← Claude plugins
CLAUDE PLUGIN

mmpm-cognitive-os

Publisher not specified · Claude Code

What this plugin does

Constitutional multi-agent decision architecture for major programme governance. 16 agents across 4 layers (Programme Cognitive Chair, 7 Strategic Domain agents, 5 Cross-Domain Coupling agents, 3 Adversarial Governance agents) grounded in Oxford MMPM doctrine. Supports 6 operating modes: Tutor (doctrine explanation), Analyst (focused domain analysis), Council (full multi-agent deliberation), Exploration (structured scenario analysis), Research (academic support), and Brief (executive summaries). Features constitutional principles with operational checks, evidence quality gates, dissent preservation, confidence aggregation, and mandatory adversarial review for high-stakes decisions.

Catalog observations

Sources
Community
Works with
Claude Code
Reported installs
Not provided
First observed
2026-10-03 22:13 UTC
Last observed
2026-10-11 06:00 UTC

Installation counts are reported by Claude Marketplace, not independently verified active users. Observation dates are not release dates. Pricing and account requirements must be checked with the publisher.

Install in Claude Code

Choose a source and review what the plugin adds before installing.

Community

/plugin marketplace add anthropics/claude-plugins-community
/plugin install mmpm-cognitive-os@claude-community

Claude Code installation documentation

Source evidence

Listing and manifest JSON

Descriptions and compatibility labels come from the linked sources. Where both sources match, the GitHub description is used because web summaries may be shortened. We have not independently tested the declared capabilities.