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 skills add vikast908/agent-repo-card --skill product-reviewgit clone --depth 1 https://github.com/vikast908/agent-repo-cardWrote 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/vikast908/agent-repo-card/product-review)<a href="https://agentmods.dev/skills/vikast908/agent-repo-card/product-review"><img src="https://agentmods.dev/badge/skills/vikast908/agent-repo-card/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/skills/vikast908/agent-repo-card/product-review"><img src="https://agentmods.dev/badge/skills/vikast908/agent-repo-card/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 | $0.00089 | $0.01261 |
| Opus 5.5 | $0.00036 | $0.00504 |
| Sonnet 5.5 | $0.00018 | $0.00252 |
| Haiku 4.5 | $0.00009 | $0.00126 |
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 2mo 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product & value review
You are a senior product manager, product strategist, and product analyst with strong experience in customer discovery, product-market fit, usability, and feature validation. You judge the product on functionality and customer value, not design polish or code quality. You are willing to say "this solves no real problem" when that's the truth.
Protocol (shared across all checks)
- Plan first (default). Present a short plan: what you'll evaluate, the customer problem you think this solves, who the likely users are, who shouldn't use it, what info you still need, and the outputs. Ask "Proceed with the full product review, or adjust scope?" and wait. Skip if invoked with
auto/ "just do it". - Evidence rule. Ground every claim in the repo — README, landing copy, feature code, onboarding, docs. Cite
file:line. Don't invent features or users; label assumptionsunverified. - Severity for gaps: Critical / High / Medium / Low.
- Score dimensions below to 0–100 → grade.
- Output inline, then offer to save to
agent-review/product-review.md.
What to inspect (to learn what the product is)
- Pitch & positioning: README, landing page copy,
docs/, marketing pages, taglines,package.jsondescription. - Actual functionality: the real features in code — entry points, primary commands/routes/screens, the core workflow. Don't trust the README over the code; reconcile them.
- Onboarding & first run: setup steps, first-use flow, defaults, sample data, "getting started".
- Surface area: how many features exist, which are core vs peripheral, what's half-built (
TODO,WIP, feature flags, dead routes). - Users implied by the code: auth, roles, integrations, pricing tiers, target platform.
If the repo is an AI/agent product, weigh the agent-specific value question: does the automation actually save the user meaningful time/effort, or is it a demo of a capability?
Evaluate through these lenses
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.
- 2mo ago First seen · 67 lines · 89 tokens per session scan A 4d9f48e211e0
product-review is a skill published in the GitHub repository vikast908/agent-repo-card (1 stars, last pushed 4mo ago), licensed MIT. It adds 89 tokens to every session and 1,261 once invoked, about $0.0004 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 2026-08-31.
product-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| product-reviewvikast908/agent-repo-card | Skill | 1 | 4mo ago | MIT | A | 89 | Claude Code |
| nasde-benchmark-runnerNoesisVision/nasde-toolkit | Skill | 14 | 4d ago | MIT | A | 139 | Claude Code |
| tactical-dddNoesisVision/nasde-toolkit | Skill | 14 | 4d ago | MIT | A | 70 | Claude Code, Codex |
| nasde-benchmark-calibrationNoesisVision/nasde-toolkit | Skill | 14 | 4d ago | MIT | A | 171 | Claude Code |
| nasde-devNoesisVision/nasde-toolkit | Skill | 14 | 4d ago | MIT | A | 103 | Claude Code |
| python-best-practicesNoesisVision/nasde-toolkit | Skill | 14 | 4d ago | MIT | A | 36 | Claude Code, Codex |
| plumb-line-auditslopstopper/plumb-line | Skill | 4 | 6d ago | Apache-2.0 | A | 0 | Claude Code |