edgemoorlf/boardroom-agents

Python multi-agent board-records assistant with a governance agent that judges every answer against an externalized policy before release — allow, revise, or block. Anonymity is enforced by the schema, not the prompt. MCP boundary with audit trail.

0Stars on the repository
3Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

redteam-anonymity

01

edgemoorlf/boardroom-agents

Skill Claude CodeCodex

Adversarially probe the board assistant's anonymity guarantee. Generates new attack phrasings, runs them through the governed pipeline, separates real leaks from detector noise, and promotes survivors into the golden eval set. Use when changing the policy, the governance checks, the research prompt, the tool layer, or…

not rated 0 1mo ago A 75 tokens