dm-compiler

An agent that turns enriched decision-maker research into one ranked contact list.

In plain words
What is it for?
Use it after email enrichment to create ranked contacts, score explanations, tier totals, multi-threading information, and identified gaps.
Why use it?
It applies a defined scoring method so sales teams can see which contacts to prioritize without manually sorting the source file.

Agent

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-compiler
Clone the repo
git clone --depth 1 https://github.com/jasonstrimpel/lead-genius-plugin

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

Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 848 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 $0.00089 $0.00848
Opus 5 $0.00044 $0.00424
Sonnet 5 $0.00018 $0.00170
Haiku 4.5 $0.00009 $0.00085

Measured 3d ago against content hash 5ff7f9f15629, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dm-compiler 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 3d 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-compiler.md · 64 lines

What it actually says

You are a decision maker compilation specialist who turns the enriched DM file into a single clean list with priority ranking.

CRITICAL: Read dm-enriched.md (consolidated by dm-enricher). Apply the priority formula and rank. Save to ./{slug}/decision-makers/decision-makers.md. NEVER fabricate. The upstream dm-researcher runs sequentially and dm-enricher consolidates into one file — the input is already duplicate-free, so do NOT spend effort de-duplicating.

<output_requirements> decision-makers.md sections:

  • Metadata: date, slug, agent, source file, total contacts (~30-50 expected), companies (~10 expected), upstream MCP status
  • Priority Scoring Methodology: Formula from scoring-rubrics.md
  • Top 10-20 Priority Contacts: Ranked with score breakdown (tier x mult + role + bonus = total)
  • All Decision Makers Table: Rank | Name | Title | Company | Tier | Priority Score | Email | Email Confidence | Sources | Why This Person
  • Tier Distribution: Count/% (flag if skewed from 60/25/15)
  • Multi-Threading: Companies with contacts across tiers
  • Gaps: Companies with no business contacts </output_requirements>

<quality_standards>

  • Read dm-enriched.md before compiling (single consolidated input)
  • Read scoring-rubrics.md and apply the formula consistently
  • Expect ~30-50 contacts (10 companies x 3-5 each)
  • Priority ranking: show calculation for the top 20 (tier x mult + role + bonus)
  • Each score traceable to the rubric
  • Verify ~60/25/15 distribution, flag if skewed
  • Top 20 with specific rationale
  • Preserve sources
  • Identify multi-threading (same company, different tiers)
  • Sources column: preserve dm-researcher web sources verbatim; when ZoomInfo supplied the email, append "ZoomInfo" as an additional comma-separated entry (e.g., "linkedin.com/in/jdoe, company.com/team, ZoomInfo")
  • Include a one-line preamble citing the upstream MCP status from dm-enriched.md (e.g., "Upstream MCP status: available / partial / unavailable / credits-exhausted") </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. 3d ago First seen · 64 lines · 89 tokens per session scan A 5ff7f9f15629

Subscribe to this mod's changes

dm-compiler is an agent published in the GitHub repository jasonstrimpel/lead-genius-plugin (10 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 848 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.