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 agentmods add skills/stackblitz/bolt-slides/slidesnpx skills add stackblitz/bolt-slides --skill slidesgit clone --depth 1 https://github.com/stackblitz/bolt-slidesWhat 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 | $0.00140 | $0.04672 |
| Opus 5 | $0.00070 | $0.02336 |
| Sonnet 5 | $0.00028 | $0.00934 |
| Haiku 4.5 | $0.00014 | $0.00467 |
Grade A, and why
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 2d 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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slides — a premium, responsive, React presentation engine for Bolt
Classic paged slides (advance one at a time, present over them) — but rebuilt in Vite + React so each slide is a responsive web layout instead of a fixed 1080×607 canvas that clips. It keeps the Slidev UI you liked (the floating dock + thumbnail rail + click-builds + presenter) and adds real web interactivity.
Two halves — keep them separate:
- The engine + UI are pre-built — this repo is a complete, runnable app: the paged
engine (
src/deck/), the dock/rail chrome, the section components (src/components/), the shared CSS. Leave the engine as-is. Never regenerate it. This is the part you liked; it must look/behave identically. - The content is authored fresh, every time — the slides (topic, structure, copy, visuals, theme) are designed from scratch for this request.
Theme surface. All color, type, radius, depth, and motion live in the
:roottoken vocabulary ofsrc/styles/tokens.css. Theme a brand once, there.
⛔ Three hard rules
- Don't touch the engine — leave
src/deck/(the engine + chrome:Deck,Slide,Build,Reveal,DeckContext,icons,Annotator,useInView) untouched. Don't rewrite or paraphrase the engine or the chrome; author around it. - Author the deck from the user's REAL input — do not reskin the starter.
src/App.tsxis a throwaway that only proves it runs. Delete its slides and write a new deck. Never reuse its order, copy, placeholders, or fake names. - Center what stands alone. Ask of every slide: does it have a side visual
(a
Splitmedia panel, an image, aBrowserFrame, a chart beside text)?- No side visual (only text, or one structured block like
Comparison/Tabs/Timeline/Accordion/StatGrid) → the slide MUST be centered: use<Slide center>, or atextAlign:'center'heading withmarginInline:'auto'on every block below it. - Yes → left-aligned/asymmetric is allowed; the visual balances the text. A lone left-anchored block floating in empty space is the #1 alignment bug — never ship one. (The structured blocks self-center with built-in max-widths as a safety net, but headings/paragraphs around them are YOUR job to center.)
- No side visual (only text, or one structured block like
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.
- 2d ago First seen · 319 lines · 140 tokens per session scan A 6c173ba67ab8
slides is a skill published in the GitHub repository stackblitz/bolt-slides (902 stars, last pushed 1mo ago), licensed MIT. It adds 140 tokens to every session and 4,672 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…