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.
git clone --depth 1 https://github.com/smithdak/claude-marketplaceWrote 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/agents/smithdak/claude-marketplace/feature-flags)<a href="https://agentmods.dev/agents/smithdak/claude-marketplace/feature-flags"><img src="https://agentmods.dev/badge/agents/smithdak/claude-marketplace/feature-flags/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/agents/smithdak/claude-marketplace/feature-flags"><img src="https://agentmods.dev/badge/agents/smithdak/claude-marketplace/feature-flags.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 | $0.00017 | $0.01632 |
| Opus 5.5 | $0.00007 | $0.00653 |
| Sonnet 5.5 | $0.00003 | $0.00326 |
| Haiku 4.5 | $0.00002 | $0.00163 |
Grade A, and why
optimizely-exp-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 1mo 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimizely Feature Flags Agent
Analyze feature flag implementation, typed accessors, and flag lifecycle management.
Analysis Areas
1. Missing Default Values
FF-001: Feature Flag Without Default (Warning)
Flags should have defaults for SDK failures:
Grep: isFeatureEnabled\(.*\)(?!\s*\?\?)
Grep: decide\(.*\)\.enabled(?!\s*\?\?)
Bad Pattern:
// No fallback if SDK fails!
const isEnabled = optimizely.isFeatureEnabled('new_feature', userId);
if (isEnabled) {
showNewFeature();
}
Good Pattern:
// With default value
const isEnabled = optimizely.isFeatureEnabled('new_feature', userId) ?? false;
// Or with try/catch
let isEnabled = false;
try {
isEnabled = optimizely.isFeatureEnabled('new_feature', userId);
} catch {
console.warn('Feature flag check failed, using default');
}
2. Typed Feature Variables
FF-002: No Typed Feature Variables (Warning)
Feature variables should use typed accessors:
Grep: getFeatureVariable\(
Grep: getFeatureVariableString\(
Grep: getFeatureVariableInteger\(
Grep: getFeatureVariableDouble\(
Grep: getFeatureVariableBoolean\(
Grep: getFeatureVariableJSON\(
Bad Pattern:
// Generic accessor - type unsafe
const discount = optimizely.getFeatureVariable('pricing', 'discount', userId);
// discount is string | number | boolean | object | null
Good Pattern:
// Typed accessor
const discount = optimizely.getFeatureVariableDouble('pricing', 'discount', userId);
// discount is number | null
// Or with modern decide API
const decision = optimizely.decide('pricing', userId);
const discount = decision.variables.discount as number;
3. Render Loop Evaluation
FF-003: Flag Evaluated in Render Loop (Warning)
Flags should not be evaluated on every render:
Grep: function.*\{[\s\S]*?isFeatureEnabled
Grep: return.*isFeatureEnabled
Bad Pattern:
function Component() {
// Called on EVERY render!
const showBanner = optimizely.isFeatureEnabled('banner', userId);
return showBanner ? <Banner /> : null;
}
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.
- 1mo ago First seen · 274 lines · 17 tokens per session scan A 1e1854fe466d
optimizely-exp-feature-flags is an agent published in the GitHub repository smithdak/claude-marketplace (3 stars, last pushed 8mo ago), licensed MIT. It adds 17 tokens to every session and 1,632 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…