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 LuuOW/meridian-mcp --skill outboundgit clone --depth 1 https://github.com/LuuOW/meridian-mcpWrote 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/luuow/meridian-mcp/outbound)<a href="https://agentmods.dev/skills/luuow/meridian-mcp/outbound"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/outbound/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/luuow/meridian-mcp/outbound"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/outbound.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 | $0.00038 | $0.02199 |
| Opus 5 | $0.00019 | $0.01099 |
| Sonnet 5 | $0.00008 | $0.00440 |
| Haiku 4.5 | $0.00004 | $0.00220 |
Grade A, and why
outbound 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.
How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
outbound
Covers the full outbound motion: ICP definition, lead sourcing, sequence design, deliverability, and CRM pipeline management. Built from lead-gen-engine patterns.
1) ICP (Ideal Customer Profile) definition
ICP = {
"firmographic": {
"company_size": "10-200 employees",
"industry": ["SaaS", "eCommerce", "Agency"],
"revenue_range": "$1M-$50M ARR",
"geography": ["US", "CA", "UK", "AU"],
"tech_stack": ["Shopify", "HubSpot", "Salesforce"], # technographic signals
},
"demographic": {
"title": ["Head of Marketing", "VP Growth", "Founder", "CMO"],
"seniority": ["Director", "VP", "C-Suite"],
"department": "Marketing or Growth",
},
"behavioural": {
"intent_signals": ["hired growth role recently", "raised funding", "launched product"],
"pain_signals": ["low organic traffic", "high CAC", "content gaps"],
},
"negative": {
"exclude": ["competitors", "agency clients", "students", "job seekers"],
},
}
2) Lead scoring model
def score_lead(lead: dict) -> float:
score = 0.0
# Firmographic fit (0-40 pts)
if lead.get("company_size") in range(10, 201): score += 15
if lead.get("industry") in ICP["firmographic"]["industry"]: score += 15
if lead.get("revenue"): score += 10
# Role fit (0-30 pts)
if any(t in lead.get("title","") for t in ICP["demographic"]["title"]): score += 20
if lead.get("seniority") in ICP["demographic"]["seniority"]: score += 10
# Intent signals (0-30 pts)
if lead.get("recent_funding"): score += 15
if lead.get("recent_hire"): score += 10
if lead.get("tech_stack_match"): score += 5
return score # > 60 = hot, 40-60 = warm, < 40 = cold
BUCKETS = {"hot": 60, "warm": 40, "cold": 0}
3) Cold email sequence structure
Sequence: 5-touch, 14-day window
Day 0 — Email 1: Hook + value prop (3 sentences max)
Day 2 — Email 2: Social proof / case study angle
Day 5 — Email 3: Pain-point reframe
Day 9 — Email 4: Objection pre-emption
Day 14 — Email 5: Breakup ("last email, no hard feelings")
Reply at any point → remove from sequence, route to human
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 · 240 lines · 38 tokens per session scan A 1f1bcac5a06b
outbound is a skill published in the GitHub repository LuuOW/meridian-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 2,199 once invoked, about $0.0002 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.
newsletter
Use when running an email newsletter as a recurring publication — subject + preview pair, issues that turn opens into clicks, the welcome sequence, cadence and engagement tiering, growth loops, and a post-Apple-MPP click scorecard. NOT one-off launch or nurture sends (that is marketing), NOT SPF/DKIM/DMARC (that is…
Lead Qualification
Score and qualify leads based on criteria and fit.
lead-scorer
Score and prioritize your leads with AI.
intent-outreach
Run a research → enrich → outreach SDR campaign from inside Claude Code, fully local with your own data-provider + model keys. This is the ORCHESTRATOR: it dispatches phase sub-agents (research, enrich, draft) in fixed order, checkpoints with you between phases, and saves a validated run. Use when the user wants to…
analytics-strategy
Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement.…