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 marchatton/agent-skills --skill demo-runbookgit clone --depth 1 https://github.com/marchatton/agent-skillsWrote 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/marchatton/agent-skills/demo-runbook)<a href="https://agentmods.dev/skills/marchatton/agent-skills/demo-runbook"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/demo-runbook/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/marchatton/agent-skills/demo-runbook"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/demo-runbook.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 | $0.00065 | $0.01983 |
| Opus 5 | $0.00032 | $0.00992 |
| Sonnet 5 | $0.00013 | $0.00397 |
| Haiku 4.5 | $0.00006 | $0.00198 |
Grade A, and why
demo-runbook 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 7d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Demo Runbook
Create a demo package that is demo-first, user-empathy-led, and technically credible. Produce two deliverables every time: a demo script and a single-file HTML runbook.
When to use this skill
Use this skill when asked to create or refresh a demo (often a PoC demo) that:
- Starts with an end-to-end live demo before explaining why, what, and how
- Includes a competitive landscape comparison using April Dunford’s respectful approach framing
- Includes technical architecture details, especially LLM patterns (RAG, evals, observability)
- Produces both a talk track and a navigable runbook page
Example triggering requests:
- “Help me create a PoC demo runbook and script for a live demo.”
- “Make a demo-first talk track, then cover why/what/how and architecture.”
- “Create a single HTML runbook with links, diagrams, and sections for tech stack.”
- “Write a respectful competitive comparison and explain our approach.”
Outputs
Always produce both:
- Demo script as markdown (talk track + what to click + timings)
- Single-file HTML runbook (visual-first with custom CSS, navigable sections, Mermaid diagrams (flowchart + sequence), in-app hyperlinks, back-to-home navigation)
HTML runbook must:
- Be single-file HTML (no build step required) with custom CSS styling (cards/callouts/layout), not a plain document.
- Include Mermaid diagrams (at least one flowchart and one sequence diagram).
- Include navigation between sections (hash router is fine) and “Back to Home” affordances.
- Include an app links section with real links or TODO placeholders.
When returning outputs, format as:
=== demo-script.md ===then the markdown=== demo-runbook.html ===then the full HTML
Input schema
Accept inputs in either bullet form or JSON. If any field is missing, insert a clear TODO placeholder rather than asking questions.
Minimum inputs to request are not required. Proceed with placeholders.
Core narrative
poc_name: Name of the PoCtagline: One-line value statementaudience: Who is watching (and expected technical depth)segment:organisation: The organisation context (industry, size, geography, constraints)buyer: Who buys / signs (budget owner, success metric, risk posture)end_user: Who uses it day-to-day (workflow, pain, what “better” feels like)
job_to_be_done: What the user is trying to dostarting_feelings: How they feel at the start (rushed, uncertain, risk-averse, too many tabs)desired_feelings: How the product changes that (confidence, clarity, speed, fewer guesses)scenario: The demo scenario in plain Englishsuccess_outcome: What “done” looks like for the userbusiness_success_outcome: What success looks like for the business (be specific: $ impact or growth/adoption metric + timeframe)
What ships with it
5 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.
- 7d ago First seen · 190 lines · 65 tokens per session scan A e6a99e523fa3
demo-runbook is a skill published in the GitHub repository marchatton/agent-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 65 tokens to every session and 1,983 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…