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 | $0.00018 | $0.01483 |
| Opus 5.5 | $0.00007 | $0.00593 |
| Sonnet 5.5 | $0.00004 | $0.00297 |
| Haiku 4.5 | $0.00002 | $0.00148 |
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 1mo 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review the product the way its next user will meet it, not the way its builder hopes it works. $ARGUMENTS may hold the URL, repo path or build, and --harsh for the stress-test mode.
| Invocation | Tone | Output |
|---|---|---|
/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: send code quality to /diff-review and security to /audit-solana or /audit-infra.
Steps
- Ask before reviewing: the product (URL, repo, or running build), the specific target user, the one core action a user must complete, and the stage (prototype, MVP, beta, launched). With no product yet, suggest
/plan-featureor/scaffoldinstead. - Walk through it as that user. With a URL or local build, offer to drive it live through the Playwright MCP (
browser_navigate,browser_snapshot, then click through the core flow;/setup-mcpadds it if it is missing); otherwise walk the screens and code. Record each friction point with where it happens and what the user sees. Checkpoints:- The landing page says what this is within 5 seconds, without crypto jargon.
- Value is visible before wallet connect; no wallet gate with nothing behind it.
- The first meaningful action is reachable within 60 seconds by an obvious path.
- The transaction preview shows what will happen and what it costs before the wallet popup.
- Pending and confirmed states are visible, with an explorer link.
- A failed transaction says why and what to try next.
- After the first action, the next step and a reason to return are clear.
Default mode
Score each dimension 1-10 with evidence from the walkthrough ("onboarding 6/10: step 3 demands a wallet without saying why"), never a bare number. Overall is the mean, one decimal. Per dimension, note what works, what needs improvement, and one concrete fix for its biggest issue.
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.
- 1mo ago Changed · -50 lines · -10 tokens per session 904415b64a88
- 2mo 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 (104 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,483 once invoked, about $0.0001 per session on Opus 5.5. 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.
product-review compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| product-reviewsolanabr/solana-ai-kit | Command | 104 | 1mo ago | MIT | A | 18 | Claude Code |
| design-auditfusengine/agents | Command | 34 | 25d ago | MIT | A | 37 | Claude Code |
| design-componentfusengine/agents | Command | 34 | 25d ago | MIT | A | 26 | Claude Code |
| design-mobilefusengine/agents | Command | 34 | 25d ago | MIT | A | 51 | Claude Code |
| designfusengine/agents | Command | 34 | 25d ago | MIT | A | 35 | Claude Code |
| design-pagefusengine/agents | Command | 34 | 25d ago | MIT | A | 27 | Claude Code |
| uimantacron/manta | Command | 10 | 1mo ago | none | A | 59 | Claude Code |