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.
npx skills add khalilbenaz/claude-skills-collection --skill feature-flag-systemgit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/skills/khalilbenaz/claude-skills-collection/feature-flag-system)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/feature-flag-system"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/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.
<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/feature-flag-system"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/feature-flag-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00166 | $0.03009 |
| Opus 5 | $0.00083 | $0.01504 |
| Sonnet 5 | $0.00033 | $0.00602 |
| Haiku 4.5 | $0.00017 | $0.00301 |
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 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 — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Système de Feature Flags
Workflow en 6 étapes
1. Qualifier le besoin
Poser les 3 questions avant d'écrire une ligne de code :
| Question | Réponse attendue |
|---|---|
| Pourquoi ce flag ? | Risque déploiement / expérimentation / accès conditionnel |
| Durée de vie prévue ? | < 2 semaines (release), 1-3 mois (expériment), permanent (ops/permission) |
| Qui décide du kill switch ? | Ops, PM, automatique sur metric |
2. Choisir le type
| Type | Exemple concret | Durée de vie |
|---|---|---|
| Release flag | Nouvelle page checkout | < 2 semaines |
| Experiment flag | CTA rouge vs bleu | 1-3 mois |
| Ops flag | Mode maintenance, circuit breaker | Permanent |
| Permission flag | Feature plan Pro uniquement | Permanent |
3. Concevoir le flag (YAML de référence)
# flags/checkout-v2.yaml
key: checkout_v2
description: "Nouvelle page checkout avec paiement 1-clic"
owner: team-payments
expires: 2026-08-01 # obligatoire sauf ops/permission
default: false
rules:
- type: user_ids # whitelist interne d'abord
values: [user_123, user_456]
- type: percentage
value: 10 # 10 % des utilisateurs
sticky: true # hash stable userId+flagKey
variants: # optionnel, A/B uniquement
- key: control
weight: 50
- key: treatment
weight: 50
4. Implémenter l'évaluation
TypeScript (SDK maison ou OpenFeature)
import { OpenFeature } from "@openfeature/server-sdk";
const client = OpenFeature.getClient();
// Évaluation simple (release flag)
const isEnabled = await client.getBooleanValue(
"checkout_v2",
false, // valeur par défaut si flag absent
{ targetingKey: user.id, plan: user.plan }
);
if (isEnabled) {
return newCheckout(cart);
} else {
return legacyCheckout(cart);
}
// Évaluation avec variante (A/B)
const variant = await client.getStringValue(
"checkout_v2_variant",
"control",
{ targetingKey: user.id }
);
trackExposure("checkout_v2", variant, user.id);
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 · 352 lines · 166 tokens per session scan A 9324cbc8ce2f
feature-flag-system is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 19d ago), licensed MIT. It adds 166 tokens to every session and 3,009 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
csharp-patterns
C#/.NET: LINQ, async/await, DI, records, nullable refs, ASP.NET Core, EF Core, MediatR. Triggers: C#, .NET, dotnet, ASP.NET, EF Core, LINQ, record type, IServiceCollection.
seo-validate
SEO validator: meta/OG, Schema.org, hreflang, Core Web Vitals, crawlability. Triggers: SEO, meta tags, Schema.org, hreflang, LCP, INP, CLS, Core Web Vitals, sitemap, crawlability.
swift-patterns
Swift/iOS: SwiftUI, Combine, async/await, actors, SPM, Core Data, UIKit interop. Triggers: Swift, SwiftUI, Combine, iOS, Xcode, actor, Core Data, @MainActor, @State.
ruby-patterns
Ruby/Rails: blocks, metaprogramming, ActiveRecord, Sidekiq, RSpec, Sorbet, Hanami. Triggers: Ruby, Rails, ActiveRecord, Sidekiq, RSpec, Gemfile, bundler, Hanami, Sorbet.
pr
Creates GitHub PR after pre-flight checks (lint/typecheck/tests), structured summary from commits. Triggers: pr, pull request, create PR, ready to merge.
research-mastery
Hierarchical retrieval: KB → MCP/Context7 → web. Triggers: research, fact-check, verify, synthesize, cross-reference, multi-source, cite sources.