Business & Operations Codex plugins

Publisher description

Assess a business workflow before investing in automation. AI Workflow Architect provides a free Architecture Readiness Preview: a readiness score and label, automation suitability, the main bottleneck, missing information and high-level improvement prioritie… …e trigger, people, systems, current steps and problems. See what may be automated, what should stay human, control themes and a broad future-state direction. If essential context is missing, the tool asks for clarification before assessing. Use it for client onboarding, approvals, support, employee…

Publisher description

The human intelligence layer for AI. OriginalVoices gives ChatGPT instant access to real human perspectives - so you can ground decisions and AI outputs in what your target audience actually thinks, feels, and values. Instead of guessing or relying on assumptions, get authentic fe…

Publisher description

Onsa finds real B2B prospects — actual people with LinkedIn profiles — scored against your ideal-customer profile, and keeps every search as a campaign you can come back to. Ask for leads in plain language and Onsa's agent runs a live search, returning each person with their title, company, a 1–5 sc… …uced replies. Onsa carries the outreach side too. It returns what prospects wrote back — the actual text, not just counts — alongside the funnel: invites sent, invites accepted, messages sent, and replies split by sentiment. When a draft reads like a mail-merge, you can pull up the research memo Ons…

Publisher description

Built for GPT, Codex, Claude, Grok Bot (GrokBot), Hermes, OpenClaw, Cursor: Humans and agents work on the same Brain, live Artifacts, Docs, Reports, Slides, Apps, Websites, Designs, with Shared Context such as Second Brain with full version history and access control.

Publisher description

VeriPIE helps users compare business options, analyze selected CSV or text data, and inspect decision reports. ChatGPT reasons using the VeriPIE skill and submits a structured draft. The MCP server stores selected evidence, executes bounded CSV and mathematical calculations, checks framework requirements and renders original HTML, text or JSON reports. The server makes no model-provider calls. Reports remain provisional and explicitly state that independent AI or human review was not performed. Calculations do not establish source truth, guarantee outcomes or authorize business actions.