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 wu736139669/agent-taskgraph-protocolnpx agentmods add plugins/wu736139669/agent-taskgraph-protocol/marketplacegit clone --depth 1 https://github.com/wu736139669/agent-taskgraph-protocolGrade A, and why
agent-taskgraph-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": "agent-taskgraph-marketplace",
"owner": {
"name": "wu736139669",
"url": "https://github.com/wu736139669"
},
"plugins": [
{
"name": "agent-taskgraph",
"source": "./plugins/agent-taskgraph",
"description": "PMO-led native Agent Teams for Codex and Claude Code with isolated contexts and document handoffs.",
"version": "0.8.0-beta.16",
"license": "Apache-2.0"
}
]
}
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 · 17 lines scan A 27a9491e77a0
agent-taskgraph-marketplace is a plugin published in the GitHub repository wu736139669/agent-taskgraph-protocol (4 stars, last pushed 19d ago), licensed Apache-2.0. 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
pilotfish
macOS and Linux Claude Code Plugin beta with hook-based ambient policy activation and namespaced role agents.
longgraph-skill
longgraph — long-horizon agent skill (Claude Code / Codex / Cursor / Grok Build): durable loop-graph runs with verified gates.
agentos
Agent Operating System — self-evolving agents, multi-agent orchestration, 25-screen TUI, 25 LLM providers. Built on iii-engine.
open-magi
Open Magi Claude Code plugin marketplace.
open-magi
Magi proposal-first multi-agent deliberation loop for Claude Code.
claude-code-fusion
Multi-model orchestration marketplace for Claude Code.