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 sammcj/agentic-coding --skill bento-slidesgit clone --depth 1 https://github.com/sammcj/agentic-codingWrote 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/sammcj/agentic-coding/bento-slides)<a href="https://agentmods.dev/skills/sammcj/agentic-coding/bento-slides"><img src="https://agentmods.dev/badge/skills/sammcj/agentic-coding/bento-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.
<a href="https://agentmods.dev/skills/sammcj/agentic-coding/bento-slides"><img src="https://agentmods.dev/badge/skills/sammcj/agentic-coding/bento-slides.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 | $0.00031 | $0.02897 |
| Opus 5.5 | $0.00012 | $0.01159 |
| Sonnet 5.5 | $0.00006 | $0.00579 |
| Haiku 4.5 | $0.00003 | $0.00290 |
Grade A, and why
bento-slides scanned grade A with 1 finding 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 22d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://bento.page/releases/slides/Bento_Slides.bento.html -o "<Topic>.bento.html" How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring Bento decks
A Bento deck is one self-contained .bento.html file: a compressed app runtime plus the document as plain JSON in one block:
<script type="application/bento+json" id="bento-doc"> { "format":"bento/slides", ... } </script>
- Edit that block only, in place. Leave the runtime untouched.
render_check.mjs --writewrites the block for you. A hand-written splice must escape every<in the JSON as its unicode escape (a backslash followed byu003c), so the block never contains a literal</script>and a build script can find the block's end at the first</script>after the opening tag.- Chat context (no filesystem): the user copies the JSON out (Save > Copy compact JSON) and pastes your replacement back (Save > Replace from JSON).
window.bento.loadDoc(json)does the same from the console.
Before touching an existing deck
- Ask the user to close the deck in their browser. A save from the open tab overwrites your edit. Autosave keeps a recovery snapshot in IndexedDB keyed by
docId, so a stale tab offers to "restore" the old version on the next open; tell the user to pick Discard. - If the
#bento-docblock contains"format":"bento/enc", the deck is password-encrypted. Stop and tell the user; plain JSON written over it destroys the ciphertext. - Leave
collabas found. Keys mint at creation and every save writes them, so nearly every saved deck carriesownerPriv: anyone with the file can join its live session.- Deleting
collabsevers the owner from their own room while sent copies keep the old one. - Tell the user once that the file contains session keys. Hand-outs: Share > View-only copy. Leaked file: Share > Reset access.
- Every save also stamps CRDT state into
collab.sync; the next open merges it with the room, so elements a script deleted come back.render_check.mjs --writedropscollab.sync. If edits still reappear, the owner's other tabs are in the room: setcollab.ontofalseand have the user Share > Reset access. - Otherwise set
collab.ontofalseonly when the user asks to stop sharing. Change that one field and keep the keys.
- Deleting
What ships with it
8 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.
- 22d ago Changed · +9 lines b0e8781d0ec8
- 23d ago Changed · -16 lines · +9 tokens per session 69baadc13da8
- 24d ago Changed · +28 lines 3a9b4c03aa40
- 25d ago First seen · 91 lines · 22 tokens per session scan A 40be4a4e0bb7
bento-slides is a skill published in the GitHub repository sammcj/agentic-coding (164 stars, last pushed 3d ago), licensed Apache-2.0. It adds 31 tokens to every session and 2,897 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-21.
Other skills, from other repositories
ai-interface-reviewer
Audit AI-powered interfaces against the uxuiprinciples Part V taxonomy — 44 principles covering transparency, trust calibration, human override, consent, agentic workflows, and conversational design. Returns structured findings with severity and remediation. API key optional — enriched output requires…
stitch-ui-design
Expert guidance for crafting effective prompts in Google Stitch, the AI-powered UI design tool by Google Labs. This skill helps create precise, actionable prompts that generate high-quality UI designs for web and mobile applications.
figma-automation
Automate Figma tasks via Rube MCP (Composio): files, components, design tokens, comments, exports. Always search tools first for current schemas.
rayden-use
Build and maintain Rayden UI components and screens in Figma via Figma MCP with full design token enforcement.
rayden-code
Generate React code with Rayden UI components using correct props, tokens, and premium layout patterns.
uxui-principles
Evaluate interfaces against 168 research-backed UX/UI principles, detect antipatterns, and inject UX context into AI coding sessions.