Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
/plugin marketplace add mlawsonking/MCPnpx agentmods add plugins/mlawsonking/mcp/agent-guards-plugingit clone --depth 1 https://github.com/mlawsonking/MCPGrade A, and why
agent-guards scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "agent-guards",
"displayName": "Agent Guards",
"version": "1.4.0",
"description": "Deterministic security checks in Claude Code's path: package names before an install, secrets and code rules on what was just written, injection and Unicode-obfuscation patterns in fetched pages. No network call in any hook, no model in any check.",
"author": {
"name": "mlawsonking",
"url": "https://github.com/mlawsonking"
},
"homepage": "https://github.com/mlawsonking/MCP/tree/main/agent-guards-plugin",
"repository": "https://github.com/mlawsonking/MCP",
"license": "MIT",
"keywords": [
"security",
"secrets",
"supply-chain",
"typosquat",
"prompt-injection",
"code-scanning"
]
}
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 22 lines scan A c1cec6ad41a4
agent-guards is a plugin published in the GitHub repository mlawsonking/MCP (0 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
trustabl
Plugin marketplace listing 1 plugin: trustabl.
trustabl
Self-audit AI agent, tool, and MCP-server code for security and reliability misconfigurations with Trustabl, the agent reliability scanner for the OpenAI Agents SDK, Claude Agent SDK, Google ADK, and MCP. Ships two skills (trustabl-scan and trustabl-enrich) and a subagent (trustabl) that together form a scan → enrich…
cerul
Cerul video memory infrastructure for AI products — understand, remember, and access video.
ryk
ryk safety hooks and skills for Claude Code.
public-apis-live
Discover working public APIs for any task, with their real endpoints. Auto-verified, refreshed daily.
runapi-cli
RunAPI CLI skill for Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents.