ai safety plugins

microsoft/agent-governance-toolkit

Plugin Claude Code

Agent Governance Toolkit plugins for Claude Code.

microsoft/agent-governance-toolkit

Plugin Claude Code

AGT governance hooks and MCP tools for Claude Code sessions.

kenryu42/cc-safety-net

Plugin Claude Code

Plugin marketplace listing 1 plugin: cc-safety-net.

kenryu42/cc-safety-net

Plugin Claude Code

Block destructive commands and secret access.

pegasi-ai/reins

Plugin Claude Code

Plugin marketplace listing 1 plugin: reins.

pegasi-ai/reins

Plugin Claude Code

Security controls for AI agents — deterministic policy enforcement, OWASP ASI10 scanning, and audit trails.

pegasi-ai/reins

Plugin Claude Code

Runtime security for AI agents. Blocks destructive actions before execution, routes high-risk operations through human approval, and maintains an immutable audit trail. Covers OWASP MCP Top 10, ASI Top 10, and Agentic Skills Top 10.

assafkip/research-mode

Plugin Claude Code

Plugin marketplace listing 1 plugin: research-mode.

assafkip/research-mode

Plugin Claude Code

Anti-hallucination research mode for Claude Code. Toggle on/off to enforce citation requirements, source grounding, and 'I don't know' behavior.

aisa-group/skill-inject

Plugin Claude Code

The CMS Coverage Connector gives Claude access to Medicare Part B coverage policies from the CMS Coverage Database, including National Coverage Determinations (NCDs) and Local Coverage Determinations (LCDs).

aisa-group/skill-inject

Plugin Claude Code

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.

aisa-group/skill-inject

Plugin Claude Code

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval/inspect-ai.

FlyFission/nuclear-grade-context-engineering

Plugin Claude Code

Nuclear-grade context engineering — the repository as its own Claude Code plugin marketplace.

FlyFission/nuclear-grade-context-engineering

Plugin Claude Code

Risk-graded context engineering for AI-assisted software work — a catalog of agent skills, paste-ready command prompts, and change-record templates that keep agent work questioned, controlled, and reviewable.

frmoretto/clarity-gate

Plugin Claude Code

Pre-ingestion verification for epistemic quality in RAG systems. Ensures documents are properly qualified before entering knowledge bases.

frmoretto/hardstop

Plugin Claude Code

Plugin marketplace listing 1 plugin: hs.

frmoretto/hardstop

Plugin Claude Code

Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.

IgorGanapolsky/ThumbGate

Plugin Claude Code

Plugin marketplace listing 1 plugin: thumbgate.

IgorGanapolsky/ThumbGate

Plugin Claude Code

One 👎 becomes a hard rule the agent cannot bypass. Captures thumbs-down feedback, distills it into PreToolUse Pre-Action Checks, enforced across every future Claude Code session.

IgorGanapolsky/ThumbGate

Plugin Claude Code

Run Codex review, adversarial review, and second-pass handoffs from Claude Code while keeping ThumbGate reliability memory in the loop.

faberlens/hardened-skills

Plugin Claude Code

Plugin marketplace listing 28 plugins: ai-agents-hardened-skills, coding-hardened-skills, devops-hardened-skills, documents-hardened-skills, finance-hardened-skills.

airblackbox/airblackbox

Plugin Claude Code

Plugin marketplace listing 1 plugin: air-blackbox.

airblackbox/airblackbox

Plugin Claude Code

EU AI Act compliance scanner and trust infrastructure for Python AI projects.

MaxwellCalkin/sentinel-ai

Plugin Claude Code

Plugin marketplace listing 1 plugin: sentinel-ai.