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 commands/jasonstrimpel/lead-genius-plugin/rungit clone --depth 1 https://github.com/jasonstrimpel/lead-genius-pluginWhat 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 | $0.00012 | $0.03223 |
| Opus 5 | $0.00006 | $0.01612 |
| Sonnet 5 | $0.00002 | $0.00645 |
| Haiku 4.5 | $0.00001 | $0.00322 |
Grade A, and why
run 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lead Genius - GTM Research & Outreach Pipeline
You are running the Lead Genius pipeline. This is a multi-phase lead generation process that interviews the user about their offering, researches qualified companies and decision makers, and generates personalized outreach emails.
CRITICAL RULES:
- Keep your own responses SHORT (2-3 sentences max between phases)
- NO greetings, NO emojis, NO chatter
- Delegate ALL research work to subagents via the Task tool
- NEVER research or write output files yourself - ALWAYS delegate to the appropriate agent
PHASE 0: SETUP
- Check if
./senders/directory exists. If it does, use Glob to find all.mdfiles in it.- If sender profiles found: List them and ask the user to pick one (or skip)
- If none found or directory doesn't exist: Note that no sender profile is available
- Check if
./collateral/directory exists. If it does, use Glob to find all.pdffiles in it.- If PDFs found: List them and confirm which ones the user wants analyzed
- If none found or directory doesn't exist: Note that no collateral is available
- Ask the user: "Describe your offering in 1-2 sentences."
- Generate a URL-safe slug from the offering description (lowercase, hyphens, 3-5 words, max 50 chars)
- Store the slug, sender name (if any), and collateral file names (if any) for use throughout
PHASE 1: COLLATERAL ANALYSIS (optional)
If PDFs were confirmed in Phase 0:
- Spawn the
collateral-analyzeragent via Task tool with:- subagent_type: "collateral-analyzer"
- prompt: "[Slug: {slug}] [Collateral: {comma-separated PDF filenames}] Analyze all PDFs in ./collateral/ and write the analysis to ./{slug}/collateral/collateral-analysis.md"
- description: "Analyzing collateral → ./{slug}/collateral/collateral-analysis.md"
- Wait for completion
- Confirm the file was written
If no PDFs: Skip to Phase 2.
PHASE 2: GTM INTERVIEW
Conduct an adaptive interview to define the offering and GTM strategy. This phase runs inline (not delegated) because it requires back-and-forth conversation with the user.
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 First seen · 269 lines · 12 tokens per session scan A d61d0926ab49
run is a command published in the GitHub repository jasonstrimpel/lead-genius-plugin (10 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 3,223 once invoked, about $0.0001 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 commands, from other repositories
feature
Post a feature to the Features Board on production and write tweets.
cluster
Build a complete topic cluster strategy with pillar page definition, 8-12 supporting articles, internal linking map, and creation sequence.
sonicjs-seo-blog
Generate a high-quality, SEO-optimized blog post for SonicJS on the topic: $ARGUMENTS.
rescue-an-account
Workflow recipe — diagnose an at-risk customer and build the full save play through to renewal by chaining 4 skills.
validate-gaql
Validates a Google Ads Query Language (GAQL) query via 4-step static analysis and live API dry-runs.
03-gap
Translate the visibility baseline + brand context into a ranked list of content actions that should move the needle. Identifies absent queries, contested queries, and competitor-displacement opportunities. Outputs contentpriorities.json validated against schema. Use after 02-audit; consumed by 04-content-brief.