Feature Flags API — Agent Skill by PostHog

From the author

PostHog feature flags for API applications

— the description by PostHog

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides guidance and implementation patterns for integrating PostHog feature flags into API-based applications. It covers the necessary API calls to evaluate flag values, how to attribute flag information to captured events for analytics, and best practices for managing flags in a server-side environment. The skill emphasizes secure handling of project tokens via environment variables and provides examples for common request patterns.

What it does

Provides API endpoints for evaluating feature flag status for specific users.
Explains how to include feature flag data in event captures for accurate analytics.
Details the optional tracking of feature flag usage via the $feature_flag_called event.
Outlines best practices for server-side flag evaluation to prevent UI flicker.
Offers guidance on using environment variables for secure PostHog project token management.

When to use it

When you need to implement feature toggles in a backend API or server-side application.
When you want to perform multivariate testing or phased rollouts for API features.
When you need to ensure feature flag values are correctly attributed to events in PostHog insights.
When you want to manage feature flags programmatically using PostHog MCP tools.

Advantages

Enables server-side control of features, avoiding client-side UI flicker.
Provides clear patterns for integrating flag evaluation into existing API logic.
Ensures consistent analytics by linking feature flag variants to event properties.
Promotes secure development practices by prioritizing environment variables over hardcoded keys.

Usage examples

“How do I check if a feature flag is enabled for a user in my Python API?”: The agent provides a Python code snippet using the requests library to POST to the PostHog flags endpoint with the user's distinct_id and project token.
“How do I ensure my API events show which feature flag variant a user saw?”: The agent explains how to include the $feature/feature-flag-key property within the event properties when sending data to the PostHog capture endpoint.

Install

Download the skill as a ZIP:
https://mp-staging.autogineer.com/agent-skills/posthog/feature-flags-api/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip feature-flags-api.zip -d .agents/skills

Documentation by PostHog

PostHog feature flags for API

This skill helps you add PostHog feature flags to API applications.

Reference files

references/api.md - API feature flags installation - docs
references/adding-feature-flag-code.md - Adding feature flag code - docs
references/best-practices.md - Feature flag best practices - docs

Consult the documentation for API details and framework-specific patterns.

Key principles

Environment variables: Always use environment variables for PostHog keys. Never hardcode them.
Minimal changes: Add feature flag code alongside existing logic. Don't replace or restructure existing code.
Boolean flags first: Default to boolean flag checks unless the user specifically asks for multivariate flags.
Server-side when possible: Prefer server-side flag evaluation to avoid UI flicker.

PostHog MCP tools

Check if a PostHog MCP server is connected. If available, look for tools related to feature flag management (creating, listing, updating, deleting flags). Use these tools to manage flags directly in PostHog rather than requiring the user to do it manually in the dashboard.

Framework guidelines

No specific framework guidelines.

Files

ATTRIBUTION.mdAdded by AutoGineer951 B
LICENSELicence file added by AutoGineer1.0 KiB
SKILL.md1.3 KiB
references/adding-feature-flag-code.md108.7 KiB
references/api.md5.6 KiB
references/best-practices.md7.9 KiB

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs an MCP server

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Claude API
AnthropicOfficial
Comprehensive reference for integrating Anthropic's Claude API, SDKs, and Managed Agents into your applications.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskHas scriptsGitHub stars of the source repository188.6k
Transformers
K-Dense· Community
Integrate Hugging Face Transformers for model loading, inference, and fine-tuning across NLP, vision, and audio tasks.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskGitHub stars of the source repository56.4k
Open Notebook
K-Dense· Community
Integrate with the self-hosted Open Notebook platform to automate research ingestion, context-aware chat, and AI-driven analysis.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository56.4k
Vision Sft
Seth Hobson· Community
A structured workflow for supervised fine-tuning of vision-language models, focusing on adapter configuration and silent failure prevention.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k
LLM Evaluation
Seth Hobson· Community
A comprehensive framework for evaluating LLM application performance using automated metrics, human feedback, and LLM-as-a-judge techniques.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k
Lora Qlora Recipes
Seth Hobson· Community
Provides configuration recipes and best-practice hyperparameters for LoRA and QLoRA supervised fine-tuning.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k