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-design-reviewnpx skills add fmind/dot --skill product-design-reviewgit 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-design-review)<a href="https://agentmods.dev/skills/fmind/dot/product-design-review"><img src="https://agentmods.dev/badge/skills/fmind/dot/product-design-review.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 5.1 | $0.00044 | $0.01044 |
| Opus 5 | $0.00022 | $0.00522 |
| Sonnet 5 | $0.00009 | $0.00209 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
product-design-review 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 2d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Design Review
Judge whether a real user can understand, trust, and complete the surface's primary job, then improve only what the requested scope authorizes; quality-assurance owns the test campaign and fmind-visuals owns Fmind brand truth.
Workflow
- Recover product truth: read the brief, existing product or design artifacts, tokens, components, user research, and representative content; name missing evidence, then classify the task as preserve, refine, or redesign.
- Map the journey: entry points, primary action, decisions, exits, failure recovery, and time to first value.
- Inspect the live surface: when a runnable app exists, use playwright to capture desktop and mobile states, DOM semantics, console and network errors, keyboard behavior, focus, reduced motion, and screenshots.
- Review comprehension: information architecture, hierarchy, labels, vocabulary, affordances, progressive disclosure, cognitive load, and whether the next action is obvious.
- Review every state: first run, loading, empty, partial, success, validation, permission, error, offline, destructive confirmation, and recovery.
- Review craft: typography, spacing, alignment, color, contrast, density, imagery, motion, and consistency; flag generic defaults only when they weaken the brief.
- Review inclusion: semantic structure, keyboard access, focus visibility and restoration, touch targets, zoom and reflow, screen-reader names, contrast, motion preferences, localization, and plain-language copy.
- Review constraints: performance, browser, device, content-length, data-density, privacy, and implementation constraints that change the recommendation.
- Prioritize: rank findings
P0–P3(see diff-review) by blocked task, trust or accessibility harm, frequency, and effort; recommend the smallest coherent improvement before aesthetic extras. - Verify authorized changes: re-run the same representative states at desktop and mobile sizes and record the evidence.
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.
- 2d ago First seen · 50 lines · 44 tokens per session scan A c13d52820cce
product-design-review is a skill published in the GitHub repository fmind/dot (4 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 1,044 once invoked, about $0.0002 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
dprint
Canonical dprint setup — the standard formatter for config and markup files (JSON, Markdown, TOML, YAML). Use when configuring or running formatting for these file types.
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.
release
Cut or verify a versioned release — bump semver, generate the changelog with git-cliff, tag and publish on GitHub, or reconcile an already-published tag and assets.
chezmoi
Manage chezmoi dotfiles: source naming, Go templates, age-encrypted secrets, and the edit-source then apply/diff workflow.