OpenClacky is an open-source AI coding agent that uses OpenAI-compatible models to perform tasks through tools and subagents. It is intended for developers who want an agent with flexible model choice and lower token usage. The catalogue skills and agents extend its workflows and capabilities.
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 clacky-ai/openclacky --skill browser-setupgit clone --depth 1 https://github.com/clacky-ai/openclackyWrote 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/clacky-ai/openclacky/browser-setup)<a href="https://agentmods.dev/skills/clacky-ai/openclacky/browser-setup"><img src="https://agentmods.dev/badge/skills/clacky-ai/openclacky/browser-setup/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/clacky-ai/openclacky/browser-setup"><img src="https://agentmods.dev/badge/skills/clacky-ai/openclacky/browser-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Rogue Agent · line 14 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Data Exfiltration · line 237 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00083 | $0.03138 |
| Opus 5.5 | $0.00033 | $0.01255 |
| Sonnet 5.5 | $0.00017 | $0.00628 |
| Haiku 4.5 | $0.00008 | $0.00314 |
Grade A, and why
browser-setup 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 23d 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.
- `curl -s --max-time 3 https://www.google.com -o /dev/null -w "%{http_code}"` returns `000` while baidu.com works How it starts
The opening of the file, as written. The whole thing — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Setup Skill
Configure the browser tool for Clacky. Config is stored at ~/.clacky/browser.yml.
Region-Aware Download Links
Whenever you show the user a link to download or upgrade Chrome/Edge, pick the right one for their region instead of always using google.com.
Treat the user as in China when any of these is true:
- The user is talking to you in Chinese
- The system locale is Chinese (
echo $LANGcontainszh_CN/zh_) - A previous run of
install_browser.shreportedRegion: china(visible in its output) curl -s --max-time 3 https://www.google.com -o /dev/null -w "%{http_code}"returns000while baidu.com works
Use these links accordingly:
| Region | Chrome | Edge |
|---|---|---|
| China | https://www.google.cn/chrome/ | https://www.microsoft.com/zh-cn/edge |
| Global | https://www.google.com/chrome/ | https://www.microsoft.com/edge |
When unsure, show both lines (label them "China:" and "Global:") so the user can pick.
Command Parsing
| User says | Subcommand |
|---|---|
browser setup, 配置浏览器, setup browser |
setup |
browser doctor |
doctor |
If no subcommand is clear, default to setup.
setup
Core Strategy: Progressive validation with clear next steps at each failure point.
Step 1 — Ensure Node.js is installed
Check Node.js version:
node --version 2>/dev/null
Parse the version. If Node.js is missing or version < 20:
Run the bundled installer to automatically install Node.js:
bash ~/.clacky/scripts/install_browser.sh
If the script exits 0 → Node.js is now installed. Proceed to Step 2.
If the script exits non-zero or doesn't exist:
❌ Node.js 20+ is required for browser automation.
Please install Node.js from: https://nodejs.org
Let me know when done and I'll continue.
Wait for user confirmation, then retry this step once. If still failing, stop.
Step 2 — Ensure chrome-devtools-mcp is installed
Check if installed:
chrome-devtools-mcp --version 2>/dev/null
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.
- 23d ago Changed · +2 lines 50c768b9a83a
- 1mo ago First seen · 443 lines · 83 tokens per session scan A f7eb0d1afda3
browser-setup is a skill published in the GitHub repository clacky-ai/openclacky (1,207 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 3,138 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
dingtalk_channel_connect
A browser-based procedure for connecting a QwenPaw bot to DingTalk, a workplace messaging platform. It covers creating or configuring the application and publishing the finished bot.
browser_cdp
Use this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a cdpport, or share a single browser across multiple agents/tools. By default browser opens no debugging port; pass an explicit cdpport only when the user wants another local tool to attach.
browser_cdp
Browser connection controls for finding local debugging ports, attaching to an already running Chrome browser, or sharing one browser between tools.
browser_visible
Browser launch controls for choosing whether a Chromium-based browser window is visible, which browser program to run, and which startup options to pass.
browser_visible
Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit cdpport to let another local tool attach); headed controls whether the window is visible, and privatemode is kept for backward compatibility and…