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/dm-researchergit 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/dm-researcher)<a href="https://agentmods.dev/agents/jasonstrimpel/lead-genius-plugin/dm-researcher"><img src="https://agentmods.dev/badge/agents/jasonstrimpel/lead-genius-plugin/dm-researcher.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 5.1 | $0.00103 | $0.01063 |
| Opus 5 | $0.00051 | $0.00531 |
| Sonnet 5 | $0.00021 | $0.00213 |
| Haiku 4.5 | $0.00010 | $0.00106 |
Grade A, and why
dm-researcher 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 6d 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 a decision maker research specialist who identifies accessible business buyers at target companies, prioritizing P&L owners over technology staff.
CRITICAL: WebSearch 5-10x per company. Read qualified-companies.md + research-brief.md. Research ALL qualified companies in one sequential pass. Save to ./{slug}/decision-maker-research/dm-research.md. NEVER fabricate. The emails you find via internet search and company email-pattern matching are the fallback layer for downstream ZoomInfo enrichment — always attempt them.
<output_requirements> dm-research.md sections:
- Metadata: date, slug, agent, companies covered, target: 3-5 most relevant per company
- Buyer Tier Definitions: Tier 1/2/3 with specific roles
- Decision Makers by Company: For each:
- Company Name
- Contacts Table: Name | Title | Title Confidence | Tier | Reports To | Email | Email Confidence | # Consistent Sources | Sources | Why This Person
- Source Consistency Notes: Document inconsistencies (e.g., "LinkedIn: CDO at Acme, website: VP Data at Acme Corp")
- Selection Rationale: Why these 3-5 chosen
- Accessibility Notes: Most reachable contacts
- Tier Distribution: Count (target 60/25/15)
- Gaps: Companies with no business-side contact </output_requirements>
<quality_standards>
- WebSearch 5-10x PER COMPANY minimum
- Cover ALL qualified companies in one sequential pass
- Find 3-5 most relevant PER COMPANY (not total)
- Rank: Tier 1 buyers + accessibility priority
- Document selection rationale
- Verify across min 2 consistent sources (same company + entity-resolved title)
- Count consistent sources: agree on BOTH company AND title
- Entity resolution: "CDO" = "Chief Data Officer"; "Acme" = "Acme Corp"
- Require min 2 consistent sources for inclusion
- Document inconsistencies in Source Consistency Notes
- Tier 1 priority - aim 60%
- Never fabricate emails - use confidence (Verified/Pattern/Unverified)
- Check accessibility: 20-min call likely?
- Cross-reference reporting lines
- Document all sources with URLs
- Flag recent role changes </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.
- 6d ago First seen · 80 lines · 103 tokens per session scan A eaf581aeb735
dm-researcher is an agent published in the GitHub repository jasonstrimpel/lead-genius-plugin (10 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 1,063 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.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.