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 agentmods add skills/fmind/dot/product-loopnpx skills add fmind/dot --skill product-loopgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/product-loop)<a href="https://agentmods.dev/skills/fmind/dot/product-loop"><img src="https://agentmods.dev/badge/skills/fmind/dot/product-loop.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.02823 |
| Opus 5 | $0.00028 | $0.01411 |
| Sonnet 5 | $0.00011 | $0.00565 |
| Haiku 4.5 | $0.00006 | $0.00282 |
Grade A, and why
product-loop 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 yesterday.
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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Loop
One product decision cycle in four phases: Discover what deserves building, Specify what must be true, Launch to a bounded audience, then Learn whether the bet paid. Enter at the phase the evidence supports and stop at the next decision; repository planning belongs to implementation-plan and interface critique to product-design-review.
| Situation | Phase |
|---|---|
| The problem, demand, or wedge is still unproven | Discover |
| Discovery is validated and behavior must be pinned down | Specify |
| The change is built and needs a staged audience | Launch |
| The experiment, launch, or sales attempt has produced results | Learn |
Ground Rules
- Separate observations, supplied evidence, inferences, and assumptions. Never convert enthusiasm into proof.
- Do not invent quotes, logos, metrics, demand, research, legal requirements, availability, or support capacity.
- Do not contact customers, create accounts, mutate a CRM or analytics, publish pages, buy ads, or spend money without explicit authorization.
- Use a requirements echo only when the input is long, contradictory, or course-changing; label user statements, evidence, inference, and proposals separately.
Workflow
Discover
Challenge the premise before refining the solution, and keep doing nothing, a manual service, or a smaller change among the alternatives. Close with the discovery brief from briefs.
- Recover context: read supplied research, product artifacts, and repository constraints; use technical-research when external facts could change the decision.
- State the thesis: target user, painful job, proposed change, expected outcome, and why now in one sentence; mark unsupported parts as assumptions.
- Interrogate the problem: how users solve it today, how often, what it costs them, who chooses or pays, and what evidence shows urgency.
- Find the wedge: the smallest end-to-end result with standalone value; reject bundles of independent products and defer scale architecture until demand justifies it.
- Test founder logic: unique insight, distribution path, switching friction, business model, defensibility, operational ownership, and unfair access to the problem.
- Generate alternatives: two or three materially different paths with trade-offs, led by the simplest and including a credible no-build path.
- Rank assumptions: score value, usability, viability, feasibility, distribution, and trust assumptions by impact and uncertainty; keep the list short.
- Design the cheapest decisive test: behavior to observe, segment, exposure, time box, success threshold, guardrail, and kill criterion; prefer commitments over compliments (see demand-tests).
- Make the call:
BUILD,TEST FIRST,PARK, orSTOP, naming the evidence that would change it.
What ships with it
2 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.
- yesterday First seen · 96 lines · 57 tokens per session scan A 954af2a3d276
product-loop is a skill published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 2,823 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 2026-09-03.
Other skills, from other repositories
go-stack
Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.
python-stack
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.
k8s-local
Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.
chezmoi
Manage chezmoi dotfiles: source naming, Go templates, age-encrypted secrets, and the edit-source then apply/diff workflow.
hugo
Canonical Hugo static-site stack with the Hextra docs theme — Hugo Modules, mise tasks, dprint, lefthook, and GitHub Pages deploy. Use for documentation sites, project docs, and static websites.
mise
Configure pinned mise tools and canonical install, format, check, test, build, and watch tasks shared by hooks and CI.