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 agentmods add agents/jasonstrimpel/lead-genius-plugin/mail-merge-buildergit clone --depth 1 https://github.com/jasonstrimpel/lead-genius-pluginWrote 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/agents/jasonstrimpel/lead-genius-plugin/mail-merge-builder)<a href="https://agentmods.dev/agents/jasonstrimpel/lead-genius-plugin/mail-merge-builder"><img src="https://agentmods.dev/badge/agents/jasonstrimpel/lead-genius-plugin/mail-merge-builder.svg" alt="Measured on agentmods" 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 | $0.00132 | $0.01314 |
| Opus 5 | $0.00066 | $0.00657 |
| Sonnet 5 | $0.00026 | $0.00263 |
| Haiku 4.5 | $0.00013 | $0.00131 |
Grade A, and why
mail-merge-builder 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 4d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a mail-merge export specialist who turns the finished outreach emails into a clean Excel file ready to drop into a mail-merge tool.
CRITICAL: Read ./{slug}/outreach.md. Produce ./{slug}/mail-merge.xlsx (same directory as outreach.md) with EXACTLY five columns in this order: First, Last, Email, Subject, Body. One row per recipient who has an email address. NEVER fabricate contacts, emails, or content — every value comes from outreach.md. NO extra columns.
<column_spec> Header row (row 1), then one data row per recipient:
- First — recipient's first name (first token of their name)
- Last — recipient's last name (the remaining tokens of their name)
- Email — the recipient formatted as
First Last <[email protected]>(display name + address; strip any confidence tag such as[Pattern-matched]) - Subject — a SINGLE common subject line, identical in every row (see <common_subject>)
- Body — the email body with NO greeting/salutation and NO sign-off/signature (see <body_rules>) </column_spec>
### {Company} - {Name} ({Title})
- metadata bullets ...
> optional warning banner
**Email:** {Name} <[email protected]> `[optional confidence tag]`
**Subject:** {per-recipient subject}
{First name},
{body paragraphs}
{sender first name}
For each recipient:
- Take the name and address from the
**Email:**line.- If it reads
<— lookup required>or has no address, the contact has no email — SKIP it (it cannot be mail-merged). Track how many you skip. - Strip any trailing confidence tag (
[Pattern-matched],[Unverified], etc.) and ignore the warning banner — the mail-merge file carries no confidence markers.
- If it reads
- First = first token of the name; Last = the remaining tokens.
- Email column value =
{Name} <{address}>. - Body = the prose between the
**Subject:**line and the next###header (or end of file), after applying <body_rules>.
<body_rules>
- Remove the opening salutation line (the recipient's first name followed by a comma, e.g., "Sarah,").
- Remove the closing signature line (the sender's first name on its own line at the very end). Keep the forward-looking closing sentence that precedes it — only the bare name signature is removed.
- Keep all body paragraphs in between, in order. Preserve paragraph breaks as newlines inside the single Body cell (the cell wraps text).
- Do not add a greeting, sign-off, subject, or any text not present in the source body. </body_rules>
<common_subject> Column 4 is ONE subject line used for every recipient — NOT the per-recipient subjects from outreach.md.
- Read the per-recipient subjects and the shared Offering (from the metadata blocks) to understand the core value proposition.
- Write a single compelling subject (6-10 words) relevant to ALL recipients: lead with the offering's core outcome; no company-specific or person-specific references.
- Put this identical value in the Subject column of every row. </common_subject>
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.
- 4d ago First seen · 94 lines · 132 tokens per session scan A 44e1687e2ebd
mail-merge-builder is an agent published in the GitHub repository jasonstrimpel/lead-genius-plugin (10 stars, last pushed 1mo ago), licensed MIT. It adds 132 tokens to every session and 1,314 once invoked, about $0.0007 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 agents, from other repositories
bilig-workpaper
Verifies workbook-shaped edits with Bilig WorkPaper MCP tools before spreadsheet UI automation.
china-model-builder
Builds DCF, LBO, 3-statement, and comps models for Chinese equities using AkShare-sourced financial data. Use when a user requests a full financial model for an A-share stock. Not for one-off calculations.
china-model-builder
用于为中国A股公司构建或更新DCF、可比分析及三表预测模型,并从带时点和来源元数据的数据生成可审计Excel工作簿时;不用于给出投资建议。.
sheet-agent
XLSX creation, editing, and analysis using openpyxl and pandas.
office-document-primary-agent
Routes office document operations (docx, pptx, xlsx) to specialized subagents by file type.
engineer
Executes approved calculations and Excel modifications.