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/sammcj/agentic-coding/guided-demonpx skills add sammcj/agentic-coding --skill guided-demogit 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/guided-demo)<a href="https://agentmods.dev/skills/sammcj/agentic-coding/guided-demo"><img src="https://agentmods.dev/badge/skills/sammcj/agentic-coding/guided-demo.svg" alt="Measured on agentmods" 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 | $0.00071 | $0.01869 |
| Opus 5 | $0.00036 | $0.00934 |
| Sonnet 5 | $0.00014 | $0.00374 |
| Haiku 4.5 | $0.00007 | $0.00187 |
Grade A, and why
guided-demo 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 today.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guided Demo Pattern
Add a self-narrating walkthrough to any HTML/web application. A declarative step array drives a setTimeout loop that toggles CSS classes on DOM elements and writes text character-by-character into a fixed panel. The engine overlays the existing page without modifying its code. When the demo stops, all state resets.
About 100 lines of JS and 30 lines of CSS for the core. Interstitials, speed controls, keyboard shortcuts, and progress bar are optional layering.
Before implementing
Ask the user these questions (skip any already answered in conversation):
- What are the sections? Tabs, routes, scroll positions, slide indices? Determines how section switching works.
- Framework? Vanilla HTML works directly. React/Vue/Svelte need the engine as a conditional overlay component, and
querySelectormust run after render. - Presenter talking over it, or self-narrating? Talking over: shorter text, longer pauses. Self-narrating: detailed text, moderate pauses.
- Interactive elements to trigger? Map to step actions. Confirm CSS selectors are stable (not framework-generated hashes).
- Offline requirement? Keep everything in one file if so. No CDN dependencies without fallbacks.
- How many steps? Under 15 for a pitch, 20-30 for a detailed walkthrough. Over 40 loses attention.
- Touch device support needed? Most guided demos target desktop/laptop presentation contexts. The narrator panel has on-screen prev/play/next buttons that work on touch, but swipe gestures or mobile-specific layout are rarely needed.
Implementation
Read references/implementation.md for all code snippets (vanilla JS / static HTML). If the target application uses React with React Router, also read references/react-integration.md for React-specific patterns covering stale closures, route navigation timing, and component architecture. For other SPA frameworks (Vue, Svelte, etc.), the same concepts apply (poll for elements after route change, store timer-relevant state outside the reactivity system) but the implementation details differ.
What ships with it
2 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.
- today Changed · +2 lines b5521e257438
- 4d ago First seen · 112 lines · 71 tokens per session scan A a6daa3857e2f
guided-demo is a skill published in the GitHub repository sammcj/agentic-coding (159 stars, last pushed today), licensed Apache-2.0. It adds 71 tokens to every session and 1,869 once invoked, about $0.0004 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
Canvas Skill
Present interactive HTML, visualizations, dashboards, and generated interfaces on connected Cybara nodes.
api-debug
Debug REST, GraphQL, webhook, and OAuth/API-key integrations with layered request, auth, schema, and response checks.
code-wiki
Generate architecture wiki docs, module maps, and Mermaid diagrams for a codebase using Cybara file/search/write tools.
comfyui
Drive ComfyUI (local Stable Diffusion / image-gen pipeline) via its HTTP API to generate and edit images. Use when the user has ComfyUI running and wants image generation/upscale/img2img workflows.
mactop
Retrieve real-time hardware metrics from Apple Silicon Macs using mactop. Provides CPU, RAM, GPU, power, thermal, network, disk I/O, and Thunderbolt bus information. Use when the user wants system stats, hardware monitoring, or performance metrics on Apple Silicon Macs.
huggingface-jobs
Plan, launch, inspect, monitor, and cancel authenticated Hugging Face Jobs for CPU, GPU, TPU, batch, inference, and data workloads.