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 hassancs91/claude-image-generation --skill story-html-publishergit clone --depth 1 https://github.com/hassancs91/claude-image-generationWrote 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/hassancs91/claude-image-generation/story-html-publisher)<a href="https://agentmods.dev/skills/hassancs91/claude-image-generation/story-html-publisher"><img src="https://agentmods.dev/badge/skills/hassancs91/claude-image-generation/story-html-publisher/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/hassancs91/claude-image-generation/story-html-publisher"><img src="https://agentmods.dev/badge/skills/hassancs91/claude-image-generation/story-html-publisher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00207 | $0.01618 |
| Opus 5 | $0.00103 | $0.00809 |
| Sonnet 5 | $0.00041 | $0.00324 |
| Haiku 4.5 | $0.00021 | $0.00162 |
Grade A, and why
story-html-publisher 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 12d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Story HTML Publisher
Takes everything the upstream skills produced and emits one self-contained HTML storybook: a swipe/tap player where each scene is one screen (illustration + narration text), with the playback controls in a fixed footer. It opens with a dedicated cover page — the first illustration shown clean, playing only the short spoken title. Every image and audio clip is embedded as a base64 data URI, so the single .html file works offline, opens with a double-click, and can be emailed or dropped on any static host with no assets folder.
This skill does no creative work — no new text, images, or audio. It only reads, validates, pairs, embeds, and writes. If something is missing upstream, it reports the gap rather than fabricating.
When this skill applies
The pipeline's earlier skills have run and the user wants the final output: "build the storybook", "export to HTML", "make the final file", "wrap up the pipeline".
Does NOT apply to stories that haven't been through scene-splitter + story-illustrator + story-narrator — point the user to the missing step.
Required inputs
In stories/{slug}/:
| Artifact | Producer | Path |
|---|---|---|
| Scenes spine | scene-splitter | {slug}_scenes.json |
| Image registry | story-illustrator | {slug}_images.json |
| Audio clips | story-narrator | {slug}_audio/{slug}_part_NN.mp3 |
| Title clip (optional) | story-narrator | {slug}_audio/title.mp3 |
Everything pairs by scene index: scenes[i].index = N → image from images.json.shots[] where index = N → audio {slug}_part_NN.mp3.
Workflow — four stages with one hard gate
Stage 1: Discover and validate
- Determine the
slug(user argument → the*_scenes.jsonin the working dir → ask). - Locate the three inputs. Confirm each scene has both an image (in
images.json) and an audio file. Build a pairing table: index → text snippet → image present? → audio present? - Reconstruction sanity check: the scene count in
scenes.jsonshould match the number ofshotsinimages.jsonand the number of_part_NN.mp3files. - Report findings:
Found 9 scenes, 9 images, 9 audio clips (+ title clip). All paired. Ready to build. If anything is missing, list the gaps. Don't proceed to build with gaps unless the user says "build partial" (the build script will embed what exists and leave placeholders for the rest).
What ships with it
3 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.
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.
- 12d ago First seen · 98 lines · 207 tokens per session scan A 9367a84eabf7
story-html-publisher is a skill published in the GitHub repository hassancs91/claude-image-generation (92 stars, last pushed 25d ago), licensed MIT. It adds 207 tokens to every session and 1,618 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 2026-08-30.
Other skills, from other repositories
app-mockup
Create deterministic browser, tablet, laptop, and phone mockups from real screenshots via the local TypeScript renderer in this plugin. Use for marketing visuals, store screenshots, and framed UI previews without ML image generation.
review-pnpm
Review the pnpm workspace configuration for alignment with current official best practices - dependency management, supply-chain safety, and developer experience across this monorepo. Your reply must be a plan of suggested changes: concise, actionable, structured - not only prose.
review-typescript
TypeScript setup review (shared presets in packages/typescript-config, per-app tsconfigs, TS 7 readiness) against current official best practices. USE WHEN: user runs /review-typescript or explicitly asks for this review. DO NOT USE WHEN: reviewing app code, other dev dependencies, or implementing features.
review-vite
Vite setup review (front-app vite.config.ts, build/performance options, @cloudflare/vite-plugin, devtools) against current official Vite best practices. USE WHEN: user runs /review-vite or explicitly asks for this review. DO NOT USE WHEN: reviewing app code, other dev dependencies, or implementing features.
NorthwoodsRhetoric
Output transformer — pipes any AI response through the deployed Northwoods Pack rhetoric module before showing it. Strips emoji-headed sections, splits long sentences on coordinating conjunctions, strips code blocks for chat context, collapses excessive blank lines. Preserves adult vocabulary. USE WHEN any AI response…
owd-obsidian-mind
Connect, initialize, resume, or coordinate an Obsidian Mind vault with MDevolved while preserving its local qmd/om MCP runtime, native note layout, scoped memories, private-note rules, and multi-agent writer safety. Use when a vault-manifest.json identifies template obsidian-mind, when adding MDevolved beside Obsidian…