agent-governance plugins

halofyai/halofy

Plugin Claude Code

Bundles 2 hooks, 1 MCP server

HaloMem organizational memory: session-start recall, session-end capture, MCP tools. Configure with HALOMEMURL and HALOMEMAPIKEY.

ucsandman/DashClaw

Plugin Claude Code

Bundles 1 skill, 4 hooks · 88 tokens together

DashClaw tool governance hooks, remote approvals, execution evidence, and setup guidance for Claude Code.

vaaraio/vaara

Plugin Claude Code

Bundles 2 commands, 4 hooks · 48 tokens together

Accountable autonomy for Claude Code. PreToolUse runs a two-layer check on Bash, WebFetch, WebSearch, Write, Edit, NotebookEdit, Task, SendMessage and MCP calls (regex deny patterns on shell, web and file mutation; conformal risk scorer on MCP). PostToolUse writes a hash-chained SQLite audit record across the same set.

event4u-app/agent-config

Plugin Claude Code

Plugin marketplace listing 1 plugin: agent-config.

getaxonflow/axonflow-claude-plugin

Plugin Claude Code

Bundles 7 skills, 10 commands, 2 hooks, 1 MCP server · 459 tokens together

Policy enforcement, PII detection, and audit trails for Claude Code. Govern tool execution, scan outputs for sensitive data, and maintain compliance-grade records of every action.

ericlovold/sanction

Plugin Cursor

Bundles 4 skills · 162 tokens together

Independent authorization plane for AI agents — approve, escalate, or deny spend, tools, credentials, and provisioning. Wires the hosted wallet MCP; the host must ask before acting.

ArdurAI/ardur

Plugin Claude Code

Bundles 5 hooks

Ardur runtime governance for Claude Code: mission-bound deny gating and signed Execution Receipts on tool calls.

chrbailey/promptspeak-mcp-server

Plugin Claude Code

Bundles 3 skills, 1 MCP server · 87 tokens together

Pre-execution governance for AI agents. Intercepts MCP tool calls with deterministic blocking, human-in-the-loop holds, and behavioral drift detection.

evanmcgoogan/skin-in-the-game

Plugin Claude Code

Bundles 6 skills, 1 hook · 731 tokens together

Give your AI agent an operating contract. Twelve build principles — the CEO/CTO division of labor, grill-me-before-you-build, reality-graded honesty — actively enforced through composable skills and a session-start hook. Stop your agent from being a yes-man.

johnrucnapier-sketch/ACGM-for-Claude-Code

Plugin Claude Code

Bundles 4 skills, 5 hooks · 377 tokens together

A set of working rules for Claude Code, Anthropic’s coding assistant, aimed at keeping long-running development work on track. It checks destructive actions, grounds work in evidence, and avoids claims that cannot be supported.