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 omarkhandji-commits/midas --skill cold-outreach-sequencegit clone --depth 1 https://github.com/omarkhandji-commits/midasWrote 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/omarkhandji-commits/midas/cold-outreach-sequence)<a href="https://agentmods.dev/skills/omarkhandji-commits/midas/cold-outreach-sequence"><img src="https://agentmods.dev/badge/skills/omarkhandji-commits/midas/cold-outreach-sequence/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/omarkhandji-commits/midas/cold-outreach-sequence"><img src="https://agentmods.dev/badge/skills/omarkhandji-commits/midas/cold-outreach-sequence.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 | $0.00000 | $0.00525 |
| Opus 5 | $0.00000 | $0.00262 |
| Sonnet 5 | $0.00000 | $0.00105 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
cold-outreach-sequence 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 9d 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
cold-outreach-sequence — 5-step B2B outreach sequence
When to use. The operator has identified an ICP (ideal customer profile) and wants a deliverability-aware sequence to test it.
Pre-flight.
- Run
email.deliverability_checkon the operator's sending domain. Score < 70 → STOP. Surface the recommendations and tell the operator to fix DNS before sending — landing in spam wastes the warm list.
Inputs.
- ICP: industry + role + company size + 1 trigger event
- Offer: 1 sentence
- Sending domain
- Up to 10 prospects (CSV of name, email, company)
What to draft.
outreach.sequence— 5 steps:- Step 1 (day 0): pattern-interrupt opener, ≤80 words, ends with a soft yes/no question (not a meeting ask).
- Step 2 (+3d): value drop — 1 specific insight the prospect's trigger event makes relevant. Cite a source.
- Step 3 (+7d): case-study-shaped — "a [similar role] at [similar company] achieved [outcome]". Don't fabricate; if no real case, drop this step.
- Step 4 (+12d): direct ask, ≤40 words, single-question close.
- Step 5 (+20d): break-up — "I'll close the loop; happy to reconnect when timing is better."
email.draftx 5 — one per step, addressed to ICP placeholder.artifact.texttodrafts/outreach/<campaign>/sending-plan.md— throttle plan: ≤20 sends/day for the first 5 business days, +20/day each subsequent week up to 200/day. This is warmup, not throttling for throttling's sake.
Honest constraints.
- NO purchased lists. Operator confirms each prospect has a legitimate reason to receive cold mail (downloaded a lead magnet, attended an event, fits a documented ICP).
- NO fake personalization ("noticed you went to X school" when scraped). If the personalization isn't specific to that prospect's actual situation, drop it.
- Unsubscribe link in EVERY step. CAN-SPAM, CASL, GDPR all require it.
- If the deliverability check returned warnings, surface them in the final email body comment so the operator sees them again.
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.
- 9d ago First seen · 45 lines · 0 tokens per session scan A 458a08e21335
cold-outreach-sequence is a skill published in the GitHub repository omarkhandji-commits/midas (1 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 525 tokens. 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
cashclaw-competitor-analyzer
Performs competitor research and generates detailed analysis reports with market positioning insights. Covers feature comparison, pricing analysis, SWOT, and strategic recommendations.
cashclaw-data-scraper
Extracts structured data from websites and APIs, delivering clean datasets in multiple formats. Handles pagination, deduplication, and data enrichment for reliable business intelligence.
cashclaw-invoicer
Handles invoice creation, payment link generation, payment status tracking, and automated reminders via Stripe API. Supports multi-currency billing and recurring payments.
cashclaw-landing-page
Creates high-converting landing page copy and responsive HTML with proven frameworks. Delivers publish-ready pages using AIDA, PAS, and other conversion-optimized copywriting structures.
cashclaw-reputation-manager
Monitors online reviews, generates professional response drafts, and creates reputation reports. Covers review aggregation, sentiment analysis, and strategic response planning across major platforms.
cashclaw-content-writer
Writes professional blog posts, social media content, and email newsletters optimized for SEO and engagement. Follows proven content frameworks to deliver publish-ready copy.