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 orlando-japan/claude-code-setting --skill feature-flag-strategygit clone --depth 1 https://github.com/orlando-japan/claude-code-settingWrote 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/orlando-japan/claude-code-setting/feature-flag-strategy)<a href="https://agentmods.dev/skills/orlando-japan/claude-code-setting/feature-flag-strategy"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/feature-flag-strategy/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/orlando-japan/claude-code-setting/feature-flag-strategy"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/feature-flag-strategy.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 | $0.00037 | $0.01010 |
| Opus 5 | $0.00018 | $0.00505 |
| Sonnet 5 | $0.00007 | $0.00202 |
| Haiku 4.5 | $0.00004 | $0.00101 |
Grade A, and why
feature-flag-strategy 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature flag strategy
A feature flag is debt. Its purpose is to temporarily decouple "code ships" from "users see it." Like any debt, unpaid flags compound.
Reasons to flag
- Progressive rollout — ship to 1% → 10% → 50% → 100%, watch metrics between each step.
- Kill switch — the ability to turn off a feature in seconds if it breaks.
- Trunk-based development — merge unfinished work safely behind a flag.
- A/B experiment — separate code path for measured comparisons.
Not a reason:
- "We might want to disable this someday." Flags are not futureproofing.
- "Just in case." Add it when there's a concrete case.
Four types of flags
| Type | Lifetime | Who reads it |
|---|---|---|
| Release flag | Days to weeks (until 100%, then delete) | No one after removal |
| Kill switch | Forever (until the feature itself is removed) | Ops during an incident |
| Experiment flag | Duration of the A/B test | Analytics pipeline |
| Permissioning flag | Forever (this is how you gate beta features) | Product & eng |
Release flags have the highest rot rate and cause the most harm if left behind. Kill switches should be boring and stable.
Setup
- Named clearly.
checkout_v2_enabled, notflag_42. - Owned. Every flag has a human owner. No owner = delete.
- Dated. Every release flag has a scheduled removal date at creation time.
- Default-safe. If the flag provider fails, the default must be "off" for new features and "on" for kill switches of shipped features.
- Scoped. User, tenant, percentage, environment — decide and document.
Rollout protocol
- Ship the code with the flag off. Nothing changes for users. Verify deploy didn't break anything.
- Turn on for internal users. Dogfood. Catch obvious bugs.
- 1% of production. Watch metrics: error rate, latency, conversion. Compare flagged vs unflagged.
- 10%, 50%, 100%. Each step, wait long enough to see a problem. Don't marathon.
- Remove the flag code. Schedule this in the same sprint you hit 100%. Don't drift.
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 · 98 lines · 37 tokens per session scan A d18264372b0b
feature-flag-strategy is a skill published in the GitHub repository orlando-japan/claude-code-setting (2 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 1,010 once invoked, about $0.0002 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
feature-flags-architect
Use when adding, retiring, or auditing feature flags. Triggers on "add a flag", "ship behind a flag", "rollout plan", "kill switch", "stale flags", "flag debt", "LaunchDarkly", "GrowthBook", "Statsig", "Unleash", "Flipt", or any progressive-delivery question. Ships flag debt scanner, rollout planner, and kill-switch…
Feature Flag Testing
Testing feature flag implementations including flag evaluation, gradual rollout verification, fallback behavior, and flag cleanup detection.
feature-flags
Feature flag strategies, rollout patterns, kill switches and flag lifecycle management.
feature-flags-architect
Use when adding, retiring, or auditing feature flags. Triggers on "add a flag", "ship behind a flag", "rollout plan", "kill switch", "stale flags", "flag debt", "LaunchDarkly", "GrowthBook", "Statsig", "Unleash", "Flipt", or any progressive-delivery question. Ships flag debt scanner, rollout planner, and kill-switch…
edgeone-clawscan
The first security skill to install after setting up OpenClaw — powered by Tencent Zhuque Lab. Works like an antivirus for your AI environment: audits installed skills, scans skills before installation, and performs a full OpenClaw security health check to prevent data leaks and privacy risks. Backed by Tencent Zhuque…
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.