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.
git clone --depth 1 https://github.com/solanabr/solana-ai-kitWrote 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/commands/solanabr/solana-ai-kit/product-review)<a href="https://agentmods.dev/commands/solanabr/solana-ai-kit/product-review"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/product-review/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/commands/solanabr/solana-ai-kit/product-review"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/product-review.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 | $0.00028 | $0.01790 |
| Opus 5 | $0.00014 | $0.00895 |
| Sonnet 5 | $0.00006 | $0.00358 |
| Haiku 4.5 | $0.00003 | $0.00179 |
Grade A, and why
product-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 13d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are reviewing a product the way its next user will experience it — not the way its builder hopes it works. Default mode is balanced and structured; --harsh is a stress test.
Related Skills
- ext/sendai/ — Solana Agent Kit patterns for agent-product reviews
- Playwright MCP (
mcp__playwright__*) — drive the live app for the walkthrough below
Modes
| Invocation | Tone | Output contract |
|---|---|---|
/product-review |
Balanced, constructive | 8-dimension scorecard + bucketed roadmap |
/product-review --harsh |
Brutal but constructive | 10 weighted dimensions + verdict + exactly 3 fixes |
This is not a code review — route code quality to /diff-review and security to /audit-solana / /audit-infra.
Step 1: Gather Context
Ask before reviewing — never assume:
- What is the product? (URL, repo, or running build)
- Who is the target user, specifically?
- What is the ONE core action a user should complete?
- Stage: prototype / MVP / beta / launched?
If no product exists yet, stop and suggest /plan-feature or /scaffold instead.
Step 2: First-Time-User Walkthrough
Become the target user from Step 1. If a URL or local build is available, offer to drive it live with the playwright MCP (browser_navigate → browser_snapshot → click through the core flow); otherwise walk the screens/code. Record an observation per checkpoint:
- Landing explains what this is in < 5 seconds, without crypto jargon
- Value is visible BEFORE wallet connect (no wallet-gate with nothing behind it)
- First meaningful action reachable in < 60 seconds, path obvious
- Transaction preview shows what will happen + cost before the wallet popup
- Pending → confirmed states visible, with explorer link
- A failed transaction explains why and what to try next
- After the first action, it's clear what to do next — and there's a reason to return
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.
- 13d ago First seen · 162 lines · 28 tokens per session scan A dae76a20b6eb
product-review is a command published in the GitHub repository solanabr/solana-ai-kit (101 stars, last pushed 23d ago), licensed MIT. It adds 28 tokens to every session and 1,790 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
design-audit
Audit an existing HTML/CSS design. Deterministic checks only (contrast, fonts, colors, states, dark mode) plus a visual pass. No generation.
design-mobile
Design a mobile screen or flow. This command never writes SwiftUI or Compose — the deliverable is a device-framed HTML mockup plus a handoff spec for the platform developer.
design-component
Generate a single component using existing design-system.md tokens. Skips inspiration browsing — fast path for isolated UI elements.
design-page
New page or screen in an existing project. Skips design-system creation — reuses the existing design-system.md tokens.
design
Full design pipeline for a web or web-app target: brief → tokens → generation → motion → review. Use /design:mobile for iOS/Android instead.
ui
Convert design files (screenshots, Figma exports, wireframes) into production-ready UI components matching the project's conventions. Reads from ui-designs/ by default. Enforces DRY by detecting existing components to reuse. Generates responsive, accessible, typed components with tests and optional Storybook stories.