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 Pushary/pushary-skillnpx agentmods add plugins/pushary/pushary-skill/marketplacegit clone --depth 1 https://github.com/Pushary/pushary-skillGrade A, and why
pushary 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": "pushary",
"description": "Push notifications, human-in-the-loop questions, and permission gating for AI agents.",
"owner": {
"name": "Pushary",
"email": "[email protected]",
"url": "https://pushary.com"
},
"plugins": [
{
"name": "pushary",
"source": "./",
"displayName": "Pushary",
"description": "Reach a human from a running agent. Push a question to their phone before an irreversible action, get the answer back on the lock screen, and gate risky tool calls on a real approval.",
"author": { "name": "Pushary", "email": "[email protected]" },
"homepage": "https://pushary.com",
"repository": "https://github.com/Pushary/pushary-skill",
"license": "MIT",
"category": "productivity",
"keywords": [
"notifications",
"push",
"human-in-the-loop",
"permissions",
"approvals",
"mcp"
]
}
]
}
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.
- yesterday First seen · 32 lines scan A 6d14833a7284
pushary is a plugin published in the GitHub repository Pushary/pushary-skill (0 stars, last pushed 3d 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
markifact
Run Google Ads, Meta Ads, GA4, Shopify, and 20+ more platforms from Claude. 1000+ operations with human-in-the-loop on every write.
dhm
Plugin marketplace listing 1 plugin: dear-hiring-manager.
cowork-os
An operating system for Claude Cowork: a company brain your team owns, outcome-driven workflows, Decision Radar, Knowledge Transfer, and a LinkedIn growth system. Built by Yempik; maintained by Raffaele Zarrelli and Simone Bova.
student-llm-wiki
Compile course materials into a persistent, interlinked Obsidian wiki. Karpathy LLM Wiki pattern with student features: Feynman review, exam prep, confidence decay, cross-course connections. Bilingual Chinese-English.
accountant
Draft tax return summaries, tax-planning memos, engagement letters, and IRS notice responses with current-law and practice-boundary guardrails.
ai-compliance-officer
Audit AI systems, generate compliance docs, track regulatory change, and evaluate autonomous agents.