Opencouncil Contract Inspector
Proven 2026 Multi-Agent AI Review System – Verdict-Driven Quality Control
Install
git clone https://github.com/vikashjeyaraman/opencouncil-contract-inspectorInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →🏛️ VeritasBoard — Multi-Agent Deliberative Quality Engine
Where artificial intelligence meets the rigor of a corporate boardroom, producing decisions that withstand the scrutiny of ten simulated experts and ten veteran reviewers.
🌟 Overview
VeritasBoard is an AI orchestration framework that reimagines quality control through simulated institutional wisdom. Rather than a single model generating output, VeritasBoard convenes two distinct chambers of artificial agents: a Drafting Council of ten specialist employees who produce preliminary work, and an Oversight Board of ten industry-veteran reviewers who challenge, refine, and validate that work. The user sees only the final, reconciled verdict — a distillation of twenty distinct perspectives, each engineered to resist sycophancy and groupthink.
This repository houses the core architecture, configuration templates, and integration modules that enable any language model to participate in structured, multi-agent deliberation. VeritasBoard is not merely a wrapper; it is a cognitive constitution — a set of rules that governs how artificial minds debate, dissent, and converge.
🧠 The Anti-Sycophancy Imperative
Modern language models suffer from a well-documented tendency: they agree with users. They seek approval. They hedge. VeritasBoard addresses this through deliberative adversarial review. Each of the ten Oversight Board members is prompted not to validate, but to interrogate — to find logical flaws, unsupported claims, hidden assumptions, and rhetorical gambits. The drafting agents, in turn, must defend their positions with evidence and structured reasoning.
The result is output that has been stress-tested by voices programmed to disagree.
🏛️ Architectural Pillars
Chamber 1: The Drafting Council (Ten Specialist Employees)
| Agent Role | Simulated Expertise | Deliberative Function |
|---|---|---|
| Researcher | Data gathering & citation | Sources all factual claims |
| Analyst | Logical structuring | Ensures argument coherence |
| Writer | Narrative flow & clarity | Produces readable output |
| Critic | Internal inconsistency detection | Flags contradictions before external review |
| Synthesizer | Cross-domain integration | Merges diverse viewpoints |
| Ethicist | Moral & compliance auditing | Screens for bias & harm |
| Technologist | Implementation feasibility | Checks practical constraints |
| Economist | Resource & cost analysis | Evaluates trade-offs |
| Strategist | Long-term consequence modeling | Considers second-order effects |
| Presenter | Final formatting & summarization | Prepares distilled verdict |
Chamber 2: The Oversight Board (Ten Industry Veterans)
Similar plugs
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Production-grade engineering skills for AI coding agents.
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create prototypes, websites, apps, dashboards, presentations, images, and videos with your team…