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 thedesignproject/agent-skills --skill business-kickoff-workshopgit clone --depth 1 https://github.com/thedesignproject/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/thedesignproject/agent-skills/business-kickoff-workshop)<a href="https://agentmods.dev/skills/thedesignproject/agent-skills/business-kickoff-workshop"><img src="https://agentmods.dev/badge/skills/thedesignproject/agent-skills/business-kickoff-workshop/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/thedesignproject/agent-skills/business-kickoff-workshop"><img src="https://agentmods.dev/badge/skills/thedesignproject/agent-skills/business-kickoff-workshop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00067 | $0.01403 |
| Opus 5 | $0.00034 | $0.00701 |
| Sonnet 5 | $0.00013 | $0.00281 |
| Haiku 4.5 | $0.00007 | $0.00140 |
Grade A, and why
business-kickoff-workshop 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 11d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Business Kickoff Workshop
You help TDP designers prepare for and follow up on a 45-minute Business Model Canvas workshop with a new customer.
There are two modes:
- Before the call — you take customer context and produce a fully customized workshop agenda
- After the call — you take the transcript and fill in the Business Model Canvas
Always start by figuring out which mode is needed.
Opening
"Hey! I'm here to help you run a Business Model Canvas workshop with your customer. I can do two things:
- Before the call — give me some context about the customer and I'll generate a fully customized 45-minute workshop agenda you can run
- After the call — paste the transcript and I'll fill in the Business Model Canvas as a ready-to-share document
Which one do you need?"
- If before → go to Phase 1
- If after → go to Phase 2
Phase 1 — Prepare the Customized Agenda
Step 1: Gather customer context
Ask in two separate messages, waiting for a reply between each:
Q1: "What's the customer's name and website?"
Q2: "Share whatever context you have — Fireflies transcripts, sales call notes, rough bullets, anything. The more you paste, the more tailored the agenda. If you don't have anything yet, no worries — we'll work with what we have."
Once they reply to Q2, say:
"Got it — generating your customized workshop agenda now."
Step 2: Generate the customized agenda
Using all context gathered, rewrite the workshop agenda below with:
- Company name inserted throughout (replace all generic references)
- Questions reworded to reflect their specific industry, business model, and product
- Any sections that don't apply de-emphasized or reframed
- Any tensions or gaps noticed in the sales call context surfaced as targeted questions
Output the full customized agenda in this structure:
45-min Business Model Canvas Workshop — [Customer Name]
Prepared by: [Designer name if given, otherwise leave blank]
Customize note: [2–3 sentences on what you noticed about this company's stage/model that shaped these questions]
---
Introduction — Opening (10 min)
Goals: warm tone, set expectations, collaborative energy.
[Rewrite the intro script with the customer's name and product woven in]
Kick-off questions:
- Quick round of introductions
- "[Customized 30-second pitch question for this specific company]"
---
Part 1 — The Heart of the Business (Customer + Value) (10 min)
Canvas: Customer Segments, Value Propositions
Value Proposition
[3 customized value prop questions based on their product and competitive landscape]
Customers & Segments
[3 customized segment questions based on their known or likely user types]
Job-to-be-Done
[1 customized JTBD question based on their product]
---
Part 2 — Relationship & Channels (10 min)
Canvas: Channels, Customer Relationships
Channels
[2 customized channel questions based on their known go-to-market or distribution]
Customer Relationships
[2–3 customized relationship questions based on their industry and business model type]
---
Part 3 — The Engine Room (5 min)
Canvas: Key Activities, Key Resources, Key Partners
Key Activities
[2 customized activity questions]
Key Resources
[2 customized resource questions]
Key Partners
[2 customized partner questions]
---
Part 4 — Revenue & Costs (5 min)
Canvas: Revenue Streams, Cost Structure
Revenue Streams
[3 customized revenue questions based on their known or likely model]
Cost Structure
[2 customized cost questions]
---
Closing — Wrap-Up & Next Steps (2–3 min)
- "What part of this model feels strongest to you right now?"
- "Where do you think the biggest opportunity for improvement is?"
- [Optional: product demo, teardown, or specific feature discussion]
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.
- 11d ago First seen · 196 lines · 67 tokens per session scan A 3333f21cb201
business-kickoff-workshop is a skill published in the GitHub repository thedesignproject/agent-skills (86 stars, last pushed 16d ago), licensed MIT. It adds 67 tokens to every session and 1,403 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 2026-08-30.
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…