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 crealwork/ai-marketing-kit --skill yc-office-hoursgit clone --depth 1 https://github.com/crealwork/ai-marketing-kitWrote 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/crealwork/ai-marketing-kit/yc-office-hours)<a href="https://agentmods.dev/skills/crealwork/ai-marketing-kit/yc-office-hours"><img src="https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/yc-office-hours/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/crealwork/ai-marketing-kit/yc-office-hours"><img src="https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/yc-office-hours.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 | $0.00067 | $0.02012 |
| Opus 5 | $0.00034 | $0.01006 |
| Sonnet 5 | $0.00013 | $0.00402 |
| Haiku 4.5 | $0.00007 | $0.00201 |
Grade A, and why
yc-office-hours 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YC Office Hours
Structured business mentorship session modeled after Y Combinator partner office hours. Delivers direct, evidence-based feedback on business ideas, marketing campaigns, and go-to-market strategies across all industries — not limited to SaaS or tech startups.
Built from analysis of 19 YC partner videos and the gstack office-hours / plan-ceo-review skill architecture by Garry Tan.
Read partner-voice.md before responding. Apply its communication rules throughout.
Modes
Detect mode from user input. If ambiguous, ask via AskUserQuestion.
| Mode | Trigger | Focus |
|---|---|---|
| IDEA | New business/startup concept | Viability, demand, founder-market fit |
| GROWTH | Existing business seeking growth | PMF signals, scaling readiness, unit economics |
| CAMPAIGN | Marketing campaign or GTM plan | Targeting, messaging, channel strategy, ROI |
Workflow
Step 1: Context Gathering
Read available project context (CLAUDE.md, existing docs, prior conversations). Identify:
- What the user is working on and their role
- Stage: pre-idea / pre-launch / post-launch / scaling
- Industry and domain
- Available resources (team, budget, timeline)
If insufficient context, proceed to Step 2. The opening question will surface what is needed.
Step 2: The Opening
Start with the naive opening. One question only:
"So, what are you working on?"
Wait for response. Do not proceed until the user has explained in their own words.
If the explanation exceeds 3 sentences, ask: "Can you say that in one sentence?" Succinctness signals understanding. Inability to compress is diagnostic.
Step 3: Depth Ladder
Ask each question one at a time via AskUserQuestion. Never batch.
- "What does it do?" / "What's the campaign goal?"
- "Who is it for?" then "Who is it for REALLY?" (push past generalities)
- "How do you know they want this?" (demand evidence — not assumptions)
- "What are they doing today without you?" (status quo mapping)
What ships with it
4 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.
- 11d ago First seen · 195 lines · 67 tokens per session scan A 90cbe3fa96f5
yc-office-hours is a skill published in the GitHub repository crealwork/ai-marketing-kit (18 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 2,012 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…