22 tagged agent-safety, measured the same way as everything else here.
Browse within: ai-governance 56claude-plugins 56cli 7approval-workflow 6audit-trail 6autonomous-agent 6claude-code-marketplace 6claude-code-plugin 6
Skill Claude CodeCodex
Install, observe, tune, and enforce Sponsio: a runtime contract layer for LLM agents that blocks unsafe tool calls and scores output quality against declared rules. Use when the user wants to set up / add / install Sponsio, add guardrails or runtime safety to an LLM agent, generate or refine a sponsio.yaml, audit tool…
kajogo777/the-agent-sandbox-taxonomy
Skill Claude CodeCodex
You are an expert in the Agent Sandbox Taxonomy (AST), a framework for evaluating and comparing AI agent sandbox security. This skill enables two capabilities.
Skill Claude CodeCodex
Use Afu Brain as a MASL butler brain before executing OpenClaw or other agent tools. It turns private owner memory and human intent into safe decisions, skill routing, and approval gates.
Skill Claude Code
Safety, privacy, cost management, and frank advice for building always-on AI agents with episodic memory. Covers data hygiene, privacy risk surfaces, runaway cost prevention, scope creep, psychological effects of persistent AI companions, and responsible deployment patterns. This is the skill that tells you what can…
Skill Claude CodeCodex
Use ProofFlow from Codex for Agent Work Ledger and maintainer workflows: wrap complex AI coding tasks in a Ledger, review diffs, export Proof Packets, triage issue text, and keep claims evidence-backed.
Skill Claude CodeCodex
An AI and MCP security scanner aligned with the OWASP MCP Top 10, a list of common risks for tool-connected AI systems. It checks for issues such as prompt injection, command injection, poisoned tools, leaked secrets, unsafe permissions, supply-chain attacks, SSRF, and banned Chinese-language content.
Skill Claude CodeCodex
Risk-gated MoA escalation and model auto-tuning.
ASER-ho/coding-agent-safety-gate
Skill Claude CodeCodex
A set of safety rules for keeping an AI coding assistant within an approved workspace, task, file scope, and security boundary.
Skill Claude CodeCodex
When to use. The operator has identified an ICP (ideal customer profile) and wants a deliverability-aware sequence to test it.
Skill Claude CodeCodex
Use Airlock before installing or executing packages, running risky shell commands, committing generated code, or declaring an agent task complete. Airlock detects hallucinated/slopsquatted dependencies, destructive commands, leaked secrets, and suspicious test changes.
Skill Codex
Retrieve revision-pinned software-agent failure evidence and unresolved verification gates without authorizing execution. Use before destructive, irreversible, privileged, broad-scope, production, infrastructure, database, filesystem, permission, MCP configuration, or supply-chain operations; when reviewing a…
Skill Claude CodeCodex
Use when Hermes needs to intake, score, and report on public bounty-like opportunities with Bounty Sieve while preserving an offline-by-default, read-only safety boundary.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: