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/petergyang/human-review/srcnpx skills add petergyang/human-review --skill srcgit clone --depth 1 https://github.com/petergyang/human-reviewWrote 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/petergyang/human-review/src)<a href="https://agentmods.dev/skills/petergyang/human-review/src"><img src="https://agentmods.dev/badge/skills/petergyang/human-review/src.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.01405 |
| Opus 5 | $0.00036 | $0.00702 |
| Sonnet 5 | $0.00015 | $0.00281 |
| Haiku 4.5 | $0.00007 | $0.00140 |
Grade A, and why
human-review 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 4d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
human-review
The user reviews your HTML, Markdown, or localhost page in a real browser: they fix small things by typing, select anything to comment on it, and send you the whole batch at once.
Markdown files open rendered. Their quotes and edits reference the rendered text, and the file itself is never touched — apply every change to the Markdown source, keeping its formatting syntax.
The loop
-
Write or update the HTML or Markdown file, or start the local page being reviewed.
-
Open it for the user:
npx -y human-review path/to/file.htmlFor a page served by a local development server, open the real route instead of recreating it as a separate HTML file:
npx -y human-review http://localhost:3000/wiki -
Wait for feedback. This blocks until they hit Send, or the timeout passes:
npx -y human-review poll path/to/file.html --timeout 600Keep this command in the foreground. Do not end your turn while it is waiting. If your shell returns a process or session handle, keep waiting on that handle until the command exits. If it prints
{"status":"timeout"}, no feedback has arrived yet — run the same poll command again to keep waiting. Feedback is saved even if a poll dies, so nothing is ever lost.If it prints
{"status":"closed"}, the user ended the review from the browser — stop polling and do not run the poll command again. Unsent feedback is kept and ships the next time this target is reviewed. -
Apply what comes back, then wait again.
--ackclears the batch you just handled:npx -y human-review poll path/to/file.html --ack --timeout 600
Repeat 3–4 until the user says they are done.
Not sure whether feedback is already waiting — say, at the start of a new turn? This answers instantly without blocking:
npx -y human-review status path/to/file.html
It prints {"status": "feedback-waiting"} when a batch is ready for a poll,
plus counts of unsent comments and edits still in the browser.
What ships with it
18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- anchor-text.js 3.6 KB runs code
- chrome-client.js 28 KB runs code
- chrome-session.js 217 B runs code
- chrome.css 12 KB
- chrome.html 3.5 KB
- cli.js 11 KB runs code
- click-target.js 982 B runs code
- editing.js 2.8 KB runs code
- frame-policy.js 623 B runs code
- html-transform.js 2.9 KB runs code
- markdown.js 3.3 KB runs code
- paths.js 2.5 KB runs code
- sdk.js 54 KB runs code
- serialize.js 1.8 KB runs code
- server-entry.js 392 B runs code
- server.js 40 KB runs code
- setup.js 5.2 KB runs code
- state.js 9.5 KB runs code
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.
- 4d ago First seen · 138 lines · 73 tokens per session scan A 010c2fda6356
human-review is a skill published in the GitHub repository petergyang/human-review (1,206 stars, last pushed 19d ago), licensed MIT. It adds 73 tokens to every session and 1,405 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
svg-press
Teaches agents how to hand-craft self-contained SVG diagrams that render correctly in browsers, tags, and Playwright PDF/PNG. Covers containment math, viewBox sizing, arrow construction, text hierarchy, KDCube brand color tokens, semantic zone fills, badges, the PNG inspection loop, writepng parameters, multi-diagram…
cc-htmlfeedback
Visualizing complex material (plans, designs, architectures, data models) as a self-contained HTML page is the preferred, best-practice way to collect the user's feedback - use this tool for EVERY HTML page meant to gather feedback. It serves your page(s) with a comment widget injected, then turns the comments you…
review-html-artifacts
Preview, edit, annotate, and generate final local HTML artifacts through Anno. Use when a user asks to open an .html/.htm file for visual review, directly edit page text, mark formatting or layout changes, continue an existing review session, or turn completed browser edits and annotations into a final standalone HTML…
interactive-html
Turn a folder of static HTML into a live commenting surface and act as the agent that responds. Inject a client library, start a local server, watch an on-disk inbox; when the user highlights text, picks an element, drags a region, or asks a question, read it and edit the HTML in response. If the user has no HTML yet…
markview
Use when the user wants to preview, browse, or read a directory's markdown or HTML files rendered in the browser — e.g. "preview the markdown files here", "start the markdown reader", "show me these md files rendered". Starts a local web server with a styled viewer.
html-report
Nested swiss-knife reference for standalone HTML deliverables. Produce polished, self-contained HTML deliverables (research memos, literature maps, dashboards, audit reports, side-by-side comparisons) that humans open in a browser or receive as Telegram/email attachments. Covers a standalone HTML skeleton, math…