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 modem-dev/sideshow --skill sideshowgit clone --depth 1 https://github.com/modem-dev/sideshowWrote 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/modem-dev/sideshow/sideshow)<a href="https://agentmods.dev/skills/modem-dev/sideshow/sideshow"><img src="https://agentmods.dev/badge/skills/modem-dev/sideshow/sideshow/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/modem-dev/sideshow/sideshow"><img src="https://agentmods.dev/badge/skills/modem-dev/sideshow/sideshow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 67 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00054 | $0.00676 |
| Opus 5.5 | $0.00022 | $0.00270 |
| Sonnet 5.5 | $0.00011 | $0.00135 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
sideshow 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 1mo 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sideshow (plugin)
The user keeps a sideshow surface open in their browser. You publish HTML snippets to it; they appear instantly. The user comments on any snippet, and this plugin streams those comments to you as notifications — you do not poll or arm a watcher. It is a two-way surface, not a fire-and-forget renderer.
How feedback reaches you
A background monitor (sideshow watch) runs for the whole session and delivers
each new user comment as a notification on your next turn, for example:
sideshow comment on “Cache layout” (snippet a1b2c3): “tighten the spacing”
Treat every such line as a message from the user. Respond by revising the
snippet it refers to (update_snippet / sideshow update <id>) or replying
(reply_to_user / sideshow comment). Comments are delivered exactly once —
you will not see the same one twice, so act on each when it arrives. You never
need to call wait_for_feedback just to stay aware of comments; the monitor
already does that. (Publish/update/reply responses may still carry a
userFeedback array; it is the same stream, also delivered once.)
Before your first publish
Fetch the design contract once per session (fragment rules, theme CSS variables, CDN allowlist, sizing):
- MCP:
get_design_guide - CLI:
sideshow guide
Publishing
Prefer the MCP tools when connected (publish_snippet, update_snippet,
wait_for_feedback, reply_to_user); otherwise use the CLI. Session grouping
is automatic.
sideshow publish sketch.html --title "Cache layout" --session-title "Cache redesign"
echo '<p>...</p>' | sideshow publish - --title "Quick note"
Rules of thumb:
- On your first publish, set a session title that names the task ("Auth
refactor"), not the tool —
sessionTitle(MCP) /--session-title(CLI). It applies only when the session is created; never retitle later (the user may have renamed it in the viewer). - One concept per snippet, with a clear title. A series of small snippets beats one giant page.
- Iterate with
update_snippet/sideshow update <id>(same card, new version) instead of publishing near-duplicates. - Use the kit from the design guide (pre-styled form elements, SVG utility classes) before writing CSS; otherwise use the theme CSS variables so snippets work in dark mode.
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.
- 1mo ago First seen · 68 lines · 54 tokens per session scan A d47ae5671ebd
sideshow is a skill published in the GitHub repository modem-dev/sideshow (623 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 676 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
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.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.