multi-thread-deals

multi-thread-deals is a skill for Claude Code, Codex from swan-gtm/gtm-skills. It costs 35 tokens per session (1,104 once invoked), scanned A, original, MIT.

A sales-workflow helper that finds open deals relying on too few active contacts and identifies missing members of the buying group.

In plain words
What is it for?
Use it to review mid- and late-stage deals, find missing stakeholder roles, and plan introductions or direct outreach.
Why use it?
It reduces the risk of a deal depending on one contact who may not represent every decision-maker. It also shows who to involve next and suggests how to reach them.

Skill for Claude CodeCodex

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

Good fit Use it to review mid- and late-stage deals, find missing stakeholder roles, and plan introductions or direct outreach.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/swan-gtm/gtm-skills/multi-thread-deals
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 multi-thread-deals
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 multi-thread-deals

README.md
[![agentmods](https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/multi-thread-deals/github.svg)](https://agentmods.dev/skills/swan-gtm/gtm-skills/multi-thread-deals)
Your own site
<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/multi-thread-deals"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/multi-thread-deals/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 multi-thread-deals

Your own site · 80×15
<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/multi-thread-deals"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/multi-thread-deals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,104 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 $0.00035 $0.01104
Opus 5 $0.00017 $0.00552
Sonnet 5 $0.00007 $0.00221
Haiku 4.5 $0.00003 $0.00110

Measured 9d ago against content hash 9c0b93c3ed03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

multi-thread-deals 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.

skills/ido-goldberg/multi-thread-deals/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions

State check. This skill assumes funnel stages and deal data are available, and that the org has a buying-committee persona model defined. Load funnel stages and recent deals via the CRM, and check that personas exist. If funnel stages aren't defined or no CRM is connected, route the user to pipeline review setup first. If personas aren't defined, surface that — without a buying committee model this skill can't tell which roles are missing.

What this skill does

Find single-threaded (or under-threaded) open deals. Identify the missing persona(s) per deal. Find the right contact at the company for each missing persona. Recommend an introduction or direct outreach.


Step 1 — Find under-threaded deals

hubspot-search-objects (object: deals) filtered to open mid-to-late-stage, owner = user (or org-wide). Page size 20.

For each deal, pull associated contacts via hubspot-get-engagements. Count contacts with engagement in the last 30 days. Flag deals with:

  • Critically thin — 1 active contact.
  • Thin — 2 active contacts.
  • OK — 3+ active contacts.

Keep critically thin and thin deals for the analysis. Discard OK ones.


Step 2 — Identify the missing personas

Load the buying committee from swan-get-memory — economic buyer, technical evaluator, end user, champion.

For each thin deal, check which personas are already engaged (match contact titles against persona definitions). Surface the gap:

  • "Acme deal: champion engaged (Sarah, RevOps). Economic buyer NOT engaged. Technical evaluator NOT engaged."

If the org doesn't have personas defined, route to persona-builder first — this skill needs the buying committee to know what's missing.


Step 3 — Find the right contact per missing persona

For each missing persona on each deal, run swan-search-employees on the company with the persona's title filter. Free preview, no enrichment yet.

Pick the best match: usually the most senior person matching the persona who isn't already engaged. If multiple candidates, prefer:

  • Direct counterparts to already-engaged contacts (same level, complementary function).
  • Anyone who's shown intent signals (visited site, engaged with social).

Read the full file on GitHub · 110 lines

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 · 110 lines · 35 tokens per session scan A 9c0b93c3ed03

Subscribe to this mod's changes

multi-thread-deals is a skill published in the GitHub repository swan-gtm/gtm-skills (153 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 1,104 once invoked, about $0.0002 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.