loom-feature-flags
Installation
SKILL.md
Feature Flags
Overview
Runtime control over feature availability without redeploying. The hard parts are not the if check — they are: bucketing correctness (stickiness, monotonicity, cross-service consistency), fail-safe evaluation (an outage of the flag service must not take down the app), experiment validity (exposure logging), and lifecycle/technical-debt (stale flags are the #1 real-world feature-flag problem). Optimize for those.
Flag Taxonomy — Type Drives Lifetime and Ownership
The single most useful classification (from Pete Hodgson / Martin Fowler). Type determines expected lifetime, who owns it, and dynamism. Mixing types under one abstraction is a common mistake.
| Type | Purpose | Lifetime | Changes at runtime? | Owner |
|---|---|---|---|---|
| Release toggle | Ship incomplete/unproven code dark, ramp | Days–weeks (SHORT) | Per deploy/ramp | Dev team |
| Experiment | A/B/multivariate measurement | Length of test | Sticky per user | PM / data science |
| Ops / kill-switch | Disable a subsystem under load/incident | Long-lived | On demand (fast) | Ops / SRE |
| Permission | Entitlements: plan tier, beta cohort | Very long / permanent | Per user/segment | Product / billing |
Consequences: