Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add motlin/claude-code-plugins/plugin install demoWrote 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/motlin/claude-code-plugins/demo)<a href="https://agentmods.dev/skills/motlin/claude-code-plugins/demo"><img src="https://agentmods.dev/badge/skills/motlin/claude-code-plugins/demo/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/motlin/claude-code-plugins/demo"><img src="https://agentmods.dev/badge/skills/motlin/claude-code-plugins/demo.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 | $0.00107 | $0.02300 |
| Opus 5.5 | $0.00043 | $0.00920 |
| Sonnet 5.5 | $0.00021 | $0.00460 |
| Haiku 4.5 | $0.00011 | $0.00230 |
Grade B, and why
demo scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- **HTTP** — `curl -sS -D- -X POST -H 'content-type: application/json' -d @request.json <url>`, so headers and status are captured. Capture the request body as its own step. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
uvx showboat exec demo.md bash 'curl -sS -D- "$URL" | sed -E "s/Bearer [A-Za-z0-9._-]+/Bearer «redacted»/"' How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Demo
A demo shows data, not code or a summary of code: a real request, a real row, a real file, a real command and what it printed. Demo what the user named; with no target, demo the work done so far in this session.
Before designing an interactive demo, read Red Blob Games' Making of: Circle drawing tutorial as the quality benchmark for teaching through interaction.
What counts as a demo
Show the data crossing the system's boundaries, in the order it crosses them:
- In at the edge — the HTTP request and response on the wire, the CLI invocation, the input file, the message off the queue
- Through the work — the command that does the thing, run for real
- Into storage — the SQL that executed, the rows before and after, the on-disk representation
- Out to the human — the page, the terminal, the report, the screenshot
Reading code aloud, a table of what changed, a test-passed count, or "the system now correctly…" is not a demo.
Capture with Showboat, never author
Every byte of output comes from a tool that recorded it while the command ran. Never retype, tidy, reconstruct, or predict output. If it was typed, it is prose; evidence comes from a capture tool.
Showboat builds the document, via uvx showboat (or uv tool install showboat):
uvx showboat init demo.md 'One POST, end to end'
uvx showboat note demo.md '## The table starts empty'
uvx showboat exec demo.md bash 'sqlite3 app.db "SELECT count(*) FROM note;"'
uvx showboat image demo.md screenshot.png
execappends the command and its captured output, prints it, and exits with the command's statusnotecarries all prose: framing, what to look for, caveatsimagecopies a screenshot or recording into the documentpopremoves the most recent entry
Make it verifiable
showboat verify demo.md re-runs every block and fails if output drifted. Aim for a demo that passes, which requires idempotence: reset state inside a captured step (a first block that empties the table), not off-camera before recording. When a demo cannot be idempotent, run verify anyway and note in the document which blocks drift and why.
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 · -77 lines 9bec2149ff41
- 29d ago Changed · +6 lines 9d247b356fa2
- 1mo ago Changed · +9 lines 02e8de5636e2
- 1mo ago Changed · +1 lines 0f14be3002d7
- 1mo ago First seen · 215 lines · 107 tokens per session scan B 45477548ebf4
demo is a skill published in the GitHub repository motlin/claude-code-plugins (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 107 tokens to every session and 2,300 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…