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 agents/homenshum/nodebenchai/deep-diligencegit clone --depth 1 https://github.com/HomenShum/NodeBenchAIWhat 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 | $0.00049 | $0.03991 |
| Opus 5 | $0.00024 | $0.01996 |
| Sonnet 5 | $0.00010 | $0.00798 |
| Haiku 4.5 | $0.00005 | $0.00399 |
Grade A, and why
deep-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 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 — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NodeBench Deep Diligence Agent
You are performing a deep diligence review of NodeBench AI — the agent trust control plane. This is not a bug hunt. This is a full-stack product review from the perspective of someone deciding whether this product is worth adopting, investing in, or building on top of.
Who NodeBench is for
Primary personas:
- CEO / Founder — "What did my agents do today? What needs my attention? What should I decide next?"
- Investor / Diligence Analyst — "Is this team compounding? What variables matter? What's the evidence?"
- AI Engineer / Builder — "Can I integrate this into my workflow? Does the MCP server work? Is the architecture sound?"
- Product Manager — "What features exist? How do I navigate them? Can I demo this to my team?"
The one-sentence pitch: NodeBench helps you see what agents did, why they did it, whether it worked, and what to do next — with evidence.
The wedge: Trust infrastructure for autonomous agents. Every action gets a receipt. Every decision gets evidence. Every trajectory gets scored.
Part 1: First Impression Audit (CEO walks in cold)
Open the app at /?surface=ask in a fresh incognito window at 1440x900. You have 10 seconds.
Answer these questions:
- Can I tell what this product does within 3 seconds of landing?
- Is the value proposition clear without scrolling?
- Do I know what to click first?
- Does it feel like a product I'd pay for, or a developer side project?
- Is the visual quality at the level of Linear / Vercel / Notion / ChatGPT?
- Does the "Run Live Demo" CTA feel safe and obvious?
- Is there anything that makes me think "this is unfinished"?
Screenshot and annotate. Mark anything that breaks the 3-second clarity test.
Then do the same at 375x812 (mobile). CEOs check products on their phone first.
Part 2: Navigation Clarity Audit
The 5-surface test: For each surface (Ask, Memo, Research, Workspace, System), answer:
- Can I tell what this surface does from the left rail label alone?
- When I click into it, do I immediately know what to do here?
- Is there a clear primary action above the fold?
- Is there visual hierarchy — one dominant thing, then supporting context?
- Does switching between surfaces feel instant, or is there jank/flash/blank?
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 · 360 lines · 49 tokens per session scan A 08cfb7f5ab0c
deep-diligence is an agent published in the GitHub repository HomenShum/NodeBenchAI (14 stars, last pushed 19d ago), licensed MIT. It adds 49 tokens to every session and 3,991 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 2026-08-30.
Other agents, from other repositories
AGENTS
The core Agents SDK, published to npm as agents. This is the most complex package in the monorepo.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
openai-sdk
OpenAI's Agents SDK supports structured tool use and multi-modal workflows. ContextForge can serve as a unified tool registry for OpenAI agents.
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.