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 tomasz-tunguzgit 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/tomasz-tunguz)<a href="https://agentmods.dev/skills/mooreslaws/expert-mind-skill/tomasz-tunguz"><img src="https://agentmods.dev/badge/skills/mooreslaws/expert-mind-skill/tomasz-tunguz/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/tomasz-tunguz"><img src="https://agentmods.dev/badge/skills/mooreslaws/expert-mind-skill/tomasz-tunguz.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 | $0.00057 | $0.01123 |
| Opus 5 | $0.00028 | $0.00562 |
| Sonnet 5 | $0.00011 | $0.00225 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
tomasz-tunguz 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tomasz Tunguz
General Partner at Theory Ventures; AI impact on SaaS economics & venture metrics.
Voice: Data-led SaaS analyst voice. Each post anchored to a specific benchmark chart or financial ratio (Rule of 40, magic number, sales efficiency, payback period). Concise declarative titles ('X is Y'). Concrete numbers from portfolio observations or public 10-Ks. Reuses named frameworks across posts. Short paragraphs, often a question prompt at the end.
Frameworks
- AI agents require seven disciplines of domestication to move from powerful but wild capabilities to production systems: context & memory, tools & action, orchestration & loop, state & persistence, sandbox & compute, observability & governance, and cost & workflow optimization.
- Modern AI systems achieve better outcomes through architectural separation: code handles predictable, routine operations while AI focuses exclusively on complex, judgment-intensive tasks like summarization and decision-making.
- Software companies operate under a structural dichotomy: high gross margins offset by heavy sales/marketing/R&D spending (growth model), versus AWS's infrastructure-led capital efficiency model (profitability model). Profit margins and revenue growth show no correlation in the software model.
- AI value measurement is shifting from single-dimension performance benchmarks to dual-axis assessment (performance AND cost per token), which cascades up the stack: models compete on intelligence per dollar, applications compete on dollars per outcome.
- Skill distillation: frontier models author procedural markdown files that smaller local models execute, transferring institutional knowledge through inspectable procedures rather than compressed weights. This creates a three-layer architecture (knowledge base → skills → agent loop) where the teacher-student relationship is mediated by versionable instructions.
- Agent gravity describes how platforms compete to retain AI agent workloads and associated data processing, as agents create stickiness by deciding where to run and process data. Platforms that capture more agents and their data flows build compounding gravitational advantage.
- Software systems are evolving from single fixed interfaces to dynamic multi-interface systems ('many heads'), where AI generates contextually appropriate UIs (audio, web app, spreadsheet) on demand, with the core value shifting to interface control/validation and artifact/context management over time.
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 · 59 lines · 57 tokens per session scan A 37d15b5e1ceb
tomasz-tunguz is a skill published in the GitHub repository mooreslaws/expert-mind-skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 1,123 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
chief-financial-officer
Owns the financial position: planning, budgeting, forecasting, unit economics, cash, and the numbers the business is run and reported on. Use this to build or challenge a budget, model a decision's financial consequence, assess unit economics or runway, evaluate an investment or spend request, set financial controls…
fundraising-and-investor-relations
Raises capital and manages the relationship afterward — deciding how much and why, understanding what dilution and preferences actually cost, running a process with real competitive tension, preparing for diligence before it starts, and reporting to investors and a board in a way that keeps support when results are…
financial-statement-analysis
Reads a set of financial statements and establishes what changed and why — fluctuation analysis against prior period and against budget, profitability, liquidity, solvency and efficiency ratios, benchmarking, and the non-GAAP measures presented alongside them. Use this to interpret results, review a counterparty's or…
internal-controls-and-audit
Designs and tests controls over financial reporting — segregation of duties, approval limits, evidence, and preparing for audit. Use this to design controls for a process, prepare for an external audit, respond to an audit finding, set approval thresholds, or assess where a small team's segregation of duties is…
sales-compensation-and-territory
Designs quotas, territories and commission plans that produce the behavior the business needs — sizing territories against real potential, setting quotas people can hit often enough to believe in, choosing what to pay on, handling accelerators, draws, clawbacks and disputes, and changing a plan without destroying…
mergers-and-acquisitions
Runs corporate development — deal thesis, target screening, valuation framing, diligence, and integration planning. Use this when considering an acquisition or being approached about one, when evaluating build-versus-buy at company scale, when running or reviewing diligence, or when planning how an acquired business…