Human Review is a browser-based tool for editing HTML and Markdown files, adding document comments, and sending collected feedback to an AI coding agent. It is for people reviewing plans, documents, landing pages, or websites with an agent. Its catalogue skill provides this review workflow inside supported AI harnesses.
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 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/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/petergyang/human-review/src"><img src="https://agentmods.dev/badge/skills/petergyang/human-review/src.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 21 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 35 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 77 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 86 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 133 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00073 | $0.02071 |
| Opus 5.5 | $0.00029 | $0.00828 |
| Sonnet 5.5 | $0.00015 | $0.00414 |
| Haiku 4.5 | $0.00007 | $0.00207 |
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 1mo 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 — 182 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 command blocks until the user hits Send in the browser, then prints their batch and exits:
npx -y human-review poll path/to/file.htmlThe command exits only when the user clicks Send or closes the review. There is nothing to re-run, no interval to poll on, and no
--timeoutto add. It survives the local server restarting, and feedback is saved even if the poll dies, so nothing is ever lost. How you wait depends on your harness:- Claude Code: run it with
run_in_background: trueand end your turn. Claude Code wakes you with the output the moment the command exits. - Codex, Cursor, and everything else: run it in the foreground,
inside your active turn, and stay on it until it prints
feedbackorclosed. Do not detach it or start it as a background session: nothing wakes you when a detached command finishes. While the review is active:- If the user sends a message, answer it as commentary and immediately
resume the foreground poll in the same turn. Do not send a final
response until the poll returns
feedbackorclosed— a final response ends the turn and kills the wait. - If your shell tool caps command duration, pass
--timeouta little under the cap and run bounded polls back to back in the same active turn until one returnsfeedbackorclosed.
- If the user sends a message, answer it as commentary and immediately
resume the foreground poll in the same turn. Do not send a final
response until the poll returns
- Claude Code: run it with
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 38 KB runs code
- chrome-session.js 217 B runs code
- chrome.css 13 KB
- chrome.html 3.8 KB
- cli.js 13 KB runs code
- click-target.js 1.5 KB runs code
- editing.js 2.8 KB runs code
- frame-policy.js 594 B runs code
- html-transform.js 3.4 KB runs code
- markdown.js 4.8 KB runs code
- paths.js 2.5 KB runs code
- sdk.js 67 KB runs code
- serialize.js 1.8 KB runs code
- server-entry.js 613 B runs code
- server.js 60 KB runs code
- setup.js 8.6 KB runs code
- state.js 17 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.
- 1mo ago Changed · +44 lines e919a34c4fbe
- 1mo 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 (1,396 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 2,071 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
browser-use
Control the user's Chrome through the existing persistent Node REPL and the Qwen Browser SDK.
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
playwright
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
url-to-code
Recreate an authorized live website or app URL as a faithful, runnable, frontend-only local implementation.
html-to-video-pipeline
Reliable HTML-to-MP4 rendering via headless browser recording (Playwright/Puppeteer) + ffmpeg — the ordering, gotchas, and verification steps you MUST get right or the output silently rots. Trigger whenever the user is building or debugging any pipeline that turns an HTML/CSS/JS page (single-file, multi-composition…