What is feature-flag-system?

A guide to feature flags, which let software turn features on or off through configuration instead of code deployment. It covers gradual rollouts, A/B tests, canary releases, user-specific variants, and emergency kill switches.

Use it to roll out features gradually, run production experiments, offer beta features to selected users, manage maintenance mode, and stop faulty behavior.

It separates putting code into a release from making that code visible to users. This lets teams limit exposure, compare alternatives, or disable a problematic feature quickly.

feature-flag-system — Skill for Claude Code and Codex by aj-geddes

Install

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.

Any agent

npx skills add aj-geddes/useful-ai-prompts --skill feature-flag-system

Clone the repo

git clone --depth 1 https://github.com/aj-geddes/useful-ai-prompts

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aj-geddes/useful-ai-prompts/feature-flag-system/github.svg)](https://agentmods.dev/skills/aj-geddes/useful-ai-prompts/feature-flag-system)

Your own site

<a href="https://agentmods.dev/skills/aj-geddes/useful-ai-prompts/feature-flag-system"><img src="https://agentmods.dev/badge/skills/aj-geddes/useful-ai-prompts/feature-flag-system/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aj-geddes/useful-ai-prompts/feature-flag-system"><img src="https://agentmods.dev/badge/skills/aj-geddes/useful-ai-prompts/feature-flag-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 634 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

Socket pass 16 Sept 2026
Snyk pass 16 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00048	$0.00634
Opus 5.5	$0.00019	$0.00254
Sonnet 5.5	$0.00010	$0.00127
Haiku 4.5	$0.00005	$0.00063

Measured 2mo ago against content hash bf56a8631fd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

feature-flag-system 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 2mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/scaffold-tests.sh, templates/test-template.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/feature-flag-system/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Implement feature flags to decouple deployment from release, enable gradual rollouts, A/B testing, and provide emergency kill switches.

When to Use

Gradual feature rollouts
A/B testing and experiments
Canary deployments
Beta features for specific users
Emergency kill switches
Trunk-based development
Dark launching
Operational flags (maintenance mode)
User-specific features

Quick Start

Minimal working example:

interface FlagConfig {
  key: string;
  enabled: boolean;
  description: string;
  rules?: FlagRule[];
  variants?: FlagVariant[];
  createdAt: Date;
  updatedAt: Date;
}

interface FlagRule {
  type: "user" | "percentage" | "attribute" | "datetime";
  operator: "in" | "equals" | "contains" | "gt" | "lt" | "between";
  attribute?: string;
  values: any[];
}

interface FlagVariant {
  key: string;
  weight: number;
  value: any;
}

interface EvaluationContext {
  userId?: string;
// ... (see reference guides for full implementation)

Reference Guides

Detailed implementations in the references/ directory:

Guide	Contents
Feature Flag Service (TypeScript)	Feature Flag Service (TypeScript)
React Hook for Feature Flags	React Hook for Feature Flags
Feature Flag with Analytics	Feature Flag with Analytics
LaunchDarkly-Style SDK	LaunchDarkly-Style SDK
Admin UI for Feature Flags	Admin UI for Feature Flags

Best Practices

✅ DO

Use descriptive flag names
Document flag purpose and lifecycle
Implement gradual rollouts
Track flag evaluations
Clean up old flags regularly
Use feature flags for experiments
Implement kill switches for critical features
Test both enabled and disabled states
Use consistent hashing for stable rollouts
Provide admin UI for non-technical users

Read the full file on GitHub · 103 lines

Files

What ships with it

7 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.

Changes

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.

2mo ago First seen · 103 lines · 48 tokens per session scan A bf56a8631fd4

Subscribe to this mod's changes

feature-flag-system is a skill published in the GitHub repository aj-geddes/useful-ai-prompts (376 stars, last pushed 8mo ago), licensed MIT. It adds 48 tokens to every session and 634 once invoked, about $0.0002 per session on Opus 5.5. 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.

DevOps and cloud

feature-flag-system next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
feature-flag-systemaj-geddes/useful-ai-prompts	Skill	376	8mo ago	MIT	A	48	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

feature-flag-system