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 crealwork/ai-marketing-kit --skill b2b-cold-emailgit clone --depth 1 https://github.com/crealwork/ai-marketing-kitWrote 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/crealwork/ai-marketing-kit/b2b-cold-email)<a href="https://agentmods.dev/skills/crealwork/ai-marketing-kit/b2b-cold-email"><img src="https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/b2b-cold-email/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/crealwork/ai-marketing-kit/b2b-cold-email"><img src="https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/b2b-cold-email.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 | $0.00066 | $0.03664 |
| Opus 5 | $0.00033 | $0.01832 |
| Sonnet 5 | $0.00013 | $0.00733 |
| Haiku 4.5 | $0.00007 | $0.00366 |
Grade A, and why
b2b-cold-email scanned grade A 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
requests.post(f"{API}/campaigns", headers=H, json=payload) How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instantly Cold Email (API v2)
Create and manage Instantly.ai cold outreach campaigns: sequences, leads, sending accounts.
Many "intuitive" details are wrong. Every gotcha in Common pitfalls is something this skill author hit on a live campaign. Read that section first when something doesn't work.
API basics
- Base URL:
https://api.instantly.ai/api/v2 - Auth:
Authorization: Bearer $INSTANTLY_API_KEY - Key location: env var
INSTANTLY_API_KEY(Instantly → Settings → Integrations → API; never hardcode) - Rate limit: 10 req/sec total. For bulk ops (>1000 leads) throttle to ~5 RPS.
- Pagination: cursor
starting_after+next_starting_afterin response.
INST_KEY=$INSTANTLY_API_KEY
Campaign creation workflow
- Confirm sending account ready (
/accounts) —daily_limit,stat_warmup_score. - Create campaign (
POST /campaigns) with sequences + schedule. - Upload leads with custom vars (
POST /leads/add). - Verify lead-campaign binding (via
/leads/listsearchfilter). - User activates (
POST /campaigns/{id}/activate) — never auto-activate.
1) Create campaign
payload = {
"name": "Cold — Offer A — 2026-05",
"email_list": ["[email protected]"],
"campaign_schedule": {
"schedules": [{
"name": "BC weekday hours",
"timing": {"from": "09:00", "to": "17:00"},
"days": {"1": True, "2": True, "3": True, "4": True, "5": True},
"timezone": "America/Dawson"
}]
},
"sequences": [{
"steps": [
{"type":"email","delay":3,"variants":[{"subject":"{{subjectLine}}","body": STEP1_HTML}]},
{"type":"email","delay":3,"variants":[{"subject":"", "body": STEP2_HTML}]},
{"type":"email","delay":0,"variants":[{"subject":"", "body": STEP3_HTML}]}
]
}]
}
requests.post(f"{API}/campaigns", headers=H, json=payload)
Key points:
campaign_scheduleis an object{schedules: [...]}, not a bare array. Inner:timing.from/to(24h "HH:MM"),daysis a{"1": true, ...}dict (Monday=1),timezone(see timezone whitelist).typeis lowercase"email"(uppercase 400s).- Subject + body live inside
variants: [{subject, body}], not flat on the step. delaysemantics — see step delay below. Set delay on the LAST step to 0; setting first step delay to 0 fires step 2 immediately = duplicate spam.- Empty
subject: ""on follow-up steps = reply thread (same subject as step 1). - Only
sequences[0]is used. Don't add more.
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.
- 10d ago First seen · 297 lines · 66 tokens per session scan A 8597b710bc1b
b2b-cold-email is a skill published in the GitHub repository crealwork/ai-marketing-kit (18 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 3,664 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…