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.
git clone --depth 1 https://github.com/runwhen-contrib/runwhen-platform-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/runwhen-contrib/runwhen-platform-mcp/runwhen-platform-mcp)<a href="https://agentmods.dev/plugins/runwhen-contrib/runwhen-platform-mcp/runwhen-platform-mcp"><img src="https://agentmods.dev/badge/plugins/runwhen-contrib/runwhen-platform-mcp/runwhen-platform-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/runwhen-contrib/runwhen-platform-mcp/runwhen-platform-mcp"><img src="https://agentmods.dev/badge/plugins/runwhen-contrib/runwhen-platform-mcp/runwhen-platform-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
runwhen-platform 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 1mo 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": "runwhen-platform",
"description": "Infrastructure automation for RunWhen — monitor, troubleshoot, and automate with AI agents. Build health checks, investigate issues, and manage SRE tasks across Kubernetes and cloud environments.",
"author": {
"name": "RunWhen"
}
}
What it installs
The manifest is a name and a version. 15 skills, 3 agents, 1 MCP server travel with it, and installing the plugin installs all of them — 1,533 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill build-runwhen-task A 115 tokens
- Skill commit-to-codecollection A 130 tokens
- Skill manage-commands A 90 tokens
- Skill manage-knowledge A 94 tokens
- Skill author-generation-rules A 83 tokens
- Skill build-operational-context A 95 tokens
- Skill create-ai-assistant A 117 tokens
- Skill discover-locations A 74 tokens
- Skill discover-secrets A 82 tokens
- Skill find-and-deploy-codebundle A 95 tokens
- Skill configure-hierarchy A 91 tokens
- Skill configure-resource-path A 88 tokens
- Skill manage-rules A 84 tokens
- Skill run-existing-slx A 89 tokens
- Skill verify-mcp-setup A 101 tokens
- Agent runwhen-codecollection-author A 47 tokens
- Agent runwhen-task-builder A 30 tokens
- Agent runwhen-sre A 28 tokens
- MCP server runwhen-platform-mcp A not measured
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.
- 1mo ago First seen · 8 lines scan A 3b02f5b967cd
runwhen-platform is a plugin published in the GitHub repository runwhen-contrib/runwhen-platform-mcp (1 stars, last pushed 9d 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
unifi-network
UniFi Network MCP server — manage network devices, clients, firewall, VPN, and more.
cloud-run
MCP configuration declaring 1 server: cloud-run.
harness-mcp
AI-native interface to the Harness Platform — ask questions, diagnose failures, and manage deployments without leaving your terminal.
aws-billing
Get a non-expert from zero to a Slack-delivered, plain-English, waste-flagged AWS bill breakdown - and cache it so you don't pay per Cost Explorer call.
axcient
Every x360Recover endpoint, plus the fleet-wide backup-health answers the API alone can't give — offline, joined, and agent-ready.
cove
The first CLI and MCP server for Cove Data Protection — fleet-wide backup health, billing usage, and storage trends from a terminal, with the local history the vendor console doesn't keep.