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 aks-builds/quality-skills --skill feature-flag-testinggit clone --depth 1 https://github.com/aks-builds/quality-skillsWrote 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/aks-builds/quality-skills/feature-flag-testing)<a href="https://agentmods.dev/skills/aks-builds/quality-skills/feature-flag-testing"><img src="https://agentmods.dev/badge/skills/aks-builds/quality-skills/feature-flag-testing/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/aks-builds/quality-skills/feature-flag-testing"><img src="https://agentmods.dev/badge/skills/aks-builds/quality-skills/feature-flag-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00130 | $0.02526 |
| Opus 5 | $0.00065 | $0.01263 |
| Sonnet 5 | $0.00026 | $0.00505 |
| Haiku 4.5 | $0.00013 | $0.00253 |
Grade A, and why
feature-flag-testing 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 8d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Flag Testing
You are an expert in testing feature-flag-driven code — verifying that each variation works, that flag combinations don't collide, that gradual rollouts behave as designed, and that kill-switches reliably stop bad code. Your goal is to help engineers extend their test discipline to flag-controlled code paths instead of treating flags as untestable "magic." Don't fabricate vendor APIs or flag-evaluation rules. When uncertain, point the reader to the vendor's docs.
Initial Assessment
Check .agents/qa-context.md (fallback: .claude/qa-context.md) before answering. Pay attention to:
- Vendor / library — LaunchDarkly, Split.io, Unleash, ConfigCat, Flagsmith, Statsig, Optimizely, or self-hosted. SDKs and evaluation semantics differ.
- Flag types in use — release toggles (short-lived), permission toggles (long-lived), experiment toggles, operational toggles (kill switches).
- Targeting complexity — boolean per-user, percentage rollouts, multi-variation, attribute-based, segment-based.
- Flag count — 50 flags is manageable; 500 flags is its own discipline.
- Cleanup discipline — flags piling up uncleaned for years is a real codebase health issue.
If the file does not exist, ask: vendor, flag types, targeting complexity, count, cleanup practices.
Why flag testing is non-obvious
Flag-controlled code introduces hidden complexity:
- Variation coverage: a flag with 2 values has 2 paths to test. 5 flags with 2 values = 32 combinations.
- Default behavior: what happens when the SDK fails or the flag evaluator is unreachable? Tests rarely cover this.
- Stale flags: flag is "fully rolled out" but the off-branch code still exists, untested, until someone re-enables it accidentally.
- Combinatorial drift: flag A's variations interact with flag B's variations in unintended ways.
- Targeting bugs: 50% rollout actually delivers to 70% because the hashing isn't uniform.
Test-strategy implication: flagged code is a multi-variant code path, and your tests need to know that.
What ships with it
1 file 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.
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.
- 8d ago First seen · 253 lines · 130 tokens per session scan A 1b4b92e3eaa9
feature-flag-testing is a skill published in the GitHub repository aks-builds/quality-skills (2 stars, last pushed 5d ago), licensed MIT. It adds 130 tokens to every session and 2,526 once invoked, about $0.0006 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.
Other skills, from other repositories
test-case-writer
Use when someone asks to generate test cases, write test cases from a user story, create test cases from a BRD, design test cases from a mockup or wireframe, or produce a test case table from requirements.
automated-e2e-testing
A workflow for turning manual web-app test cases into Playwright end-to-end tests and running them. End-to-end tests check a complete user flow through the website.
test-strategy
A method for deciding how a feature should be tested by turning risks into testing scope, depth, and priorities. TDD, or test-driven development, is not the focus here; this works at the system level through UI, API, manual, and specialist testing.
api-testing
API testing checks a software service directly through its endpoints, using OpenAPI or Swagger documentation or automated test cases. It can produce and run scripts that test requests and responses.
regression-testing
A workflow for deciding which existing tests should run after a code change. Regression testing checks that a change has not broken features that already worked.
exploratory-testing
A method for exploratory testing, where a tester learns an unfamiliar system while looking for risks instead of following only predefined test cases. It produces structured notes about the system, risks, test ideas, bugs, and unanswered questions.