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 richfrem/agent-plugins-skillsnpx agentmods add plugins/richfrem/agent-plugins-skills/agent-loopsgit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsGrade A, and why
agent-loops 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": "agent-loops",
"version": "2.2.0",
"description": "Composable agent loop architectures for learning loops, agent orchestration (0-to-N inner agents), and red team coordination. Framework-agnostic: works with any CLI agent (Claude, Gemini, Copilot, OpenHands, etc.).",
"author": {
"name": "Richard Fremmerlid"
},
"repository": "https://github.com/richfrem/agent-plugins-skills",
"license": "MIT",
"keywords": [
"agent-loops",
"orchestrator",
"learning-loop",
"dual-loop",
"agent-swarm",
"red-team-review",
"multi-agent"
],
"capabilities": [
"orchestration",
"multi-agent",
"red-team-review"
]
}
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 · 25 lines scan A 51f987eceaf2
agent-loops is a plugin published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed 4d 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
agent-harness-generator
MetaHarness — mint a custom AI agent harness from any repo. Paste a GitHub URL or start blank; output runs on Claude Code, OpenAI Codex, pi.dev, Hermes, OpenClaw, or RVM. WASM kernel (Rust → wasm-bindgen + NAPI-RS), 6 hosts, witness-signed Ed25519 releases, GCP Secret Manager validation. Browser Studio + npx metaharne.
Citadel
Claude Code harness for routing requests, preserving run state, enforcing hooks, and recording evidence.
hcf
Autonomous development orchestration with parallel TDD execution.
recursive-decomposition
Agent skill for long-context work: decompose tasks that exceed the context window with filtering, chunking, recursive sub-agents and verification, based on the Recursive Language Models research.
devin-handoff
Hand off tasks to a cloud Devin session — VM, browser, shell, and full repo access. Create a session, get a URL, poll until done.
agents-md-optimizer
Audit bloated agent-instruction files (CLAUDE.md, AGENTS.md, and their variants) and rewrite them lean, or author a new one from scratch following the 200-line recipe-book principle. Detects anti-patterns like embedded API docs, negative rules, tutorials, and preemptive file preloads.