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/dotfiles/product-loopnpx skills add fmind/dotfiles --skill product-loopgit clone --depth 1 https://github.com/fmind/dotfilesWhat 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 | $0.00053 | $0.04420 |
| Opus 5 | $0.00026 | $0.02210 |
| Sonnet 5 | $0.00011 | $0.00884 |
| Haiku 4.5 | $0.00005 | $0.00442 |
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 — 183 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, rather than running all four by default.
Phase Selection
| 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 |
Entering the wrong phase is the common failure: writing requirements for an unvalidated problem, or claiming lessons from a launch that never shipped. Name the phase and its evidence before starting.
Ground Rules
These apply to every phase.
- Separate observations, supplied evidence, inferences, and assumptions. Never convert enthusiasm into proof.
- Treat market size, demand, willingness to pay, and competitor claims as current facts that require primary evidence.
- 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.
- Planning an interview is read-only. Contacting or recording a person, retaining identifiable notes, or publishing a quote requires explicit authorization, applicable consent, and a stated data-retention boundary.
- Scale the artifact to the change. A compact, low-risk decision should not acquire empty sections merely to satisfy a template.
- Scale the dialogue to uncertainty. Proceed when the decision is already clear; ask one high-leverage question when an answer would materially change direction.
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 · 183 lines · 53 tokens per session scan A 46ebe70c0dd9
product-loop is a skill published in the GitHub repository fmind/dotfiles (4 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 4,420 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
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
aiq-research
Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
obsidian-bases
Obsidian Bases database feature for YAML-based interactive note views. Use when creating .base files, writing filter queries, building formulas, configuring table/card views, or working with Obsidian properties and frontmatter databases.
telegram
Send notifications, interactive questions, or multiple-choice polls to the user via Telegram. Use when the user asks to be notified ("ping me", "notify me on Telegram", "ask me when..."), when a long-running task finishes and the user is likely away, when an irreversible action needs out-of-band confirmation, or when…
chezmoi-expert
Comprehensive chezmoi dotfiles management expertise including templates, cross-platform configuration, file naming conventions, and troubleshooting. Covers source directory management, reproducible environment setup, and chezmoi templating with Go templates. Use when user mentions chezmoi, dotfiles, cross-platform…