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.
git clone --depth 1 https://github.com/wingify/wingify-fme-mcpWrote 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/wingify/wingify-fme-mcp/statsig-to-wingify-sdk-migration)<a href="https://agentmods.dev/rules/wingify/wingify-fme-mcp/statsig-to-wingify-sdk-migration"><img src="https://agentmods.dev/badge/rules/wingify/wingify-fme-mcp/statsig-to-wingify-sdk-migration/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/wingify/wingify-fme-mcp/statsig-to-wingify-sdk-migration"><img src="https://agentmods.dev/badge/rules/wingify/wingify-fme-mcp/statsig-to-wingify-sdk-migration.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 | $0.00000 | $0.02085 |
| Opus 5 | $0.00000 | $0.01043 |
| Sonnet 5 | $0.00000 | $0.00417 |
| Haiku 4.5 | $0.00000 | $0.00209 |
Grade A, and why
statsig-to-wingify-sdk-migration 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Statsig SDK → Wingify FE SDK — Application code migration
Purpose
When the user's codebase uses Statsig SDK and they want to move to Wingify Feature Experimentation (FE) SDK, refactor application code using this rule. This is not the same as console entity migration (statsig-to-wingify-migration-mcp-rules.mdc).
Non-negotiables (apply to every model, every run)
- Deterministic — Produce the same migration regardless of which model runs it. Follow the API mapping table, package names, and language guides literally. Never invent flag keys, variable names, or import styles; if a case is not covered, ask instead of guessing.
- No new rule files in the client's repo — During SDK migration, do NOT create
.cursor/rules/*.mdc,.github/instructions/*.md, or any other rule file in the user's repo, and do NOT callAddWingifyRules. Rely on this rule, the MCP tool outputs, and the repo guides instead. - Precise naming from Statsig — Flag keys, variable names, and any variation/rule names you reference must match the migrated Statsig config exactly (
name→id/baseIDfallback). Never add random strings or invented labels. Use the flag keys from the console migration output verbatim. - Wingify SDKs only (every language, no exceptions) — For all language SDKs, install the verified Wingify-branded id from
sdkNpmPackageMap(lib/utils/GetDocumentationData.ts) verbatim and always construct a Wingify-based client (e.g.wingifyClientfromWingify.init(...)/WingifyFme.initialize(...)/init(...)). Never add avwo/vwo-fme-*dependency, invent a package id, or create avwo/VWO-based client (incl. Javacom.wingify.sdk:wingify-fme-java-sdk, Androidcom.wingify.sdk:wingify-fme-android-sdk, iOS CocoaPodsWingify-FME). Supported SDK list (source of truth): https://developers.wingify.com/v3/docs/list-of-fme-sdks. The public SDK API symbols are Wingify-branded exactly as shown in each language'sfme-{sdk}-initializationdocs (e.g.from wingify import init,require 'wingify'/Wingify.init,com.wingify.Wingify,WingifyFme,WingifyProvider); take symbol names verbatim from the docs and never emitvwo/VWO-branded symbols. - The v3 docs are the single source of truth — For every install/init/usage detail, follow the SDK's own pages under https://developers.wingify.com/v3/docs (
fme-{sdk}-install,fme-{sdk}-initialization,fme-{sdk}-flags,fme-{sdk}-metrics). Ignore npm/GitHub README package names: if npm or a README says to install avwo/vwo-fme-*package, disregard it and install the Wingify-branded package the docs name. Never treat avwo-fme-*"Source Code Repository" link as canonical.
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 · 117 lines · 0 tokens per session scan A 1458f1aa32da
statsig-to-wingify-sdk-migration is a cursor rule published in the GitHub repository wingify/wingify-fme-mcp (3 stars, last pushed 19d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,085 tokens. 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 2026-08-31.
Other cursor rules, from other repositories
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.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.