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 agentmods add skills/arjunprabhulal/devops-skills/feature-flagsnpx skills add arjunprabhulal/devops-skills --skill feature-flagsgit clone --depth 1 https://github.com/arjunprabhulal/devops-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/arjunprabhulal/devops-skills/feature-flags)<a href="https://agentmods.dev/skills/arjunprabhulal/devops-skills/feature-flags"><img src="https://agentmods.dev/badge/skills/arjunprabhulal/devops-skills/feature-flags.svg" alt="Measured on agentmods" 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 | $0.00119 | $0.01364 |
| Opus 5 | $0.00060 | $0.00682 |
| Sonnet 5 | $0.00024 | $0.00273 |
| Haiku 4.5 | $0.00012 | $0.00136 |
Grade A, and why
feature-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 4d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Flags
A feature flag turns a deploy-time decision into a runtime decision, which is enormously valuable for exactly one reason: it lets you separate "is the code safely running in production" from "can users see the new behavior." That separation is the entire point. Flags misused as a permanent branching mechanism, left in code long after their purpose is served, become a second, undocumented configuration system that makes the codebase harder to reason about than not having flags at all.
Every flag you add is a debt you're taking on with an implicit promise to pay it back by removing it.
A feature flag is a temporary bridge between "deployed" and "released" — it should have an owner and an expected removal date from the moment it's created.
1. Distinguish release flags from operational flags — they have different lifespans
A release flag exists to ramp a specific feature from 0% to 100% of users and then gets deleted once fully rolled out — its lifespan is weeks, not years. An operational flag (a kill switch for a risky dependency, a toggle for degrading gracefully under load) is meant to live indefinitely as a genuine piece of operational tooling. Treating a release flag like it's permanent is how flag debt accumulates; treating an operational kill switch like it needs to be deleted after rollout is how you lose a tool you'll need in the next incident.
- Release flags: temporary, tied to one feature's rollout, deleted once at 100% and stable.
- Operational/kill-switch flags: permanent, tied to resilience, kept and tested like any other safety mechanism.
- Experiment flags: temporary, tied to an A/B test's duration, deleted once the experiment concludes and a winner is picked.
Done when: every flag in the system is labeled with its type, and release/experiment flags have a target removal date.
2. Target deliberately, and make the default path the safe one
Flag targeting (percentage rollout, user segment, internal-only) is what makes a flag useful for buying information gradually rather than an all-or-nothing switch. The default state of any new flag should be "off" or "old behavior," so that if the flag system itself fails (config service down, cache stale) the system fails toward the known-safe, already-verified behavior rather than toward the new, less-proven one.
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.
- 4d ago First seen · 108 lines · 119 tokens per session scan A 0f2867b7c331
feature-flags is a skill published in the GitHub repository arjunprabhulal/devops-skills (2 stars, last pushed 10d ago), licensed MIT. It adds 119 tokens to every session and 1,364 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
google-mobile-ads-android-migrate-to-next-gen
Migrates Android applications from the old, legacy Google Mobile Ads (GMA) SDK (com.google.android.gms:play-services-ads) to the new GMA Next-Gen SDK (com.google.android.libraries.ads.mobile.sdk:ads-mobile-sdk). Provides comprehensive mapping tables for imports, classes, and method signatures to help determine…
agent-platform-inference
Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when asked to perform inference, ask a model a question, run a test prompt, execute chat completions, or generate code for calling…
agent-platform-deploy
Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check the status of an in-progress deployment operation, or clean up resources by undeploying models and deleting endpoints. Use when asked to actively deploy a model, list the Model Garden CATALOG of available models, check if a…
agent-platform-eval-flywheel
Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing failures, comparing results before and after a fix, or when guidance is needed on…
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
agent-platform-alert-configuration
Configures best-practice alerting policies for AI agents using OpenTelemetry (OTel) metrics, generating output as Terraform (.tf) configuration files. Use when analyzing, writing, or deploying alerting policies to monitor agent latency, error rates, token usage, and quality metrics. Don't use for standard…