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 cc10143/annotation-overlay-mcp --skill annotation-feedback-waitgit clone --depth 1 https://github.com/cc10143/annotation-overlay-mcpWrote 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/cc10143/annotation-overlay-mcp/annotation-feedback-wait)<a href="https://agentmods.dev/skills/cc10143/annotation-overlay-mcp/annotation-feedback-wait"><img src="https://agentmods.dev/badge/skills/cc10143/annotation-overlay-mcp/annotation-feedback-wait.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 5.1 | $0.00090 | $0.01460 |
| Opus 5 | $0.00045 | $0.00730 |
| Sonnet 5 | $0.00018 | $0.00292 |
| Haiku 4.5 | $0.00009 | $0.00146 |
Grade A, and why
annotation-feedback-wait scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- MCP server 在 localhost:3847 健康(`curl http://localhost:3847/api/health`) How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
标注反馈等待(Annotation Feedback Wait)
何时用
需要用户通过 Annotation Overlay 在浏览器标注页面反馈、并等待其提交时。典型场景:视觉设计评审、UI 问题反馈、页面缺陷圈画、before/after 验证。
核心前提:annotation-overlay-mcp 是 MCP 拉取模型 —— 用户点 Submit 后数据静默落库,agent 不会自动感知。必须主动挂 watcher 或轮询 read_annotations 才能收到反馈。设计缺陷,靠流程弥补。
流程
1. 确认环境
annotation-overlay-mcpMCP server 已连接(read_annotations/capture_page/set_annotation_mode/clear_annotations四个工具可用)- 用户 Chrome 已加载 Annotation Overlay 扩展(chrome://extensions → Load unpacked →
extension/目录) - MCP server 在 localhost:3847 健康(
curl http://localhost:3847/api/health)
2. 先 clear_annotations(关键:保证读到的是这一轮的新反馈)
调 clear_annotations 清空 store。clear 在前而不是在后:这样 read_annotations 永远只返回本轮用户新提交的标注,不需要"判断哪些是残留"。也顺带清掉上一轮的 before/after 截图路径。
(要保留历史做对比就跳过此步,改用 _receivedAt 时间戳判断残留 —— 主流程不做这个。)
3. 挂后台 watcher(在请用户标注之前)
用 Monitor 工具轮询标注数量,count 变化即推送事件。不要用 Bash 的 run_in_background 起 watcher —— 它只在进程退出时通知一次,持续输出的行不会推送,submit 后 agent 感知不到(踩过)。
Monitor 的 command 每个 stdout 行都变成事件通知,所以脚本只在 count 变化时输出一行:
last=""
while true; do
c=$(curl -s --max-time 3 http://localhost:3847/api/annotations 2>/dev/null | grep -o '"count":[0-9]*' | cut -d: -f2)
if [ -n "$c" ]; then
if [ -z "$last" ]; then last="$c"
elif [ "$c" != "$last" ]; then echo "annotation count changed: $last -> $c"; last="$c"; fi
fi
sleep 5
done
Monitor 会一直跑到 timeout 或 TaskStop。用户 submit → count 增加 → 收到事件;agent 自己 clear_annotations → count 回落 → 也收到事件。超时后若还需等待,重启一个 Monitor。
4. 让标注工具栏出现(主流程:agent 自己的浏览器)
主入口:调 annotation-browser-launch skill —— agent 用 Playwright 拉起 chromium-956323 + 扩展 + 持久 profile,导航目标页并 activate() 显示工具栏。agent 拥有浏览器,后续刷新/截图/复验都由 agent 原生控制。
兜底(用户真实 Chrome):若标注必须发生在用户自己的 Chrome,才用 set_annotation_mode(true)(MCP 工具,走 SW 通道,返回 {ok, enabled, tabUrl} —— 核对 tabUrl 是否是要标注的页面)。用户也可按 Ctrl+Shift+A 手动唤出/隐藏。
然后明确告诉用户:在浏览器用标注工具圈画问题区域(箭头/方框/文字/自由画/点选元素/选文字),然后点 Submit。
5. 等通知,读取
收到 watcher 通知(或用户确认已提交)后,调 read_annotations。返回结构:
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.
- 7d ago First seen · 93 lines · 90 tokens per session scan A a4d5a007635f
annotation-feedback-wait is a skill published in the GitHub repository cc10143/annotation-overlay-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 90 tokens to every session and 1,460 once invoked, about $0.0005 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.
Other skills, from other repositories
extension-ui
Build polished Chrome extension UIs (popup/sidepanel/options). Analyze existing UI, suggest improvements, set up design systems, enforce a11y and UX best practices.
peek
Use when the user mentions a recent browser session, an error they just reproduced, "what was the user doing before X", DOM state at some past moment, or wants to turn a manual repro into a Playwright test. Peek exposes 18 MCP tools backed by a local SQLite store of rrweb-captured browser sessions.
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…
draw
Ask the user to draw or annotate something and get it back as an image. Use when the user runs /draw, says they want to sketch or diagram, or when words alone are failing to pin down a visual change and it would be faster for them to point at it.
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include…
generate-token-map
Maps all Figma design tokens from figma-variables.md to their equivalent C++ (Views) identifiers, CSS (WebUI) variables, and Clank (Android) resource attributes/macros/methods in Chromium, and saves the formatted mapping table to the assets directory of the Chrome Design System project. Use this skill when asked to…