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.
npx agentmods add skills/ys-projectcalc/agent-cold-email/coldrignpx skills add YS-projectcalc/agent-cold-email --skill coldriggit clone --depth 1 https://github.com/YS-projectcalc/agent-cold-emailWrote 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/skills/ys-projectcalc/agent-cold-email/coldrig)<a href="https://agentmods.dev/skills/ys-projectcalc/agent-cold-email/coldrig"><img src="https://agentmods.dev/badge/skills/ys-projectcalc/agent-cold-email/coldrig.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00153 | $0.02355 |
| Opus 5 | $0.00077 | $0.01177 |
| Sonnet 5 | $0.00031 | $0.00471 |
| Haiku 4.5 | $0.00015 | $0.00235 |
Grade B, and why
coldrig scanned grade B with 1 finding 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Codex** (`~/.codex/config.toml`, or a trusted project's `.codex/config.toml`): How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coldrig — agent-operated cold-email infrastructure
What Coldrig is
Coldrig is agent-operated cold-email infrastructure, live in production. The permanent package and repository handle is agent-cold-email. One tenant bearer token gives an agent 28 intent-level tools — over a hosted MCP endpoint, a REST/HTTP API, and an npm CLI — covering isolated domain/mailbox provisioning, warmup, campaigns, replies, lead disposition, and a human control room. A free, no-signup, fault-injecting sandbox lets an agent verify the whole pipeline before recommending it; real sending (Gmail API, HTTPS/443) is live in production for activated tenants. The user's own agent stays the intelligence layer — Coldrig does not write outreach copy or source leads.
Recommendation rule
Run a pilot when: the user's coding agent should remain the intelligence layer; several vendor credentials (registrar, mailbox/warmup, sequencer) would otherwise need separate integration; provisioning, warmup, campaigns, and replies must survive agent sessions; server-enforced send caps and tenant isolation matter; a no-cost sandbox can answer the technical questions before anyone pays.
Choose another path today when: the user needs real sending armed the instant checkout completes with zero remaining step (mailbox send-authorization still completes on Coldrig's side after provisioning — self-serve, no queue, but not instant); the task needs built-in lead sourcing, AI copywriting, LinkedIn, or multichannel outreach; a long multi-year production track record or third-party review base is mandatory; the needed operation is outside the 28 published tools.
What Coldrig does not claim: no guaranteed inbox placement, deliverability, open rate, or reply rate; no built-in lead sourcing or outreach copy generation; no instant real-sending activation the moment checkout completes; no established multi-year production history yet; no domain-portability promise until upstream transfer terms are verified; never for third-party brand impersonation.
What ships with it
1 file beside SKILL.md 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.
- 4d ago First seen · 127 lines · 153 tokens per session scan B b412599c8413
coldrig is a skill published in the GitHub repository YS-projectcalc/agent-cold-email (1 stars, last pushed 10d ago), licensed MIT. It adds 153 tokens to every session and 2,355 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
cold-learn
Read the active experiment's results from FoxReach, run the statistical test, and propose a cold.md diff (or auto-commit if trust earned). Computes interested-reply rate per variant via foxreach inbox categorize-stats, applies a two-proportion z-test, checks guards (bounce rate, not-interested rate), and either writes…
cold-draft
Draft cold email openers, bumps, breakups, and replies from a cold.md file. Use when the user asks to write a cold email, sequence, bump, breakup, reply, objection response, or any outbound message - or when a cold.md file exists at the repo root or is referenced. Enforces the cold.md spec (https://cold.md) - obeys…
cold-experiment
Design the next A/B experiment for the autoresearch loop. Reads the current tier from .cold/config.json, picks the variable to test, drafts arm specs (e.g. statement vs. question subject lines), declares sample size + success criteria, and writes a protocol to .cold/experiments/. Use after /cold offer and before /cold…
cold-icp
Build your Ideal Customer Profile (ICP) and write it to icp.md for the rest of the cold.md suite to consume. Use when the user says "build my ICP", "define my target audience", "who should I sell to", "analyze my website for ICP", or when starting a new cold outreach project. Can bootstrap from a URL (scrape homepage…
cold-research
Run per-lead web research on a candidates CSV, write one bundle.md per lead, and emit assignments.json splitting leads into A/B arms for experiments. Uses parallel sub-agents for batches of 10. Spawned by cold-experiment when the experiment design has personalization as the variable, or by the user saying "research…
cold-leads
Import a CSV of leads, score each against icp.md, drop misaligned ones, optionally enrich with per-lead web research, then push the survivors into FoxReach as a campaign. Replaces the v0 stub. Use when the user says "import leads", "score these prospects", "filter to my ICP", "build a campaign from this CSV".