dryui-live-feedback

dryui-live-feedback is a skill for Codex from rob-balfre/dryui. It costs 57 tokens per session (2,304 once invoked), scanned A, original, MIT.

A workflow for collecting visual feedback on a DryUI application. It opens the running app, lets a user draw annotations on the page, and sends those comments back for implementation.

In plain words
What is it for?
Use it when a user wants to annotate a page, review a UI visually, or iterate on an interface using drawings and feedback submissions.
Why use it?
It turns visual review into a structured loop, so layout or styling issues can be marked directly on the interface and handled one by one.

Skill for Codex

Written for Codex: reads ~/.codex or $CODEX_HOME. Also seen: mentions Codex.

Good fit Use it when a user wants to annotate a page, review a UI visually, or iterate on an interface using drawings and feedback submissions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rob-balfre/dryui/dryui-live-feedback
Install

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.

Any agent
npx skills add rob-balfre/dryui --skill dryui-live-feedback
Clone the repo
git clone --depth 1 https://github.com/rob-balfre/dryui

Made for: Codex.

Wrote 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.

agentmods badge for dryui-live-feedback

README.md
[![agentmods](https://agentmods.dev/badge/skills/rob-balfre/dryui/dryui-live-feedback/github.svg)](https://agentmods.dev/skills/rob-balfre/dryui/dryui-live-feedback)
Your own site
<a href="https://agentmods.dev/skills/rob-balfre/dryui/dryui-live-feedback"><img src="https://agentmods.dev/badge/skills/rob-balfre/dryui/dryui-live-feedback/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.

agentmods 80×15 button for dryui-live-feedback

Your own site · 80×15
<a href="https://agentmods.dev/skills/rob-balfre/dryui/dryui-live-feedback"><img src="https://agentmods.dev/badge/skills/rob-balfre/dryui/dryui-live-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,304 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.02304
Opus 5 $0.00028 $0.01152
Sonnet 5 $0.00011 $0.00461
Haiku 4.5 $0.00006 $0.00230

Measured 9d ago against content hash 3d7898dcba78, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dryui-live-feedback scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:4748/health
skills/dryui-live-feedback/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feedback

Orchestrates the visual feedback loop: ensure servers are running, open the app, wait for the user to draw annotations, then act on them.

1. Ensure the Feedback Server Is Running

Check the health endpoint:

curl -s http://localhost:4748/health

If it returns {"status":"ok"}, the server is already running. Otherwise launch it:

bunx dryui-feedback --no-open

In the DryUI monorepo, if you need a repo-internal fallback and dist/ does not exist, build first:

cd packages/feedback-server && bun run build

The server binds port 4748 by default (DEFAULT_FEEDBACK_PORT) and walks up to the first free port if it's taken. State lives under <project>/.dryui/feedback/ (store.db, screenshots, server.json), so each project keeps its own queue.

If dryui.config.json has feedback.defaultAgent, the server uses it as the dispatch default. Users can edit that file directly or ask an agent to add one of the manual MCP paths listed under feedback.manualAgentConfig.

2. Confirm the Widget Is Wired and Find the Dev Server

2a. Verify @dryui/feedback and @dryui/feedback-server are installed and the widget is mounted

dryui-init installs @dryui/feedback and @dryui/feedback-server as dev deps but does NOT mount the widget by default — the mount is opt-in. Confirm the install + mount before continuing:

test -f node_modules/@dryui/feedback/package.json && echo WIDGET_OK || echo WIDGET_MISSING
test -x node_modules/.bin/dryui-feedback && echo SERVER_OK || echo SERVER_MISSING
grep -q "from '@dryui/feedback'" src/routes/+layout.svelte && echo MOUNTED || echo MISSING

If WIDGET_MISSING or SERVER_MISSING, fall through to the dryui-init skill's Apply Setup → Install steps. If MISSING (mount), follow dryui-initLive Feedback (Opt-In) to add the import + <Feedback serverUrl="http://localhost:4748" /> mount in src/routes/+layout.svelte. A package.json overrides entry alone is not proof of installation — bun only applies overrides when the package is also a dep, so the node_modules check is the source of truth. Skipping this step is the most common way the rest of the flow silently breaks: the import resolves at edit time but vite throws Cannot find module '@dryui/feedback' on first request, or bunx dryui-feedback 404s against the npm registry because no top-level package by that name exists.

Read the full file on GitHub · 167 lines

Changes

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.

  1. 9d ago First seen · 167 lines · 57 tokens per session scan A 3d7898dcba78

Subscribe to this mod's changes

dryui-live-feedback is a skill published in the GitHub repository rob-balfre/dryui (9 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 2,304 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality and accessible markup. Use this skill when the user asks to build or beautify web components, pages, applications, landing pages, dashboards, artifacts, or React/HTML/CSS UI. Generates creative, polished code that avoids generic AI…

spinspire/pocketbase-sveltekit-starter · 76 tokens

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json…

shadcn-ui/ui · 94 tokens

popular-web-designs

54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.

NousResearch/hermes-agent · 23 tokens

anti-ui-slop

Stop coding agents from shipping generic UI. Extend the product's design system, use UIZZE evidence only when useful, cover required states, and inspect the rendered result.

sickn33/agentic-awesome-skills · 39 tokens

shadcn-ui-flutter

A comprehensive Flutter UI library inspired by shadcn/ui. Provides high-quality, customizable, and accessible components including Buttons, Cards, Forms, and more. Use this skill when building Flutter UIs, implementing design systems, or needing specific component usage examples.

nank1ro/flutter-shadcn-ui · 58 tokens

design

Use when the user wants the visual/experiential design of a product done systematically — a design system, a screen, a landing page, or a visual identity — grounded in researched real-world prior art and free of AI slop. Establishes/extends the design system, invokes the matching local taste skill, dispatches the…

jeremylongshore/tons-of-skills-marketplace · 126 tokens