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 cdeistopened/skill-stack --skill icp-roleplay-demo-scriptgit clone --depth 1 https://github.com/cdeistopened/skill-stackWrote 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/cdeistopened/skill-stack/icp-roleplay-demo-script)<a href="https://agentmods.dev/skills/cdeistopened/skill-stack/icp-roleplay-demo-script"><img src="https://agentmods.dev/badge/skills/cdeistopened/skill-stack/icp-roleplay-demo-script/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/cdeistopened/skill-stack/icp-roleplay-demo-script"><img src="https://agentmods.dev/badge/skills/cdeistopened/skill-stack/icp-roleplay-demo-script.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 | $0.00096 | $0.00987 |
| Opus 5.5 | $0.00038 | $0.00395 |
| Sonnet 5.5 | $0.00019 | $0.00197 |
| Haiku 4.5 | $0.00010 | $0.00099 |
Grade A, and why
icp-roleplay-demo-script 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ICP Roleplay Demo Script
A launch video that explains the product in third person loses. A launch video where the founder steps into the ICP's life, hits the ICP's pain in real time, and opens the product to solve it — that one travels. This skill produces the script frame.
When invoking: Ask for the product, the ICP (role + seniority + company stage), and the specific pipeline the demo will show. Then produce the roleplay frame.
The frame
The founder is the ICP. Not "imagine a founder." Not "here's how our customer Lisa uses it." The founder speaks in first person as the ICP, on camera, using the product to solve a moment-specific pain.
The moment must be specific:
- Bad: "Every day founders struggle to keep track of their team."
- Good: "Hi, I'm Cailyn. I'm a founder and today is the day after the launch. Team Slack channels are blowing up and I need to know what's happening right now. So I open up Momo."
The bad version is about a category. The good version is about Tuesday at 9:47 a.m. in a specific person's life.
The 4 story beats (fits inside the 10-15s story window of x-launch-video-structure)
- Identity (1-2 seconds). "Hi, I'm [name]. I'm a [ICP role]."
- Moment (2-3 seconds). The specific time/context/trigger. "Today is the day after launch." "It's Friday and I'm about to send the investor update." "I just landed in Berlin for the conference." Time-stamps make the story real.
- Pain in real terms (2-3 seconds). Not "I'm struggling with productivity." Concrete: "I have seven Slack channels blowing up and I don't know what's real." "I have 40 demo requests in my inbox and three are from Fortune 500s I can't miss."
- Product moment (remaining seconds). "So I open up [product]." → cut straight to the product solving it. No menu tour. First click should show the payoff.
Rules
- First person only. No "founders like me" or "our users." "I."
- One specific ICP. If your product serves three ICPs, make three videos. A demo pretending to serve all three serves none.
- The moment has to be recent. Yesterday, today, "10 minutes ago." Not "imagine if."
- Pain must be measurable. Count something: channels, emails, hours, dollars.
- Solve visibly. Every second after "so I open up [product]" must show product UI with the outcome unfolding.
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 · 62 lines · 96 tokens per session scan A 001edc440f25
icp-roleplay-demo-script is a skill published in the GitHub repository cdeistopened/skill-stack (30 stars, last pushed 3mo ago), licensed MIT. It adds 96 tokens to every session and 987 once invoked, about $0.0004 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 2026-09-03.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.