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 ssheleg/agent-stacknpx agentmods add plugins/ssheleg/agent-stack/marketplacegit clone --depth 1 https://github.com/ssheleg/agent-stackGrade A, and why
agent-stack 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
{
"$schema": "https://json.schemastore.org/claude-code-marketplace.json",
"name": "agent-stack",
"owner": {
"name": "ssheleg",
"url": "https://github.com/ssheleg"
},
"description": "Production patterns for building agent orchestrators — and for billing the LLM access they burn.",
"plugins": [
{
"name": "agent-stack",
"displayName": "Agent Stack",
"source": "./plugins/agent-stack",
"description": "Four skills: agent-orchestrator — tool-calling loops, pipelines with checkpoints, provider routing with fallback, memory architecture, plus the wallet side of reselling LLM access; agent-evals — run/trace/thread evals, LLM judges, and fixtures grown from production; agent-interop — MCP servers and clients, A2A agent cards, the MCP Registry, and gateways; agent-harness — system prompts, tool shaping, workflow-vs-agent, and auditing an agent system.",
"version": "0.17.1",
"author": {
"name": "ssheleg",
"url": "https://x.com/sshlg93"
},
"repository": "https://github.com/ssheleg/agent-stack",
"homepage": "https://github.com/ssheleg/agent-stack",
"license": "MIT",
"keywords": [
"agent",
"orchestrator",
"llm",
"tool-calling",
"multi-agent",
"openrouter",
"llm-billing",
"claude-code",
"cursor"
],
"category": "development"
}
]
}
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 · 38 lines scan A ace41598142e
agent-stack is a plugin published in the GitHub repository ssheleg/agent-stack (2 stars, last pushed yesterday), 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
cotal-mesh
The Cotal mesh adapter for Claude Code — join a shared pub/sub space as a lateral peer.
connector-claude-code
Join the Cotal mesh — coordinate with other AI agents as lateral peers (presence, messaging, role requests) over NATS.
skills-plugin
Cotal-authored Claude Code skills for coordinating agent teams on the mesh.
systemprompt-marketplace
Plugin marketplace listing 4 plugins: systemprompt, enterprise-demo, systemprompt-admin, systemprompt-dev.
systemprompt-admin
CLI administration tools for managing users, analytics, agents, services, jobs, logs, and database.
systemprompt-dev
Complete development toolkit: Rust, frontend, architecture standards, extension development guides, and 6 specialized agents.