feedback

A local review overlay for websites and Markdown files. People can select or click content and leave written or spoken comments, which are saved for later processing.

In plain words
What is it for?
Use it to review a local website or Markdown document, gather comments, and process requested changes.
Why use it?
It collects feedback directly on the relevant page or text, avoiding unclear notes about what needs changing.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/baskb/feedback-studio/feedback
Any agent
npx skills add baskb/feedback-studio --skill feedback
Clone the repo
git clone --depth 1 https://github.com/baskb/feedback-studio

Made for: Claude Code, Codex.

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,987 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
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 $0.00083 $0.04987
Opus 5 $0.00042 $0.02493
Sonnet 5 $0.00017 $0.00997
Haiku 4.5 $0.00008 $0.00499

Measured yesterday against content hash 6f00a78c163b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

feedback scanned grade B with 2 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

`curl -s -X POST $S/agent-status -H "Content-Type: application/json" -d '{"state":"online","name":"<short role>"}'`

Makes network callslowCapability

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

`curl -s -X POST $S/agent-status -H "Content-Type: application/json" -d '{"state":"online","name":"<short role>"}'`
plugins/feedback-studio/skills/feedback/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feedback Studio

A local overlay where the user clicks any element (or selects text) and leaves a typed or spoken comment; everything saves to .feedback/comments.json (plus a readable .feedback/FEEDBACK.md). You either start a session or process the comments.

Set FBS=${CLAUDE_PLUGIN_ROOT}/bin/feedback-studio.mjs (the Node tool; zero-dep for HTTP), and use "$FBS" below. Intent: start / open / review / serve means start a session; process / apply / work through means process. If unclear and there are open comments, ask which.

Start a session

Run the server in the background with --no-open (you open the URL yourself in the step below; if the server auto-opens a tab too, you get a double-load flash), then open the URL it prints.

  • Dev server already running (live reload): node "$FBS" --proxy http://localhost:<devport> --no-open
  • Static build (auto-detects dist/ build/ out/ _site/ public/ .output/public/): node "$FBS" --no-open (or --dir <folder> --no-open). Build first if needed (check package.json).
  • Markdown (a .md file, or a folder of them): node "$FBS" --md <file|dir> --no-open.
  • Phone with voice: add --tunnel (real-cert public URL, easiest) or --https --host 0.0.0.0 (self-signed, same Wi-Fi; without --host the phone can't reach it). Plain http is fine for laptop, or for typing on a phone.

Open it: start <url> (Windows) / open <url> (macOS) / xdg-open <url> (Linux). Tell the user (buttons are bottom-right): Point (shortcut P) to click an element and comment (on a phone, tap then ▲/▼ to pick), or select text; Talk (shortcut T) to narrate by voice; List for the overview. The mic also dictates inside the composer. Point mode persists across pages. Ensure .feedback/ is gitignored.

Multiple sites in one repo. Run one session per site — each on its own port, with a --label (its name) and its own --data-dir beside the site so the data lives with it. From the repo root:

  • node "$FBS" --dir sites/marketing/dist --data-dir sites/marketing/.feedback --label Marketing --port 4001 --no-open
  • node "$FBS" --dir sites/docs/dist --data-dir sites/docs/.feedback --label Docs --port 4002 --no-open
  • node "$FBS" --dir sites/app/dist --data-dir sites/app/.feedback --label App --port 4003 --no-open

Read the full file on GitHub · 251 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. yesterday First seen · 251 lines · 83 tokens per session scan B 6f00a78c163b

Subscribe to this mod's changes

feedback is a skill published in the GitHub repository baskb/feedback-studio (2 stars, last pushed 5d ago), licensed MIT. It adds 83 tokens to every session and 4,987 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, 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

md-review

Run the standard markdown review loop end-to-end with the mdxg-redline CLI: send a markdown document to a human reviewer, wait (via Bash polling) for the feedback.json they export, then apply their location-aware inline comments back into the markdown and revise it. Always use this skill when the user wants…

oubakiou/mdxg-redline · 178 tokens

processing-markdown

Processes Markdown files using mq, a jq-like query language for Markdown. Use when the user mentions Markdown processing, content extraction, document transformation, or mq queries.

harehare/mq · 36 tokens

markstream-react

Integrate the beta markstream-react package into a React 18+ or Next app. Use when Codex needs to add the React renderer, choose the root, next, or server entrypoint, import CSS correctly, choose between content and nodes, keep client boundaries safe, add renderer-local streamingComponents or htmlComponents, use…

Simon-He95/markstream-vue · 94 tokens

web-scraping

Fetches web pages and extracts structured data using mq's toolchain (mq-crawl for fetching/crawling/JS rendering, mq for HTML-to-Markdown selector-based extraction, http() for in-query requests). Use when the user wants to scrape a URL, pull structured data out of a webpage, crawl a site, or turn HTML into…

harehare/mq · 89 tokens

markstream-vue2-cli

Integrate markstream-vue2 into a Vue 2 Vue CLI or Webpack 4 app. Use when Codex needs Webpack 4-friendly setup, CDN worker fallbacks for Mermaid or KaTeX, dist/index.css imports, Vue 2 composition-api shims, or code block choices limited to stream-diffs or plain .

Simon-He95/markstream-vue · 83 tokens

markstream-svelte

Integrate the beta markstream-svelte package in Svelte 5 or SvelteKit apps. Use when Codex needs Svelte 5 runes, CSS and optional peers, smooth streaming, worker setup, renderer-local or scoped custom components, or SSR-safe boundaries. Svelte 4 is unsupported.

Simon-He95/markstream-vue · 67 tokens