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 kwannoel/the-controller --skill the-controller-feedback-widgetgit clone --depth 1 https://github.com/kwannoel/the-controllerWrote 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/kwannoel/the-controller/the-controller-feedback-widget)<a href="https://agentmods.dev/skills/kwannoel/the-controller/the-controller-feedback-widget"><img src="https://agentmods.dev/badge/skills/kwannoel/the-controller/the-controller-feedback-widget/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/kwannoel/the-controller/the-controller-feedback-widget"><img src="https://agentmods.dev/badge/skills/kwannoel/the-controller/the-controller-feedback-widget.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 | $0.00040 | $0.07275 |
| Opus 5.5 | $0.00016 | $0.02910 |
| Sonnet 5 | $0.00008 | $0.01455 |
| Haiku 4.5 | $0.00004 | $0.00728 |
Grade A, and why
the-controller-feedback-widget 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 yesterday.
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 — 944 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feedback Widget
Set up a floating feedback button that lets users capture a screenshot, annotate it (freehand draw, arrows, rectangles, crop), and submit it as a GitHub issue — all without leaving the app.
Prerequisites
- Next.js App Router project (13+)
- shadcn/ui installed (Button, Sheet components)
- lucide-react installed
Setup Steps
1. Understand the target project
Before writing any code, determine:
- Auth system: How does the project authenticate users? (Supabase, NextAuth, Clerk, custom JWT, none)
- UI components path: Where are shadcn components? (usually
src/components/ui/orcomponents/ui/) - App metadata: What project-specific context should be captured with feedback? (current page URL is always captured; additional context like selected items, user settings, etc. is project-specific)
2. Install dependencies
npm install html2canvas-pro
# or: pnpm add html2canvas-pro / bun add html2canvas-pro
Ensure these shadcn components are installed:
npx shadcn@latest add button sheet
3. Create the AnnotationEditor component
Create annotation-editor.tsx in the project's component directory.
This component is fully portable — copy it verbatim from ## AnnotationEditor Reference below. It has no project-specific dependencies beyond shadcn Button and lucide icons.
Key features:
- Dual-canvas architecture (base image + draw overlay) for efficient rendering
- Tools: freehand draw, arrow, rectangle, crop
- Undo/clear via ImageData history stack
- Retina display support via
devicePixelRatio - Outputs a single composited PNG data URL on "Done"
4. Create the FeedbackButton component
Create feedback-button.tsx in the project's component directory. This needs project-specific adaptation:
Auth gating: Replace the auth check with the project's auth system:
// Supabase example
const supabase = createClient();
const { data: { user } } = await supabase.auth.getUser();
setIsAuthenticated(!!user);
// NextAuth example
const { data: session } = useSession();
setIsAuthenticated(!!session);
// Clerk example
const { isSignedIn } = useUser();
setIsAuthenticated(isSignedIn ?? false);
// No auth (always show)
setIsAuthenticated(true);
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.
- yesterday First seen · 944 lines · 40 tokens per session scan A 91f89f21e65c
the-controller-feedback-widget is a skill published in the GitHub repository kwannoel/the-controller (13 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 7,275 once invoked, about $0.0002 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 2026-09-23.
Other skills, from other repositories
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…