agentmods.dev

html-slides

html-slides is a skill for Claude Code, Codex from bks-lab/open-bridge. It costs 80 tokens per session (2,593 once invoked), scanned A, original, MIT.

A tool for building single-file HTML slide decks from supplied content, with presentation layouts, themes, speaker notes, and PDF export.

In plain words
What is it for?
Use it to create or refresh slide decks, add notes and agendas, prepare different presentation versions, and check the result before sending it.
Why use it?
It provides a repeatable way to turn content into a shareable presentation without relying on online assets. HTML slides are presentations viewed in a web browser.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 skills/html-slides/scripts/new-deck.py --title "Quarterly review" --lang en \.

not rated 13repo yesterday A scan 80 tokens original MIT

Good fit Use it to create or refresh slide decks, add notes and agendas, prepare different presentation versions, and check the result before sending it.

Compare 6 skills from other repositories ↓
View source ↗ bks-lab/open-bridge bks-lab.github.io
Install

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.

Clone the repo
git clone --depth 1 https://github.com/bks-lab/open-bridge
agentmods
npx agentmods add skills/bks-lab/open-bridge/html-slides

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for html-slides

README.md
[![agentmods](https://agentmods.dev/badge/skills/bks-lab/open-bridge/html-slides/github.svg)](https://agentmods.dev/skills/bks-lab/open-bridge/html-slides)
Your own site
<a href="https://agentmods.dev/skills/bks-lab/open-bridge/html-slides"><img src="https://agentmods.dev/badge/skills/bks-lab/open-bridge/html-slides/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.

agentmods 80×15 button for html-slides

Your own site · 80×15
<a href="https://agentmods.dev/skills/bks-lab/open-bridge/html-slides"><img src="https://agentmods.dev/badge/skills/bks-lab/open-bridge/html-slides.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,593 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00080 $0.02593
Opus 5.5 $0.00032 $0.01037
Sonnet 5.5 $0.00016 $0.00519
Haiku 4.5 $0.00008 $0.00259

Measured 3d ago against content hash 56ff2b31c47b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

html-slides 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 3d 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.

skills/html-slides/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HTML Slide Deck Generator

Single-file HTML presentations: a scroll-snap engine with keyboard, tracks, speaker notes and deep links, the Bridge's DESIGN.md brand or one of 10 style presets, light and dark, fonts embedded, nothing fetched from a network. The foundation (tokens, fonts, the quality gate, the send bundle) is shared with html-canvas and called from there, never copied: this skill needs skills/html-canvas/ next to it.

Decision tree

The request Do this Read
A new deck scripts/new-deck.py (Build path below) reference/slide-types.md, reference/rules.md
Bring an existing deck up to date: newer engine, changed DESIGN.md, other preset new-deck.py --refresh deck.html reference/deck-build.md
Edit the slides of an existing deck edit them by hand (outside the marker regions), then the gate reference/slide-types.md
A different cut of one deck (prep vs. live, short vs. long) data-track on slides, key F reference/slide-types.md § Engine Contract
Speaker notes, a clickable agenda <aside class="notes">, slide type 10 (Overview) reference/slide-types.md
A running simulation inside a slide new-deck.py --with-stage, a .stage element reference/stage.md
Presenting live: blank screen, jump to a slide number, zoom, language switch, notes handout built in: keys B / W, digits + Enter, Alt+click, L, data-print-notes reference/slide-types.md § Engine Contract
An optional deck feature (one of the 5 modules below) or writing one new-deck.py --with NAME (or --with all), SlideDeck.use() reference/modules.md
A presenter view on a second screen, a time budget per slide, a rehearsal with plan vs actual --with presenter, data-time="90" on slides, key P reference/modules.md § Module: presenter
Point at or mark up a slide while presenting: laser pointer, pen, marker --with draw, keys Q and D reference/modules.md § Module: draw
Reveal points one by one, walk through code line by line --with steps, data-step, data-lines reference/modules.md § Module: steps
Morph an element from one slide to the next --with morph, data-morph="name" reference/modules.md § Module: morph
A deck handed over to be read, not presented: every slide with its notes as one document --with read, key R; a send copy opens in it with --deck-attr data-read-default= reference/modules.md § Module: read
Pick a look DESIGN.md (default) or a style preset by name reference/deck-build.md § Presets
A deck in no house brand, or no DESIGN.md exists --preset <slug> presets/_template.yaml, assets/discovery-menu.html
PDF, mail, customer, external the send path below reference/output-formats.md
A new style preset fill presets/_template.yaml reference/deck-build.md § Presets
A page to read, not a deck to present use html-canvas instead

Read the full file on GitHub · 160 lines

Files

What ships with it

60 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.

Changes

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.

  1. 3d ago First seen · 160 lines · 80 tokens per session scan A 56ff2b31c47b

Subscribe to this mod's changes

html-slides is a skill published in the GitHub repository bks-lab/open-bridge (13 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 2,593 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-25.

Claude CodeCreative and mediaDesign and UXagent-memoryagent-orchestrationagentic-aiai-agentscodex
Related

Other skills, from other repositories

wireframe

Produce low-fidelity black-and-white UI wireframes as SVGs or viewer pages. Use when asked to wireframe, sketch a screen, draft a layout, make a low-fi mockup, or publish wireframes.

paperclipai/paperclip · 47 tokens

design-critique

Give a structured product design critique — user job clarity, hierarchy, affordance, error states, accessibility, and consistency — focused on what to change, in what order, and why.

paperclipai/paperclip · 42 tokens

paperclip-capsules

Generate, implement, or review Paperclip capsule visuals. Use for capsule art, agent capsules, heartbeat status capsules, identicons, capsule banks, or brand-usage validation.

paperclipai/paperclip · 41 tokens

tutti-ui-system

Use when working with @tutti-os/ui-system components, replacing local UI with shared components, querying component ids or metadata, promoting UI into shared base or business components, or maintaining UI-system storyboard inventory.

tutti-os/tutti · 46 tokens

mcp-host-styling-integration

Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.

a5c-ai/babysitter · 44 tokens

anti-slop-frontend

A mechanical, countable anti-slop checklist for AI-generated frontend. Catches the specific signatures an undirected model defaults to: AI-purple glows, Inter-everywhere, em-dashes, div-based fake screenshots, eyebrow-on-every-section, beige+brass "premium" palettes, generic Jane Doe / Acme data. Advisory layer that…

BlackBeltTechnology/pi-agent-dashboard · 147 tokens