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 Misar-AI/misarmail-mcp --skill ab-test-campaigngit clone --depth 1 https://github.com/Misar-AI/misarmail-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/misar-ai/misarmail-mcp/ab-test-campaign)<a href="https://agentmods.dev/skills/misar-ai/misarmail-mcp/ab-test-campaign"><img src="https://agentmods.dev/badge/skills/misar-ai/misarmail-mcp/ab-test-campaign/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/misar-ai/misarmail-mcp/ab-test-campaign"><img src="https://agentmods.dev/badge/skills/misar-ai/misarmail-mcp/ab-test-campaign.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 | $0.00053 | $0.00426 |
| Opus 5 | $0.00026 | $0.00213 |
| Sonnet 5 | $0.00011 | $0.00085 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
ab-test-campaign 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 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.
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
A/B test a campaign
Check the audience is big enough — first
Call get_campaign (or list_campaigns) for the recipient count.
With the default 20% sample split across two variants, an audience of 10,000 gives ~1,000 per variant. Below that, normal variance swamps the effect and the "winner" is noise. Say so plainly and recommend against testing rather than running a test that produces a confident-looking but meaningless result.
Design
create_ab_test takes campaign_id, a type, and 2–5 variants:
| Type | Varies | Notes |
|---|---|---|
subject |
Subject line | Highest signal, easiest to interpret |
content |
Body HTML | Test one change, not a redesign |
from_name |
Sender name | Often larger effect than expected |
send_time |
Delivery time | Needs a longer measurement window |
For subject tests, generate_subject_lines produces candidates. Test variants
that differ in approach (question vs. statement, specific vs. curiosity), not
in wording trivia — two near-identical subjects cannot produce a real winner.
Set winner_metric to match the goal: open_rate for subject tests,
click_rate or conversion_rate for content.
Selecting the winner
select_ab_test_winner sends the winning variant to the entire remaining
audience. It is irreversible. Do not call it until results are in, and never
without explicit confirmation.
Let the sample run at least 4 hours — opens arrive over hours, and an early reading systematically favours whichever variant reached the more active segment first.
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 · 44 lines · 53 tokens per session scan A b9495c635f07
ab-test-campaign is a skill published in the GitHub repository Misar-AI/misarmail-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 426 once invoked, about $0.0003 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
email-automation-builder
Build multi-sequence email automation flows with branching logic. Triggers on: "build email automation", "create email funnel", "email automation flow", "welcome series with branches", "conditional email sequence", "set up automation", "email workflow builder", "segmented email flow", "advanced email sequence"…
email-management-expert
Expert email management assistant for Apple Mail. Use this when the user mentions inbox management, email organization, email triage, inbox zero, organizing emails, managing mail folders, email productivity, checking emails, or email workflow optimization. Provides intelligent workflows and best practices for…
ai-newsletter
Use when building and monetizing AI-powered email newsletters. Curate content, automate writing, and grow paid subscriptions. Generate $1K-20K/month.
confirmation-protocol
Foresay-derived confirmation workflow for email operations. Use this skill BEFORE executing archive-mail with vague filters, composeemail (sending mail), deleteemail/moveemail in bulk, or any operation that touches 5+ emails. Show user a structured preview of "what I understood" before taking action, achieving…
bulk-operation-preview
Show structured preview of bulk email operations (5+ emails) before execute. Group by thread, flag false-positive candidates, count side-effect scope (files written, attachments downloaded, mailboxes touched). Use after email-search-disambiguation finishes Phase 1, as Phase 2 of the confirmation protocol.
email-search-disambiguation
A clarification step for email searches when a person, time period, direction, or scope is unclear. It presents specific possible meanings so the user can choose one.