champion-move-detection

champion-move-detection is a skill for Claude Code, Codex from swan-gtm/gtm-skills. It costs 121 tokens per session (4,544 once invoked), scanned A, original, MIT.

A monthly process for finding important users of paying customers who changed jobs, checking their new roles against live LinkedIn data, and identifying possible sales leads.

In plain words
What is it for?
It helps maintain account watchlists, verify job moves, score new companies, create marketing-qualified leads, exclude competitor moves, and send a monthly digest.
Why use it?
It reveals when a known buyer may bring the product to a new company while also highlighting possible churn risk at the company they left.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit It helps maintain account watchlists, verify job moves, score new companies, create marketing-qualified leads, exclude competitor moves, and send a monthly digest.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/swan-gtm/gtm-skills/champion-move-detection
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 champion-move-detection
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 champion-move-detection

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/champion-move-detection"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/champion-move-detection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,544 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 $0.00121 $0.04544
Opus 5 $0.00060 $0.02272
Sonnet 5 $0.00024 $0.00909
Haiku 4.5 $0.00012 $0.00454

Measured 13d ago against content hash ffaf555e1277, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

champion-move-detection 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 13d 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/ariel-cohen/champion-move-detection/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Champion move detection

Once a month, detect champions and heavy users of your paying customers who changed jobs and moved to a new company. A known buyer bringing {{PRODUCT}} to their next company is one of your highest-conversion signals — score the new company and surface it as an MQL when it qualifies. Secondary purpose: catch churn risk on the account they left.

Template placeholders

Replace every {{...}} before enabling. See the setup checklist for the full list.

  • {{PRODUCT}} — Your product's name
  • {{CRM}} — Your CRM (e.g. HubSpot, Salesforce, Attio)
  • {{SCORING_SKILL}} — Your account-scoring skill/process; this skill feeds moves into it as a high-intent signal
  • {{LINKEDIN_LOOKUP}} — Live LinkedIn profile lookup tool (e.g. an Apify profile-search actor). Must return the profile's full experience section
  • {{MQL_OWNER}} — Who owns champion-move MQL tasks and alerts
  • {{DIGEST_CHANNEL}} — Where the monthly digest posts
  • {{COMPETITORS}} — Your direct competitors (moves into these are logged, never scored)
  • {{WATCHLIST_MAX}} — Max watched people per account (default: 5)
  • {{REFRESH_WINDOW}} — Days before an account's watchlist is rebuilt (default: 90)
  • {{USAGE_WINDOW}} — Lookback for "materially active" usage (default: 90 days)
  • {{SELF_SERVE_THRESHOLD}} — Company size/funding below which a move is future pipeline, not an MQL (default: <50 employees AND ≤$10M raised)
  • {{TIER_FLOOR}} — Minimum tier a confirmed champion move scores (default: one tier above your standard mid-tier — mirror of a closed-lost floor if you run one)

Scan set (which accounts run each month)

Run across BOTH:

  1. All accounts in your Closed Won stage — the customer base.
  2. Any company carrying an active carried-forward champion — tagged champion-move AND holding an active [CHAMPION WATCHLIST] entry marked carried-forward (see Phase 3.C). These are NOT customers; they are companies a proven serial champion moved into, tracked so you catch the person's NEXT move. A serial champion is your highest-value signal — never drop them because their current employer isn't a customer.

Read the full file on GitHub · 165 lines

Files

What ships with it

1 file 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. 13d ago First seen · 165 lines · 121 tokens per session scan A ffaf555e1277

Subscribe to this mod's changes

champion-move-detection is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 121 tokens to every session and 4,544 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 2026-08-30.