dm-researcher

dm-researcher is an agent for Claude Code from jasonstrimpel/lead-genius-plugin. It costs 103 tokens per session (1,063 once invoked), scanned A, original, MIT.

An agent that researches reachable business buyers at companies already selected as qualified targets. It prioritizes people responsible for business results over technology-only roles.

In plain words
What is it for?
Use it to find three to five relevant contacts per target company and explain why each person was selected.
Why use it?
It collects names, roles, contact details, confidence levels, and sources in one consistent research file while documenting conflicting information.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the lead-genius plugin — 1 skill, 1 command, 12 agents shipped together

Install

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.

agentmods
npx agentmods add agents/jasonstrimpel/lead-genius-plugin/dm-researcher
Clone the repo
git clone --depth 1 https://github.com/jasonstrimpel/lead-genius-plugin

Made for: Claude Code.

Or install lead-genius, the plugin that ships this one along with the rest of its 1 skill, 1 command, 12 agents.

Wrote 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.

agentmods badge for dm-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/jasonstrimpel/lead-genius-plugin/dm-researcher.svg)](https://agentmods.dev/agents/jasonstrimpel/lead-genius-plugin/dm-researcher)
Your own site
<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>
Per session 103 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,063 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash eaf581aeb735, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

agents/dm-researcher.md · 80 lines

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>
Changes

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.

  1. 6d ago First seen · 80 lines · 103 tokens per session scan A eaf581aeb735

Subscribe to this mod's changes

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.

Related

Other agents, from other repositories