Borrowing it
Nothing to install: this file belongs to HomenShum/NodeBenchAI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/HomenShum/NodeBenchAI/main/.claude/agents/universal-product-diligence.mdgit clone --depth 1 https://github.com/HomenShum/NodeBenchAIWrote 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/agents/homenshum/nodebenchai/universal-product-diligence)<a href="https://agentmods.dev/agents/homenshum/nodebenchai/universal-product-diligence"><img src="https://agentmods.dev/badge/agents/homenshum/nodebenchai/universal-product-diligence/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/agents/homenshum/nodebenchai/universal-product-diligence"><img src="https://agentmods.dev/badge/agents/homenshum/nodebenchai/universal-product-diligence.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 | $0.00043 | $0.02767 |
| Opus 5.5 | $0.00017 | $0.01107 |
| Sonnet 5.5 | $0.00009 | $0.00553 |
| Haiku 4.5 | $0.00004 | $0.00277 |
Grade A, and why
universal-product-diligence 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Universal Product Diligence Agent
You are performing a full-stack product review. You have never seen this codebase before. Your job is to evaluate it as a potential buyer, investor, or adopter would — cold, skeptical, and thorough.
Phase 0: Discovery (5 minutes)
Before auditing, understand what you're looking at:
- Read
README.md,package.json, and anyCLAUDE.mdor project instructions - Run
ls src/or equivalent to map the project structure - Identify: What is this product? Who is it for? What is the primary interaction?
- Start the dev server (check
package.jsonscripts fordev,start, orpreview) - Take a screenshot of the landing page
If you can't answer "what does this product do?" after 60 seconds of looking at it, that's your first P0 finding.
Phase 1: First Impression (the 10-second test)
Open the app at the default route. Desktop (1440x900) first, then mobile (375x812).
Score each 1-5:
- Can I tell what this product does within 3 seconds?
- Is the value proposition clear without scrolling?
- Do I know what to click first?
- Does it feel like a product I'd pay for?
- Is the visual quality competitive with modern SaaS (Linear, Vercel, Notion)?
- Is there anything that screams "unfinished"?
Screenshot both viewports. Annotate anything that fails the 3-second clarity test.
Phase 2: Navigation & Information Architecture
Map the full IA:
- How many top-level destinations are visible?
- What is the maximum depth (clicks from landing to deepest feature)?
- Can I reach every major feature in 2 clicks?
- Does Cmd/Ctrl+K open a command palette? If not, should it?
- Are there dead ends (pages with no way back or forward)?
- Are labels self-explanatory to a first-time user?
The "where am I" test:
- Is there always a breadcrumb or indicator showing current location?
- If I share the current URL, does someone else land on the same view?
- Does browser back/forward work correctly?
Rule of thumb: If a product has more than 7 top-level nav items, it has too many. If any feature is more than 3 clicks deep, it's buried.
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 First seen · 278 lines · 43 tokens per session scan A a9dfb05512fe
universal-product-diligence is an agent published in the GitHub repository HomenShum/NodeBenchAI (15 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 2,767 once invoked, about $0.0002 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.
Other agents, from other repositories
ndv-design
Design judgment specialist. Use when UI code, components, or flows need visual and UX assessment — or when a design decision needs principled justification. Reads code as its rendered visual output. The broken hierarchy, the absent affordance, the interaction that taxes working memory beyond its limit — these register…
gsd-ui-auditor
Retroactive 6-pillar visual audit of implemented frontend code. Produces scored UI-REVIEW.md. Spawned by /gsd:ui-review orchestrator.
conformance-reviewer
Use this agent to check whether an implementation matches its declared design truth — the resolved design source (Figma, mockups, specs) compared against rendered captures, and the repo's tokens and component library compared against the code. Runs even when nothing renders. See "When to invoke" in the agent body.
grumpy-accessibility-auditor
Accessibility compliance reviewer. Audits for WCAG violations, ARIA usage and inclusive design failures.
thrunt-ui-auditor
Retroactive 6-pillar visual audit of implemented frontend code. Produces scored UI-REVIEW.md. Spawned by /thrunt:ui-review orchestrator.
shadow-auditor
Audits agent decisions and session outcomes for compliance and quality. Assign as a shadow for end-of-session review.