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 YS-projectcalc/agent-cold-emailnpx agentmods add plugins/ys-projectcalc/agent-cold-email/coldriggit clone --depth 1 https://github.com/YS-projectcalc/agent-cold-emailGrade A, and why
coldrig 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
{
"name": "coldrig",
"version": "0.3.0",
"description": "Agent-native cold-email infrastructure. Bundles the hosted, 28-tool Coldrig MCP server (domains, mailboxes, campaigns, inbox, metrics, lead disposition) so your agent runs outbound email end to end with one bearer token — no dashboard required. Real sending is live in production (Gmail API, HTTPS/443), plus a free sandbox demo. Signup, billing, screening, and real mailbox provisioning are fully self-serve and automatic; mailbox send-authorization completes on our side after provisioning — you don't wait on a queue or do anything. $99/mo all-in for 5 mailboxes.",
"author": {
"name": "EpiphanyMade",
"url": "https://coldrig.dev"
},
"homepage": "https://coldrig.dev/",
"repository": "https://github.com/YS-projectcalc/agent-cold-email",
"license": "MIT",
"keywords": [
"cold-email",
"cold-outreach",
"email-infrastructure",
"mcp",
"model-context-protocol",
"ai-agent",
"coding-agent",
"sales-automation",
"outreach"
],
"userConfig": {
"token": {
"type": "string",
"title": "Coldrig bearer token",
"description": "Tenant bearer token from POST https://api.coldrig.dev/signup, or the free `npx agent-cold-email demo` sandbox.",
"sensitive": true,
"required": 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.
- yesterday First seen · 33 lines scan A 6c48e80c9a01
coldrig is a plugin published in the GitHub repository YS-projectcalc/agent-cold-email (1 stars, last pushed 7d 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
cold-md
The full cold.md suite for Claude Code. Six skills that run your cold outreach end-to-end: ICP building, lead sourcing, drafting, sending, reply triage, and reporting. Backed by the FoxReach API for sending infrastructure. Reads the open cold.md spec.
copilotkit-plugins
Plugin marketplace listing 1 plugin: copilotkit.
piyaz
Plugin marketplace listing 1 plugin: piyaz.
mantle
Build and embed Mantle applications with version-matched Core skills and deterministic examples.
fundraising-skills
Plugin marketplace listing 1 plugin: fundraising-skills.
brain-paper-to-alpha-plugin
Marketplace for the WQ BRAIN Alpha plugin.