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 alelaguard/agentguards-pluginsnpx agentmods add plugins/alelaguard/agentguards-plugins/claude-selfhostedgit clone --depth 1 https://github.com/alelaguard/agentguards-pluginsGrade A, and why
agentguards-claude-selfhosted 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 2d ago.
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": "agentguards-claude-selfhosted",
"displayName": "AgentGuards (Self-Hosted)",
"description": "LLM security guardrails for Claude Code, for a self-hosted AgentGuards appliance — jailbreak detection, prompt-injection and web-content scanning, data-exfiltration blocking, and destructive-command authorization, enforced entirely by hooks. No bundled MCP server: Claude Code's .mcp.json cannot point at a per-installation URL, so a shared one would silently talk to AgentGuards' SaaS instead of your appliance. Use agentguards-claude instead if you're on the hosted product.",
"version": "0.1.11",
"author": {
"name": "AgentGuards",
"email": "[email protected]",
"url": "https://agentguards.co"
},
"homepage": "https://agentguards.co",
"repository": "https://github.com/alelaguard/agentguards-plugins",
"license": "MIT"
}
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.
- 2d ago First seen · 15 lines scan A c3ac98c32772
agentguards-claude-selfhosted is a plugin published in the GitHub repository alelaguard/agentguards-plugins (1 stars, last pushed 3d ago), 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
bridgeward
Skeptical-reading and prompt-injection defense for AI coding agents. Trust nothing. Ship safely.
makoto
Holds Claude Code to its word — every claim checked against the agent's own logged record; faked checks blocked, not warned (four narrow advisory self-checks excepted). Two-tier catalog (15 pre-checks, 19 Stop gates), each shipped at measured zero false positives.
warrant-mcp marketplace
Policy firewall for AI agent tool calls — plain-English rules compiled once, enforced by deterministic code.
cordon
Deterministic layer between untrusted content and agent actions.
nuguard
AI Application Security — SBOM generation, static analysis, behavioral testing, and adversarial red-teaming for AI agents and LLM-powered applications.
skillscake
Create or upgrade agent skills with SkillsCake.