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.
npx agentmods add plugins/iii-experimental/agentos/plugin/plugin marketplace add iii-experimental/agentosgit clone --depth 1 https://github.com/iii-experimental/agentosGrade A, and why
agentos 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": "agentos",
"description": "Agent Operating System — self-evolving agents, multi-agent orchestration, 25-screen TUI, 25 LLM providers. Built on iii-engine.",
"version": "0.1.0",
"author": {
"name": "iii-hq",
"url": "https://github.com/iii-hq"
},
"homepage": "https://agentsos.sh",
"repository": "https://github.com/iii-hq/agentos",
"license": "Apache-2.0",
"keywords": ["agent-os", "multi-agent", "orchestration", "self-evolving", "iii-engine", "mcp", "tui"],
"categories": ["Development", "AI Agents", "Workflow Automation", "DevOps"],
"engines": { "claude-code": ">=1.0.0" },
"capabilities": {
"skills": true,
"commands": true,
"agents": true,
"hooks": true,
"mcpServers": true
},
"main": {
"skills": "./skills",
"commands": "./commands",
"agents": "./agents",
"hooks": "./hooks/hooks.json",
"mcp": "./.mcp.json"
}
}
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 · 30 lines scan A 1b4269499fa2
agentos is a plugin published in the GitHub repository iii-experimental/agentos (162 stars, last pushed 3mo ago), licensed Apache-2.0. 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
pilotfish
macOS and Linux Claude Code Plugin beta with hook-based ambient policy activation and namespaced role agents.
longgraph-skill
longgraph — long-horizon agent skill (Claude Code / Codex / Cursor / Grok Build): durable loop-graph runs with verified gates.
kdcube-builder
Build KDCube bundles and run local KDCube development flows from Claude Code.
claude-code-fusion
Multi-model orchestration marketplace for Claude Code.
agent-taskgraph
PMO-led native Claude Code Agent Teams with isolated contexts and document handoffs.
relay
Delegate work packets from a lead Claude Code session to executor sessions in their own iTerm tabs, with session reuse instead of always spawning fresh.