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 microsoft/agent-governance-toolkitnpx agentmods add plugins/microsoft/agent-governance-toolkit/agent-governance-claude-codegit clone --depth 1 https://github.com/microsoft/agent-governance-toolkitGrade A, and why
agt-governance 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": "agt-governance",
"description": "AGT governance hooks and MCP tools for Claude Code sessions",
"version": "5.0.0",
"author": {
"name": "Microsoft Corporation",
"email": "[email protected]"
},
"homepage": "https://github.com/microsoft/agent-governance-toolkit/tree/main/agent-governance-claude-code",
"repository": "https://github.com/microsoft/agent-governance-toolkit",
"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 · 13 lines scan A fb03c4f6003f
agt-governance is a plugin published in the GitHub repository microsoft/agent-governance-toolkit (6,175 stars, last pushed today), 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 2026-08-30.
Other plugins, from other repositories
agentlas-core-engine
Plugin marketplace listing 1 plugin: hephaestus.
nist-ai-rmf
Expert NIST AI Risk Management Framework (AI RMF 1.0) advisor — gap assessments, organizational profiles, GOVERN/MAP/MEASURE/MANAGE function guidance, AI risk registers, trustworthiness evaluation, and cross-framework mapping to ISO 42001, EU AI Act, and NIST CSF.
aeon
Aeon's Claude Code plugins - install the operator console for setting up and running an Aeon agent instance.
aeon
Operator console for an Aeon agent instance: enable/schedule/edit skills, wire secrets and channels, debug runs, and mine past coding-agent chats into scheduled skills.
dashclaw
DashClaw governance, integration, troubleshooting, and platform intelligence for Claude Code.
ai-team-os
Plugin marketplace listing 1 plugin: ai-team-os.