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 zapier/gtm-cheat-codes --skill cross-crm-opportunity-syncgit clone --depth 1 https://github.com/zapier/gtm-cheat-codesWrote 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/zapier/gtm-cheat-codes/cross-crm-opportunity-sync)<a href="https://agentmods.dev/skills/zapier/gtm-cheat-codes/cross-crm-opportunity-sync"><img src="https://agentmods.dev/badge/skills/zapier/gtm-cheat-codes/cross-crm-opportunity-sync/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/zapier/gtm-cheat-codes/cross-crm-opportunity-sync"><img src="https://agentmods.dev/badge/skills/zapier/gtm-cheat-codes/cross-crm-opportunity-sync.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 | $0.00027 | $0.00570 |
| Opus 5 | $0.00014 | $0.00285 |
| Sonnet 5 | $0.00005 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
cross-crm-opportunity-sync 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 11d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-CRM Opportunity Sync
Use this skill when a company runs multiple CRMs and needs one deal, account, or customer relationship to stay understandable across systems.
Workflow
- Detect a new opportunity or approved stage-change event in a connected CRM.
- Match the account against a master customer record or matching rules.
- Determine whether the deal touches another CRM, business unit, product line, or customer relationship.
- Mirror or link the opportunity in the relevant CRM with approved fields only.
- Surface cross-CRM context to the rep through an internal note, briefing, or team notification.
- Write an audit trail for every cross-CRM write.
- Route low-confidence matches, old conflicts, and revenue-sensitive updates for human review.
Zapier MCP And SDK Role
- Use Zapier MCP to read and write approved CRM fields, call an LLM for matching and enrichment, look up a master customer record, and route rep notifications.
- Use Zapier SDK for developer-led implementations that need durable workflow execution, retries, logs, schedules, sandbox-to-production promotion, and audit trails.
- Keep production writes, fuzzy matches, revenue-touching workflows, and customer-data workflows approval-gated.
Master Customer Record Patterns
- Canonical CRM: one CRM is the source of truth and other CRMs sync from it.
- Warehouse-driven: a warehouse creates a shared customer ID that all CRMs reference.
- Match-on-the-fly: the agent uses email domain and company-name matching with confidence scoring and human review.
Known Gotchas
- Sync loops require a
synced_frommarker. - Historic duplicates require a separate one-time cleanup pass before go-live.
- Bulk migration can hit CRM rate limits.
- Field types differ across CRMs and need translation maps.
- Stage names drift across CRMs and need a canonical taxonomy.
- Currency and FX rules must be explicit before syncing pipeline or revenue values.
Guardrails
- Do not sync raw text notes between CRMs without explicit approval.
- Do not sync intermediate stage changes by default.
- Do not sync owner changes by default.
- Do not auto-promote low-confidence matches.
- Do not touch production without sandbox review and designated approval.
- Always write an audit row for cross-CRM writes.
What ships with it
5 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.
- 11d ago First seen · 53 lines · 27 tokens per session scan A ce456a56a190
cross-crm-opportunity-sync is a skill published in the GitHub repository zapier/gtm-cheat-codes (334 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 570 once invoked, about $0.0001 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.
Other skills, from other repositories
bcc-throughline
BCC global progress cockpit (plans.md/progress.md/findings.md). Slash: /bcc-throughline · chat: bcc:throughline · "where are we" · reprioritize · resume after /clear. Not for coding or full PLAN grill.
specgate-work-preparation
Use when preparing a request or existing source documents for SpecGate approval, creating quick SpecGate work, publishing an artifact version, or repairing artifact readiness before implementation.
handoff
Guides the Claude Code agent through completing a task, selecting a handoff tier, building a valid completion-card, and performing a clean task handoff.
specgate
Use when the working repository is SpecGate-governed, or when the user mentions SpecGate, the specgate CLI, or a SpecGate artifact, gate, Context Pack, work reference, or delivery state.
post-prd-expander
Expand a completed PRD into the full execution-readiness artifact package across 3 ordered layers with quality gates, post-PRD skill bootstrapping, and autopilot decision checkpoints.
vibe-handoff-to-spec
Prepare a project for structured downstream execution by packaging the trusted context, visible assumptions, and active decisions into a clean Spec-Kit handoff.