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/baskb/feedback-studio/feedbacknpx skills add baskb/feedback-studio --skill feedbackgit clone --depth 1 https://github.com/baskb/feedback-studioWhat 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 | $0.00083 | $0.04987 |
| Opus 5 | $0.00042 | $0.02493 |
| Sonnet 5 | $0.00017 | $0.00997 |
| Haiku 4.5 | $0.00008 | $0.00499 |
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 $S/agent-status -H "Content-Type: application/json" -d '{"state":"online","name":"<short role>"}'` How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feedback Studio
A local overlay where the user clicks any element (or selects text) and leaves a typed or
spoken comment; everything saves to .feedback/comments.json (plus a readable
.feedback/FEEDBACK.md). You either start a session or process the comments.
Set FBS=${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 "$FBS" --no-open(or--dir <folder> --no-open). Build first if needed (checkpackage.json). - Markdown (a
.mdfile, or a folder of them):node "$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--hostthe 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 "$FBS" --dir sites/marketing/dist --data-dir sites/marketing/.feedback --label Marketing --port 4001 --no-opennode "$FBS" --dir sites/docs/dist --data-dir sites/docs/.feedback --label Docs --port 4002 --no-opennode "$FBS" --dir sites/app/dist --data-dir sites/app/.feedback --label App --port 4003 --no-open
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 · 251 lines · 83 tokens per session scan B 6f00a78c163b
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.
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…
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.
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…
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…
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 .
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.