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 anshulixyz/multi-agent-loop-kitnpx agentmods add plugins/anshulixyz/multi-agent-loop-kit/marketplacegit clone --depth 1 https://github.com/anshulixyz/multi-agent-loop-kitGrade A, and why
multi-agent-loop-kit 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
{
"$schema": "https://json.schemastore.org/claude-code-marketplace.json",
"name": "multi-agent-loop-kit",
"owner": {
"name": "Anshuli Gupta",
"email": "[email protected]"
},
"description": "Marketplace for the Multi-Agent Loop Kit. The repo is its own single-plugin marketplace.",
"metadata": {
"description": "Marketplace for the Multi-Agent Loop Kit. The repo is its own single-plugin marketplace."
},
"plugins": [
{
"name": "loop",
"source": "./",
"description": "Turn any repo into a supervised multi-agent loop: spawn parallel coding agents in git worktrees, track them on a radar, and keep a human in the approval loop.",
"category": "orchestration",
"keywords": [
"ai-agents",
"multi-agent",
"worktrees",
"human-in-the-loop"
]
}
]
}
What ships with it
1 file beside marketplace.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.
- 2d ago First seen · 27 lines scan A f4f89fc6338f
multi-agent-loop-kit is a plugin published in the GitHub repository anshulixyz/multi-agent-loop-kit (5 stars, last pushed 2mo 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
nobrainer-tech
NoBrainer Tech portable agent skills.
nobrainer-tech-skills
Portable workflows for one-brief autopilot, specialist teams and verified agentic delivery.
ctx
Plugin marketplace listing 1 plugin: ctx.
ctx
Fast local search and 'git blame' for agent sessions.
clean-room
Carves safety-adjacent requests into a safe scope, executed by a genuinely isolated fresh-context subagent, with an adversarial verify pass and a descope ledger.
full-audit
Exhaustive audit of an entire area (codebase/docs/skills/memory/config) — deterministic sweep + content review, anti-false-positive kill-test, persistent coverage map.