Entity intelligence for any company, market, or question — not a chatbot that answers once, but a system that synthesizes with sources, turns each run into a reusable artifact, and watches for change later. Five-surface app + deep-work Workspace, Convex state, and a hosted public research MCP (npx nodebench-mcp).
These files are HomenShum/NodeBenchAI's own configuration. They tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.
AGENTS.md C 30,200 tok CLAUDE.md A 4,629 tok .claude/skills/demo-video-quality-loop/SKILL.md A — .claude/skills/dep-convex-agent/SKILL.md A 72 tok .claude/skills/dep-skills-howto/SKILL.md A 50 tok .claude/skills/dep-tiptap-pm/SKILL.md A 81 tok .claude/skills/dep-vega/SKILL.md A 80 tok .claude/skills/dep-xlsx/SKILL.md A 95 tok .claude/skills/live-qa-dogfood-loop/SKILL.md A 17 tok .claude/skills/pipeline-operational-loop/SKILL.md A 99 tok .claude/skills/proof-looping/SKILL.md A 118 tok .claude/commands/agentic-reliability-audit.md A — .claude/commands/nodebench-qa.md A — .claude/commands/orchestrating-swarms.md B 59 tok .claude/commands/render-demo-video.md A — .claude/commands/scenario-testing.md A — .claude/commands/usage-report.md A — .claude/agents/deep-diligence.md A 49 tok .claude/agents/deploy-and-launch.md A 41 tok .claude/agents/dogfood-loop.md A 25 tok .claude/agents/nodebench-benchmark-runner.md A 26 tok .claude/agents/nodebench-changelog-updater.md A 24 tok .claude/agents/nodebench-deep-sim-analyst.md A 40 tok .claude/agents/nodebench-frontend-polisher.md A 38 tok .claude/agents/nodebench-supervisor.md A 31 tok .claude/agents/qa-dogfood.md A 44 tok .claude/agents/universal-product-diligence.md A 43 tok