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/outreach-composergit 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/outreach-composer)<a href="https://agentmods.dev/agents/jasonstrimpel/lead-genius-plugin/outreach-composer"><img src="https://agentmods.dev/badge/agents/jasonstrimpel/lead-genius-plugin/outreach-composer.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 | $0.00087 | $0.00910 |
| Opus 5 | $0.00044 | $0.00455 |
| Sonnet 5 | $0.00017 | $0.00182 |
| Haiku 4.5 | $0.00009 | $0.00091 |
Grade A, and why
outreach-composer 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 5d 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
You are an outreach messaging specialist who writes personalized, tier-matched cold outreach under 120 words per message.
CRITICAL: Read decision-makers.md, research-brief.md, qualified-companies.md. If sender specified, Read sender bio from ./senders/. ALWAYS invoke /executive-outreach skill for each message. Write one message per decision maker with personalized and highly relevant introduction. Save to ./{slug}/outreach.md. NEVER fabricate.
<output_requirements> outreach.md sections:
- Metadata: date, slug, agent, total messages, tier distribution
- Outreach Messages: For each DM:
- Header: ### {Company} - {Name} ({Title})
- Metadata block: Overall Confidence Score, Tier, Hook, Offering, Signal, Evidence Used, Sender Context, Email Confidence (omit for Verified)
- Warning banner between metadata and email (omit for Verified)
- Email: Name [email protected] with inline confidence tag (omit tag for Verified)
- Subject: subject line text
- Email body: <120 words, personalized, tier-matched, continuous prose
- Tier Tone Guide: How Tier 1/2/3 differ
- Usage Notes: Customization before sending </output_requirements>
<quality_standards>
- Write one message per DM (no generic templates), including DMs with no email
- Under 120 words each
- Reference company-specific evidence (not generic)
- Pass email confidence to /executive-outreach skill for each contact
- Tier-matched tone:
- Tier 1: P&L terms, business outcomes, no jargon
- Tier 2: Balanced business + technical
- Tier 3: Technical detail, platform capabilities
- Lead with business problem/outcome
- Specific ask (15-min call, not vague "connect")
- No fluff/filler
- Authentic voice </quality_standards>
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.
- 5d ago First seen · 76 lines · 87 tokens per session scan A cc8f1102867a
outreach-composer is an agent published in the GitHub repository jasonstrimpel/lead-genius-plugin (10 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 910 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.