vidhunnan/agentic-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/vidhunnan/agentic-skills/post-card)<a href="https://agentmods.dev/skills/vidhunnan/agentic-skills/post-card"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/post-card/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/vidhunnan/agentic-skills/post-card"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/post-card.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 | $0.00111 | $0.02004 |
| Opus 5 | $0.00056 | $0.01002 |
| Sonnet 5 | $0.00022 | $0.00401 |
| Haiku 4.5 | $0.00011 | $0.00200 |
Grade A, and why
post-card 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 10d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
post-card
Renders the visual plan into frames that read as one system, from a direction the user chose rather than one the model invented.
Instagram and Threads are visual-first, so a family that only produces text is half a skill there. The default alternatives are both bad: opening a design tool means leaving the work and rebuilding the same layout every time, and letting a model invent a look each post produces a feed where nothing matches, which is most of what a card was for.
There is a subtler failure, and it is the dangerous one. A frame is where a claim
stops being auditable. Prose can carry a hedge; twelve words in 86-point type
cannot. A card will happily state as settled the exact thing the post's own
Not claimed section refused, and unlike the caption it travels — screenshotted,
reposted, separated from everything that qualified it.
Three rules govern this skill:
- A frame may never say what the post declined to claim, and where the post is unverified, unbuilt or inconclusive the frame carries that status visibly.
- It proposes treatments; it does not choose the look. Same rule as
design-language, one level down. - It renders a direction, it does not iterate on one. This is not a design tool and should not pretend to be.
Instructions
Step 0 — Detect your surface
Using Bash availability:
- Claude Code — Bash works and there's a real filesystem. Full flow, including rasterising.
- Claude.ai — no filesystem and no browser. Emit each frame's HTML as a downloadable artifact, and say plainly that you could not rasterise it and could not verify the rendering — in particular that text may overflow, which you cannot see. Don't error.
Step 1 — Read the plan and the direction
- The post file's
## Visual planand## Alt text. posts/CARD.mdfor the direction — resolved via a CLAUDE.md declared path, an existing file, then canon.- The post's
## Not claimed, because it constrains what a frame may say.
What ships with it
1 file 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.
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.
- 10d ago First seen · 169 lines · 111 tokens per session scan A 546f7386b57d
post-card is a skill published in the GitHub repository vidhunnan/agentic-skills (2 stars, last pushed 4d ago), licensed MIT. It adds 111 tokens to every session and 2,004 once invoked, about $0.0006 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
html-ppt-zhangzara-retro-zine
A neighborhood zine on the disappearing corner shops — portraits, voices, and what a block loses when they close. Built as a decision-grade story deck for community, local readers.
html-ppt-zhangzara-studio
A photography studio's portfolio-and-rate deck — the signature work, the process, and the packages that win the brief. Built as a decision-grade design craft deck for prospective clients.
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
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.
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…