warm-intro-intelligence

warm-intro-intelligence is a skill for Claude Code, Codex from swan-gtm/gtm-skills. It costs 116 tokens per session (1,938 once invoked), scanned A, original, MIT.

A relationship-mapping guide for finding people who could introduce a sales representative to someone at a target company. A warm introduction comes through an existing professional connection.

In plain words
What is it for?
Searching employee, investor, customer, partner, and other relationship records for possible introduction paths to a chosen prospect and buyer role.
Why use it?
It helps reps use trusted contacts instead of relying only on unsolicited outreach.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Searching employee, investor, customer, partner, and other relationship records for possible introduction paths to a chosen prospect and buyer role.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/swan-gtm/gtm-skills/warm-intro-intelligence
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.

Any agent
npx skills add swan-gtm/gtm-skills --skill warm-intro-intelligence
Clone the repo
git clone --depth 1 https://github.com/swan-gtm/gtm-skills

Made for: Claude Code, Codex.

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 warm-intro-intelligence

README.md
[![agentmods](https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/warm-intro-intelligence/github.svg)](https://agentmods.dev/skills/swan-gtm/gtm-skills/warm-intro-intelligence)
Your own site
<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/warm-intro-intelligence"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/warm-intro-intelligence/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for warm-intro-intelligence

Your own site · 80×15
<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/warm-intro-intelligence"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/warm-intro-intelligence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,938 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00116 $0.01938
Opus 5 $0.00058 $0.00969
Sonnet 5 $0.00023 $0.00388
Haiku 4.5 $0.00012 $0.00194

Measured 9d ago against content hash dd1329bd764a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

warm-intro-intelligence 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 9d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/din-arbel/warm-intro-intelligence/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Warm Intro Intelligence

Template placeholders

  • {{COMPANY_NAME}} — Your company's name.
  • {{COMPANY_DOMAIN}} — Your company's email/website domain (e.g. acme.com). Also used to filter your own employees out of partner data.
  • {{TEAM_ROSTER}} — A sub-page you build and maintain: every employee at your company with LinkedIn handle and full career history. Build instructions are in the Node Registry sub-page.
  • {{INVESTOR_REGISTRY}} — A sub-page you maintain: your company's investor firms plus (ideally) the named individual partners. Build instructions are in the Node Registry sub-page.
  • {{CUSTOMER_LIST}} — Your CRM's source-of-truth list of active customers (examples assume HubSpot; adapt to your CRM).
  • {{PARTNER_LIST}} — Your CRM's partner list or custom object (name/view of your partner records).
  • {{HUBSPOT_PARTNERS_OBJECT_ID}} — The objectTypeId of your partners custom object, if you store partners as a HubSpot custom object (e.g. 2-XXXXXXXXX).
  • {{PERSONA_MAP}} — Your segment → buyer-persona priority table (from your ICP qualification process): for each ICP segment, the primary personas and fallbacks.

Purpose

On-demand play that surfaces the strongest available warm intro paths from your company's relationship network to a target prospect.

Triggered by natural language such as: "Find warm intro paths for [company]", "Who do we know at [company]?", "Can anyone intro me to [role] at [company]?", "Warm intro - [company]", or similar intent.

Output is decision support only. The agent never contacts anyone, drafts outreach to connectors, or takes any action. The rep always decides.


Step 1 - Resolve Input

Determine what the rep provided:

  • Specific contact named -> target that contact only. Skip Steps 2 and 3. Go directly to Step 4.
  • Persona or role specified -> go to Step 3b to find matching contacts at the prospect.
  • Company only -> go to Step 2.

Step 2 - ICP Segment Classification (company-only input)

Read the full file on GitHub · 159 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 159 lines · 116 tokens per session scan A dd1329bd764a

Subscribe to this mod's changes

warm-intro-intelligence is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 116 tokens to every session and 1,938 once invoked, about $0.0006 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 2026-09-03.

Related

Other skills, from other repositories