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 avelikiy/great_cto --skill product-economicsgit clone --depth 1 https://github.com/avelikiy/great_ctoWrote 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/avelikiy/great_cto/product-economics)<a href="https://agentmods.dev/skills/avelikiy/great_cto/product-economics"><img src="https://agentmods.dev/badge/skills/avelikiy/great_cto/product-economics/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/avelikiy/great_cto/product-economics"><img src="https://agentmods.dev/badge/skills/avelikiy/great_cto/product-economics.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 | $0.00055 | $0.01536 |
| Opus 5 | $0.00028 | $0.00768 |
| Sonnet 5 | $0.00011 | $0.00307 |
| Haiku 4.5 | $0.00006 | $0.00154 |
Grade A, and why
product-economics 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product economics
A product can pass every gate this pipeline has — architecture reviewed, tests green, security signed off, deployed — and still lose money on every user. The pipeline is silent about that, and silence reads as approval.
This is the missing question, and it is three questions:
- Does a unit pay for itself? (contribution margin)
- What is the price, and on what basis? (pricing)
- Are there enough units to matter? (market size, bottom-up)
The rule that makes this worth doing
Every number carries its provenance, in the notation the brief already uses — do not invent a second vocabulary for this:
[source: <where it was read>]— an invoice, a usage log, a competitor's published price with the date you checked it[assumption]— you made it up, and saying so is the point
artifact-lint already rejects a figure carrying neither. That rule was written
for the Problem section; it binds here at least as hard, because arithmetic
launders provenance: an [assumption] conversion rate and a [source:] one are
indistinguishable once they have been multiplied together, and the product of
two guesses is presented with the same confidence as a measurement.
The third state is the one the notation has no symbol for: a number nobody
knows. Do not fill that hole with a plausible figure — a plausible figure
becomes [assumption], gets multiplied, and disappears into a margin. Write the
line as an open question instead, and carry it into Risks & kill-criteria
with the threshold that would end the project. An unknown that decides the
answer is a finding, not a gap.
1. Contribution margin — per unit, per month
price per unit $
− variable cost per unit $
LLM tokens (in + out, at list price) $ ← usually the largest, often forgotten
inference / GPU seconds $
storage + egress attributable to one unit
per-unit third-party fees (payments %, SMS, maps, email)
support minutes × loaded hourly cost
= contribution margin $ ← this must be POSITIVE
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 · 146 lines · 55 tokens per session scan A 96104c53b9f3
product-economics is a skill published in the GitHub repository avelikiy/great_cto (93 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,536 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 2026-09-05.
Other skills, from other repositories
spec-drift
Standalone plan-vs-code audit on any branch: runs /ship Step 8's plan-completion section from disk (hash-pinned) against an explicit plan and base. Report, JSON, exit code. Never edits code.
third-lens-review
After Claude self-pitfall + Codex on a ship-worthy/architecture/RT/security/contract change: run a third external model house (distant training distribution → different blind spots) on the patched artifact, then adversarial synthesis.
quality-review
After a PRD, spec, or plan, before implementation: hunt perceived-quality pitfalls (silent failures, missing loading/empty states, error recovery, state drift) that make a product feel cheap. Complements pitfall-verification.
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.
triage
Triage review findings interactively — approve, skip, or prioritize each issue. Use after /phx:review to filter findings before fixing.
incorporation
A guide for moving from working as an individual business owner to operating through a company in Japan. It covers company types, setup steps, officer pay, taxes, and social insurance.