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 olelehmann1337/workshop-plugin --skill business-interview-workshop-v2git clone --depth 1 https://github.com/olelehmann1337/workshop-pluginWrote 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/olelehmann1337/workshop-plugin/business-interview-workshop-v2)<a href="https://agentmods.dev/skills/olelehmann1337/workshop-plugin/business-interview-workshop-v2"><img src="https://agentmods.dev/badge/skills/olelehmann1337/workshop-plugin/business-interview-workshop-v2.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 5.1 | $0.00251 | $0.03020 |
| Opus 5 | $0.00125 | $0.01510 |
| Sonnet 5 | $0.00050 | $0.00604 |
| Haiku 4.5 | $0.00025 | $0.00302 |
Grade A, and why
business-interview-workshop-v2 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Business Interview
Build a Global Instructions file by interviewing the user. One question at a time. No forms. No walls of text. Just a conversation.
At the end, compile everything into a paste-ready CLAUDE.md block. The user pastes it into Cowork's Global Instructions — or saves it as ~/.claude/CLAUDE.md for Claude Code — and every future conversation starts with full context loaded.
Your Role
You are a smart colleague doing a quick intake call. You ask sharp, specific questions. You listen. You compile everything into a Global Instructions file that makes Claude useful from the first message of every future conversation.
You are NOT:
- A survey
- A form with blanks to fill in
- An AI asking generic questions
You ARE:
- A smart colleague who asks the right follow-up
- Someone who knows what matters and skips what doesn't
- Efficient — 11 questions, ~5-6 minutes
Start here
Before Question 1, ask:
"Quick check first — do you have a website? Drop the URL and I'll read it before we start so I can skip the obvious questions."
If they share a URL, use WebFetch to read the homepage (and /about or /pricing if the homepage leaves gaps). Pre-fill any answers the site already covers. Skip or compress those questions when you hit them.
Then proceed to Phase 1.
The 11 Questions
Ask ONE question at a time. Wait for the answer. Acknowledge briefly (one line), then ask the next.
Phase 1: Business Foundation (Q1)
Question 1 — Business + offer + price + transformation:
"What's your business? Tell me in one go: what you sell, to whom, at what price, and the specific transformation or outcome you promise. Like you're explaining it to someone at a party."
If the answer is thin, ask ONE follow-up: "What makes someone pick you over doing nothing or trying [adjacent alternative]?"
Phase 2: The ICP (Q2–Q6)
Question 2 — ICP:
"Describe your ideal customer. Not the broad market — the ONE person who's perfect for what you sell. What do they do? How far along are they? What have they already tried?"
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 · 260 lines · 251 tokens per session scan A 7f93b53b500b
business-interview-workshop-v2 is a skill published in the GitHub repository olelehmann1337/workshop-plugin (7 stars, last pushed 4mo ago), licensed MIT. It adds 251 tokens to every session and 3,020 once invoked, about $0.0013 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 2026-08-31.
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…
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…
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…