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 skills add cmj-hub/claude-cold-email --skill cold-email-kickoffgit clone --depth 1 https://github.com/cmj-hub/claude-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/cmj-hub/claude-cold-email/cold-email-kickoff)<a href="https://agentmods.dev/skills/cmj-hub/claude-cold-email/cold-email-kickoff"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-email-kickoff/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/skills/cmj-hub/claude-cold-email/cold-email-kickoff"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-email-kickoff.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00099 | $0.01414 |
| Opus 5 | $0.00049 | $0.00707 |
| Sonnet 5 | $0.00020 | $0.00283 |
| Haiku 4.5 | $0.00010 | $0.00141 |
Grade A, and why
cold-email-kickoff 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Email Kickoff — adaptive router
State-aware router. Operators don't ship cold email on day 1 — they go through a sequence: ICP → PSP → EVP → infrastructure → first send → reply triage → iterate. Kickoff detects where the operator is in that sequence and picks the right next step.
Activation
Loaded by cold-email on:
- Bare
/cold-emailinvocation (no other intent) - "Where do I start"
- "What should I do next"
- "I'm new — what's the path"
- "Onboard me"
State detection
Before recommending, kickoff checks the project state:
# Pseudo-code
state = {
"has_brand_config": file_exists("brand-config.json"),
"has_soul": file_exists("SOUL.md"),
"has_psp": "psp" in brand_config and brand_config.psp.primary_pain != "",
"has_evp": "evp" in brand_config and brand_config.evp.primary != "",
"has_infrastructure": "infrastructure" in brand_config and brand_config.infrastructure.sending_domain != "",
"deliverability_audited_recently": days_since(brand_config.infrastructure.deliverability_last_audited) < 30,
"first_send_logged": has_entries(brand_config.operations.experiment_log_path),
"reply_data_available": has_logged_replies(brand_config.operations.experiment_log_path)
}
Map state to the next-best step:
| State condition | Route to |
|---|---|
!has_brand_config OR !has_soul |
cold-email-onboarding |
has_brand_config AND !has_psp |
"Install cmj-hub/claude-psp first; let me know when PSP is done" |
has_psp AND !has_evp |
"Install cmj-hub/claude-evp first; let me know when EVP is done" |
has_evp AND !has_infrastructure |
"Let's set up infrastructure. Run cold-email-deliverability for a baseline audit." |
has_infrastructure AND !deliverability_audited_recently |
"Deliverability hasn't been re-audited in 30+ days. Run cold-email-deliverability first." |
deliverability_audited_recently AND !first_send_logged |
"Ready to ship. Want to draft your first sequence via cold-email-craft?" |
first_send_logged AND !reply_data_available |
"First sequence shipped. Set up reply routing — see cold-email-reply-scoring." |
reply_data_available |
"You've got data. Run cold-email-audit to score the program + cold-email-weekly-rhythm for the cadence going forward." |
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.
- 3d ago Changed · -1 lines 41b24cd320c8
- 12d ago First seen · 133 lines · 99 tokens per session scan A 335171708240
cold-email-kickoff is a skill published in the GitHub repository cmj-hub/claude-cold-email (2 stars, last pushed 3d ago), licensed MIT. It adds 99 tokens to every session and 1,414 once invoked, about $0.0005 per session on Opus 5. 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 skills, from other repositories
afrexai-lead-hunter
Enterprise-grade B2B lead generation, enrichment, scoring, and outreach sequencing for AI agents. Find ideal prospects, enrich with verified data, score against your ICP, and generate personalized outreach — all autonomously.
graphify
Knowledge graph engine for B2B sales intelligence. Builds queryable graphs from product catalogs, customer conversations, and market research. Powered by graphify.
telegram-toolkit
Register these commands with @BotFather using /setcommands.
lead-discovery
AI-driven lead discovery for B2B export. Searches web for potential buyers matching ICP, evaluates fit, and creates CRM records for follow-up.
b2b-sdr-agent
Open-source B2B AI SDR template. 7-layer context system with 10-stage sales pipeline, 4-layer anti-amnesia memory, 14 automated pipeline checks, WhatsApp IP isolation, multi-channel (WhatsApp+Telegram+Email). Built on OpenClaw.
sdr-humanizer
Transform AI-generated sales messages into natural, human-like conversations that build trust and rapport.