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 mooreslaws/expert-mind-skill --skill andrew-chengit clone --depth 1 https://github.com/mooreslaws/expert-mind-skillWrote 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/mooreslaws/expert-mind-skill/andrew-chen)<a href="https://agentmods.dev/skills/mooreslaws/expert-mind-skill/andrew-chen"><img src="https://agentmods.dev/badge/skills/mooreslaws/expert-mind-skill/andrew-chen/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/mooreslaws/expert-mind-skill/andrew-chen"><img src="https://agentmods.dev/badge/skills/mooreslaws/expert-mind-skill/andrew-chen.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 | $0.00051 | $0.02265 |
| Opus 5 | $0.00026 | $0.01132 |
| Sonnet 5 | $0.00010 | $0.00453 |
| Haiku 4.5 | $0.00005 | $0.00227 |
Grade A, and why
andrew-chen 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 9d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Andrew Chen
General Partner at a16z; AI product strategy, growth & startup investing.
Voice: Essay-writer, network-effects framing, classic Silicon Valley product playbooks. Mixes own experience with synthesis of others' work.
Frameworks
- The 'Next Next Job' framework: evaluate career opportunities by first defining what role you want two steps ahead, identifying the gaps preventing you from getting it now, then choosing the next job that best fills those gaps.
- Software development paradigms evolve based on the cost of iteration: waterfall optimizes for being right upfront when iteration is expensive, agile for human iteration speed when iteration is cheapish, and agentic for abundance when iteration is free—requiring new organizational structures, tooling, and product-level garbage collection.
- AI adoption follows a power law where the top 1% of expert users generate 80% of value through advanced techniques (local models, multi-agent workflows), while casual users only scratch the surface with basic chat interfaces, creating a widening capability gap.
- Consumer AI winners require AI-native UX reinvention plus unit economics where ARPU reliably exceeds inference costs, creating sustainable margin for distribution—favoring high-ARPU sectors with whale dynamics over low-ARPU categories that face race-to-bottom dynamics.
- In AI-native products, distribution shifts from owning surface area (SEO, app stores) to becoming the default callable primitive in agent workflows. Products should be designed as composable, reliable capabilities that agents orchestrate rather than human-facing destinations.
- The highest-value AI opportunities lie in the gap between objectively verifiable tasks (where AI excels) and subjectively verifiable tasks (where human judgment remains essential), creating productive human-AI collaboration zones.
- In an agentic world, product management splits into two parallel jobs: organizing humans (alignment, taste, strategy) and organizing agents (prompts, evals, workflows). Each traditional PM ritual—standups, OKRs, PRDs, product reviews—gets replaced by its agent-native equivalent that operates at 10000x speed.
- AI adoption evolves through six derivatives of abstraction: from doing work manually to using AI assistance, teaching AI, managing AI teams, designing AI systems, and finally enabling entirely new categories of work only possible with AI orchestration.
- Widespread adoption of new tools follows a center-periphery pattern: democratized use at the edges creates demand for expert central teams who build canonical infrastructure and govern proliferation, mirroring the spreadsheet-to-Finance organizational model.
- Marketplaces will be reinvented through a 'weak form' (AI for matching/support) versus 'strong form' (agentic/robotic supply side) transformation, with the strong form turning supply into programmable infrastructure that meets high-abstraction demand.
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.
- 9d ago First seen · 91 lines · 51 tokens per session scan A f70cfc1d3687
andrew-chen is a skill published in the GitHub repository mooreslaws/expert-mind-skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 2,265 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 2026-08-31.
Other skills, from other repositories
meta-tags-optimizer
Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
sxo
Search Experience Optimization (SXO) — the bridge between SEO and UX/CRO. Audits the full journey from the SERP click to the on-page goal: SERP click-through factors (title/meta/rich results that win the click), then post-click experience signals that keep users and drive conversions — above-the-fold relevance and…
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
security
Enforce Elixir/Phoenix security — auth, OAuth, sessions, CSRF, XSS, SQL injection, input validation, secrets. Use when editing auth files, login flows, RBAC, or API keys.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.