Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cmj-hub/claude-cold-emailnpx agentmods add skills/cmj-hub/claude-cold-email/cold-email-list-qualityWrote 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-list-quality)<a href="https://agentmods.dev/skills/cmj-hub/claude-cold-email/cold-email-list-quality"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-email-list-quality/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-list-quality"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-email-list-quality.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 | $0.00088 | $0.01555 |
| Opus 5 | $0.00044 | $0.00777 |
| Sonnet 5 | $0.00018 | $0.00311 |
| Haiku 4.5 | $0.00009 | $0.00155 |
Grade A, and why
cold-email-list-quality 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 2d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Email List Quality — list scoring + dedup
Run before any campaign. Bad lists kill reply rates more than bad copy. This sub-skill scores the list across 6 axes, returns the rows to remove, and surfaces fix recommendations.
Activation
Loaded by:
cold-email-weekly-rhythm— Monday's list refresh- User invocation: "Score my list", "Check list quality", "Clean my prospect list"
Inputs
The skill accepts:
- CSV with at minimum:
email, optionalfirst_name,last_name,role,company,signal,signal_date,linkedin_url - JSONL with same fields
If brand-config.json is loaded, the skill cross-references
icp.segment, icp.role_targets, icp.exclusion_criteria, and
psp.signal_anchors for scoring.
Scoring (6 axes, 100 total)
| Axis | Max | What it catches |
|---|---|---|
| Dedup | 20 | Exact-match emails, near-duplicate same-company-same-person rows |
| Role-fit | 25 | Role title matches brand-config.icp.role_targets or known equivalents |
| Signal freshness | 20 | Signal age — fresh (≤14d) > recent (15-30d) > stale (>30d) |
| Email validity | 15 | Heuristic checks — RFC-shaped, no plus-extensions for B2B, no free-email domains, no role-account emails (info@, sales@) |
| Exclusion match | 10 | Row matches any brand-config.icp.exclusion_criteria → fail |
| Company-stage match | 10 | Company stage (from signal or heuristic) matches ICP segment |
Output
# List Quality Score — <file>
## Overall: <0-100>/100
| Axis | Score | Issues |
|---|---|---|
| Dedup | <0-20>/20 | <N> duplicate rows |
| Role-fit | <0-25>/25 | <N> rows outside ICP role targets |
| Signal freshness | <0-20>/20 | <N> stale signals (>30d) |
| Email validity | <0-15>/15 | <N> invalid / free-email / role-account |
| Exclusion match | <0-10>/10 | <N> rows hit exclusion criteria |
| Company-stage match | <0-10>/10 | <N> wrong-stage companies |
## Rows to remove (<N> total)
| Row | Email | Reason |
|---|---|---|
| 12 | [email protected] | Free-email domain (B2B) |
| 14 | [email protected] | Role-account email |
| 22 | [email protected] (Engineering Manager) | Role outside ICP (target: VP+) |
| 27 | [email protected] | Signal stale (45 days) |
| ... |
## Fix recommendations (in order)
1. Remove the 12 free-email + role-account rows (immediate)
2. Re-pull signals for the 8 stale rows (today)
3. Tighten role-fit list — 14 rows are "Engineering Manager" / "Director"
while ICP targets VP+. Consider adding "Director" if the ICP has
shifted, or excluding these rows.
4. Run `cold-email-deliverability` on the sending domain before this
list ships.
## Send-volume recommendation
With cleaning, the deliverable list is: <N - removed> rows.
Given warm-up state (`<warm_up_status>`), recommended weekly send
volume: <X> per day across <M> mailboxes = <X*M> per day = <X*M*5>
per week.
## Send the cleaned list
The skill writes `<file>.cleaned.csv` and `<file>.removed.csv` to the
project root. Operator can review before importing into Smartlead /
Instantly / etc.
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.
- 2d ago Changed · -1 lines c3c4c49b8eea
- 11d ago First seen · 162 lines · 88 tokens per session scan A 7f4bbe8d08e4
cold-email-list-quality is a skill published in the GitHub repository cmj-hub/claude-cold-email (2 stars, last pushed 2d ago), licensed MIT. It adds 88 tokens to every session and 1,555 once invoked, about $0.0004 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.