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 jpicklyk/task-orchestratornpx agentmods add plugins/jpicklyk/task-orchestrator/marketplacegit clone --depth 1 https://github.com/jpicklyk/task-orchestratorGrade A, and why
task-orchestrator-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.
What it actually says
{
"name": "task-orchestrator-marketplace",
"owner": {
"name": "Jeff Picklyk"
},
"description": "Server-enforced workflow discipline for AI agents — persistent work items, dependency graphs, note-gated transitions, and actor attribution",
"plugins": [
{
"name": "task-orchestrator",
"version": "3.6.0",
"description": "Skills, hooks, and workflows for MCP Task Orchestrator. Schema-aware context, note-driven workflow, and session hooks.",
"author": {
"name": "Jeff Picklyk",
"url": "https://github.com/jpicklyk"
},
"homepage": "https://github.com/jpicklyk/task-orchestrator",
"repository": "https://github.com/jpicklyk/task-orchestrator",
"license": "MIT",
"keywords": ["task-management", "project-management", "workflow", "mcp", "ai-orchestration", "claude-code", "ai-agents", "workflow-enforcement", "model-context-protocol", "quality-gates"],
"category": "productivity",
"tags": ["tasks", "features", "projects", "dependencies", "workflows", "mcp-server", "ai-coding"],
"source": "./claude-plugins/task-orchestrator",
"strict": true
}
]
}
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 476402295106
task-orchestrator-marketplace is a plugin published in the GitHub repository jpicklyk/task-orchestrator (205 stars, last pushed 28d 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
sugar-plugins
🍰 Sugar - The autonomous layer for AI coding agents.
clear
Context Layered Engineering for Agentic Resources - Persistent memory and intelligent context management for Claude Code sessions.
awareness-memory
Persistent cross-session memory for Claude Code via Awareness Memory Cloud.
claude-mneme
Automatic session memory for Claude Code — every session picks up where the last one left off.
f5-framework
AI-assisted development framework with quality gates, TDD support, and workflow optimization. 70+ commands, 25 agents, 800+ skills across 14 industry domains.
f5-framework
F5 Framework - AI-powered development framework with quality gates, TDD support, and enterprise-grade tooling for Claude Code.