Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/thatrebeccarae/claude-marketingnpx agentmods add rules/thatrebeccarae/claude-marketing/klaviyo-developerWrote 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/rules/thatrebeccarae/claude-marketing/klaviyo-developer)<a href="https://agentmods.dev/rules/thatrebeccarae/claude-marketing/klaviyo-developer"><img src="https://agentmods.dev/badge/rules/thatrebeccarae/claude-marketing/klaviyo-developer/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/rules/thatrebeccarae/claude-marketing/klaviyo-developer"><img src="https://agentmods.dev/badge/rules/thatrebeccarae/claude-marketing/klaviyo-developer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00082 | $0.04346 |
| Opus 5 | $0.00041 | $0.02173 |
| Sonnet 5 | $0.00016 | $0.00869 |
| Haiku 4.5 | $0.00008 | $0.00435 |
Grade A, and why
klaviyo-developer 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 — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Klaviyo Developer
Expert-level guidance for building with the Klaviyo API — custom event tracking, profile management, SDK integration, webhooks, catalog sync, and data pipeline architecture.
For marketing strategy, flow auditing, segmentation, deliverability, and campaign optimization, see the klaviyo-analyst skill.
MCP vs. SDK: When to Use Which
This skill is SDK-first by design — you're building production integrations against the Klaviyo API, not running ad-hoc queries. That said, Klaviyo's official MCP server is the right tool for parts of integration work, and you should know when to reach for it.
Use the SDK (klaviyo-api) when… |
Use the MCP (https://mcp.klaviyo.com/mcp) when… |
|---|---|
| Writing production event-tracking code | Exploring an account's event schema before writing the integration |
| Building bulk import / sync pipelines | Sanity-checking that events landed with the right property shape |
| Implementing webhook handlers | Pulling a quick property inventory during integration design |
| Catalog sync jobs | Inspecting flow trigger conditions while debugging why an event isn't firing a flow |
| Anything in CI, cron, or a deployed service | Iterating on event schema design with the marketing analyst in the room |
The MCP wraps the same API this skill targets, so the schema rules, rate limits, and nesting constraints below apply equally to MCP-driven calls. The MCP is currently pinned to API revision 2026-04-15 — keep that in mind if you're versioning your own SDK code against an older revision.
For the full MCP tool inventory, OAuth setup, and read-only mode flag, see REFERENCE.md. For audit/analyst work, see the klaviyo-analyst skill — it's built around the MCP.
Core Capabilities
API Authentication & Versioning
- Private API key setup and key management best practices
- Public API key usage for client-side tracking (klaviyo.js)
- OAuth 2.0 authorization flow for third-party apps
- API revision headers and version lifecycle management
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 · 377 lines · 82 tokens per session scan A 474077e6cc4a
klaviyo-developer is a cursor rule published in the GitHub repository thatrebeccarae/claude-marketing (133 stars, last pushed 3mo ago), licensed MIT. It adds 82 tokens to every session and 4,346 once invoked, about $0.0004 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 cursor rules, from other repositories
fastapi
Apply when building FastAPI endpoints, Pydantic models, or async APIs. Covers routing, dependency injection, error handling, testing, and OpenAPI hygiene.
instructions
Definitive guidelines for building high-performance, maintainable, and secure web applications with actix-web 4, focusing on modern Rust best practices.
backend-service-authorization-permissions
Rules for writing authorization, access and permission checks in backend services. Every service method should have access checks.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.