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 agent-sh/agentsysnpx agentmods add plugins/agent-sh/agentsys/marketplacegit clone --depth 1 https://github.com/agent-sh/agentsysGrade A, and why
agentsys marketplace 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.
How it starts
The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "agentsys",
"description": "26 specialized plugins for AI workflow automation - task orchestration, PR workflow, slop detection, code review, drift detection, enhancement analysis, documentation sync, unified static analysis, durable memory, negative behavior memory, skill and system prompt curation, perf investigations, topic research, agent config linting, cross-tool AI consultation, structured AI debate, workflow pattern learning, codebase onboarding, contributor guidance, Zig language support, Mojo language support, and Ada/SPARK language support",
"version": "6.0.2",
"owner": {
"name": "Avi Fenesh",
"url": "https://github.com/avifenesh"
},
"repository": "https://github.com/agent-sh/agentsys",
"keywords": [
"ai",
"llm",
"agents",
"agentic",
"claude-code",
"opencode",
"codex",
"mcp",
"automation",
"workflow",
"code-review",
"multi-agent"
],
"plugins": [
{
"name": "next-task",
"source": {
"source": "url",
"url": "https://github.com/agent-sh/next-task.git",
"ref": "v1.1.2",
"commit": "8feba0141a895d651a850cbe724a0e333c24a3a0"
},
"description": "Master workflow orchestrator: autonomous workflow with model optimization (opus/sonnet/haiku), two-file state management, workflow enforcement gates, 8 specialist agents",
"version": "1.1.2",
"category": "productivity",
"homepage": "https://github.com/agent-sh/next-task"
},
{
"name": "prepare-delivery",
"source": {
"source": "url",
"url": "https://github.com/agent-sh/prepare-delivery.git",
"commit": "0e9685fe0e93e058af5ca9a0374f4f97e1db878c",
"ref": "v0.1.2"
},
"description": "Pre-ship quality gates: deslop, simplify, agnix, enhance, review loop, delivery validation, docs sync",
"version": "0.1.2",
"category": "productivity",
"homepage": "https://github.com/agent-sh/prepare-delivery"
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 · 344 lines scan A a1a9a080264f
agentsys marketplace is a plugin published in the GitHub repository agent-sh/agentsys (980 stars, last pushed 5d 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 2026-08-30.
Other plugins, from other repositories
no-human
File a task with nohuman and check on it without leaving Claude Code: taskadd and taskstatus over your local nohuman server (127.0.0.1:8420). nohuman plans, codes, tests and has the work reviewed by a second model, then opens the pull request and stops.
supervise-loop
Autonomous supervisor/worker/critic iteration loop for Claude Code (the evaluator-optimizer pattern). Delegate a goal once; a supervisor agent grades each round against a checkable rubric — mechanical checks plus a SEPARATE critic sub-agent — and re-dispatches with feedback until the rubric passes or a hard cap is hit.
agentlas-core-engine marketplace
Plugin marketplace listing 1 plugin: hephaestus.
claude
Connect Claude Code to your local OpenLoomi runtime. One-command install, mirror Claude's lifecycle onto the Loomi Pet, and auto-archive every Stop into your OpenLoomi memory. Talks to your local OpenLoomi over HTTP and the OpenLoomi helper CLI. AI provider config is owned by OpenLoomi itself — this plugin never reads.
skill-based-architecture
Restructure oversized SKILL.md or scattered project rules into a well-organized Skill directory, with cross-tool thin shells, SessionStart hooks, Task Closure Protocol, and self-evolving workflows.
claudeclaw
Persistent agent orchestrator for Claude Code. Multi-channel message routing, triage, and SWE task management. Run /claudeclaw:setup to create your first instance and configure channels.