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.
npx skills add swan-gtm/gtm-skills --skill track-contact-job-changesgit clone --depth 1 https://github.com/swan-gtm/gtm-skillsWrote 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.
[](https://agentmods.dev/skills/swan-gtm/gtm-skills/track-contact-job-changes)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/track-contact-job-changes"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/track-contact-job-changes/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.
<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/track-contact-job-changes"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/track-contact-job-changes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00177 | $0.01327 |
| Opus 5 | $0.00088 | $0.00664 |
| Sonnet 5 | $0.00035 | $0.00265 |
| Haiku 4.5 | $0.00018 | $0.00133 |
Grade A, and why
track-contact-job-changes 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
One line: run this when you want the CRM's contacts to reflect where those people actually work now, and to catch champions who moved to a new account. It produces a reviewed batch of CRM changes, never a silent rewrite.
Golden rule: propose, then confirm. Collect every proposed change and show it as one table before touching the CRM. And never act on the wrong person — if the enriched identity doesn't match the contact, it goes to "can't confirm", not to a write.
Setup (once)
Before the first run, capture the operator's configuration and save it — see references/setup-checklist.md. It records: the CRM and whether writes are allowed; the match keys for a person (record id, email, LinkedIn URL) and a company (domain, LinkedIn company URL, name); the four data sources the play needs (a LinkedIn-URL finder, a work-history source that returns current + past roles, an email lookup, a company-enrichment source); the tier rules that define a create-worthy account; the opt-out rules that mark a move as a dead end; and the CRM field names to write. On a later run, load the saved config; if none exists, run setup first.
The play (per contact)
- Confirm the contact is in the CRM using the person match keys, and read their current company, title, and LinkedIn URL.
- Have a LinkedIn URL? If not, look one up from name + company and validate the found profile's name against the contact before trusting it. Retry once. Still nothing → mark can't confirm and stop.
- Pull current + past roles from the work-history source. Validate the returned person's name against the contact. On a name mismatch → the stored URL is likely wrong → mark can't confirm (re-find), stop.
- Compare the current employer to the CRM company using the matching rules in
references/matching.md — domain and LinkedIn-page agreement decide it; a name
alone never does. Three outcomes:
- Still there → propose refreshing title/tenure if they changed; otherwise mark verified. Done.
- Can't confirm (weak or conflicting signals) → propose re-finding the URL or flag for review. Never guess. Done.
- Confirmed left → separate old (the CRM company) from new (the current employer), and continue.
- Is the new company already in the CRM? Match it with the same rules.
- Yes → apply the opt-out rules. If the new company is a customer, competitor, or otherwise disqualifying → flag & opt out (stop outreach, record the move). Otherwise → update the contact to the new company/title and re-associate to the existing account.
- No → enrich the company, then tier it against the rules in references/tiering.md. A fit account → propose creating the account, then update the contact onto it. A non-fit account → skip & flag (don't create it), but still update the contact's new company/title so the record is honest. Both paths end at an updated contact.
- Approve & apply. Present the batch as one table — contact, old → new company, outcome, fields to write, and the evidence/confidence behind it. Apply only what's approved. If writes are disabled, export the table instead of writing.
What ships with it
3 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.
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.
- 9d ago First seen · 75 lines · 177 tokens per session scan A 6243b0ee2069
track-contact-job-changes is a skill published in the GitHub repository swan-gtm/gtm-skills (153 stars, last pushed 2d ago), licensed MIT. It adds 177 tokens to every session and 1,327 once invoked, about $0.0009 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.