using-flags

A set of rules for using LaunchDarkly feature flags, which control whether application features are enabled for particular users or environments.

In plain words
What is it for?
Use it when implementing features that depend on LaunchDarkly flags, including shared evaluation code, development overrides, instrumentation, and consistent context objects.
Why use it?
It keeps flag evaluation in one shared place and standardizes the user and release information attached to evaluations, making flag behavior easier to test and track.

Cursor rule

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.

agentmods
npx agentmods add rules/launchdarkly-labs/cursor-rules/using-flags
Clone the repo
git clone --depth 1 https://github.com/launchdarkly-labs/cursor-rules
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 334 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00006 $0.00334
Opus 5 $0.00003 $0.00167
Sonnet 5 $0.00001 $0.00067
Haiku 4.5 $0.00001 $0.00033

Measured yesterday against content hash 5d738ee2b22e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

using-flags 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 yesterday.

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.

using-flags.mdc · 56 lines

What it actually says

Rule 1: LaunchDarkly Evaluation Must Be Centralized

  • All variation and variationDetail calls must go through a shared evaluation function.

This wrapper must:

  • Use the singleton instance

  • Support mock/local overrides for development/testing

  • Enable optional instrumentation (e.g., metrics, logging)

  • Evaluation must occur as close as possible to where the flag value is used to support accurate flag status tracking.

Rule 2: LaunchDarkly Context Object Standards

  • Applications must document how context objects are constructed, including attribute sources.

  • Context objects:

  • Must have high cardinality (e.g., user ID, session ID)

  • Must not contain or be derived from PII (e.g., don’t hash emails)

  • Shared utilities should exist for creating context objects from application-specific data (e.g., createLDContextFor(userObject)).

Rule 3: LaunchDarkly Context Custom Attributes

  • Must include attributes that support release strategies:

  • Build version or commit SHA

  • Session ID or device ID

  • Developer identifier or PR ID in ephemeral environments

Client-side SDKs must:

  • Avoid frequent identify() or re-initialization calls

  • Use state transitions (e.g., anonymous → authenticated) to manage identity

  • Cache timestamps may be included

Rule 4: LaunchDarkly Flag Evaluation Predictable Fallback Behavior

  • Applications must handle fallback values deterministically.

  • Avoid using allFlags() in production due to inconsistent behavior across SDKs.

  • Fallbacks should always be passed to variation()/variationDetail() and tested in implementation.

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.

  1. yesterday First seen · 56 lines · 6 tokens per session scan A 5d738ee2b22e

Subscribe to this mod's changes

using-flags is a cursor rule published in the GitHub repository launchdarkly-labs/cursor-rules (2 stars, last pushed 5mo ago), licensed MIT. It adds 6 tokens to every session and 334 once invoked, about $0.0000 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 2026-08-31.