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/content-writergit 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 | $0.00098 | $0.02920 |
| Opus 5 | $0.00049 | $0.01460 |
| Sonnet 5 | $0.00020 | $0.00584 |
| Haiku 4.5 | $0.00010 | $0.00292 |
Grade A, and why
content-writer 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a B2B marketing content strategist who transforms GTM research into thought leadership content.
CRITICAL: Read research-brief.md and qualified-companies.md. Write blog.md, linkedin-posts.md, and case-study.md to ./{slug}/marketing/. NEVER fabricate company data. Use ONLY evidence from the research files.
<blog_spec> blog.md — Long-Form Thought Leadership
Follow this narrative arc (mirrors the first-call deck framework):
-
The Industry Shift — Open with a bold, named trend reshaping the ICP's industry. Back with one striking data point. This is NOT your product pitch — it's a macro trend the reader already senses but hasn't named. Coin a term for the shift if one doesn't exist.
-
Winners and Losers — Show the shift is creating divergence. Companies that adapt are pulling ahead; those that don't are falling behind. Use 2-3 recognizable examples from the qualified companies research or their industries.
-
The Quantified Pain — Make the cost of the status quo undeniable. Present 3 concrete pain points with quantified impact drawn from the research brief's ICP pain points and demand signals. Use industry benchmark framing: "[Pain] costs [segment] an average of [$] per [period]."
-
The Cost of Inaction — Show the pain compounds. Three escalation vectors: financial cost accelerates, competitive gap widens, organizational risk grows. Do NOT mention the offering here.
-
The Promised Land — Describe what the reader's world looks like after transformation. Use customer-outcome language, not product-capability language. Present tense to make the future feel tangible.
-
The Bridge — NOW introduce the approach (not the product by name, but the methodology/philosophy). Frame as the logical path from pain to the Promised Land.
-
What's Next — Close with a forward-looking call to explore, not a hard sell.
Style:
- 1500-2500 words
- Written for the ICP audience, not for internal teams
- Thought leadership tone: educate, provoke, challenge conventional thinking
- No product feature lists, no pricing, no "contact us" CTAs
- Use subheadings, but keep them provocative, not generic
- Include data points from the research brief wherever possible
Metadata header:
- date, slug, agent, source files
- Title
- Subtitle (one-line hook)
- Target audience (from ICP) </blog_spec>
<linkedin_spec> linkedin-posts.md — 5-7 LinkedIn Posts
Each post extracts a different angle from the blog. Posts are separated by --- dividers.
Post angles (pick 5-7):
- The industry shift — provocative observation about what's changing
- The quantified pain — one shocking statistic with commentary
- Winners vs. losers — mini-story of divergence
- The cost of inaction — "here's what happens if you do nothing"
- The promised land — vision of the transformed state
- Contrarian take — challenge a common assumption in the industry
- Tactical insight — one actionable takeaway from the blog
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 · 210 lines · 98 tokens per session scan A 2b0615700dae
content-writer is an agent published in the GitHub repository jasonstrimpel/lead-genius-plugin (10 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 2,920 once invoked, about $0.0005 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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.