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/davidtoby/agent-skills/automation-browser-api-workflowsnpx skills add davidtoby/agent-skills --skill automation-browser-api-workflowsgit clone --depth 1 https://github.com/davidtoby/agent-skillsWrote 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/davidtoby/agent-skills/automation-browser-api-workflows)<a href="https://agentmods.dev/skills/davidtoby/agent-skills/automation-browser-api-workflows"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/automation-browser-api-workflows.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 | $0.00082 | $0.00438 |
| Opus 5 | $0.00041 | $0.00219 |
| Sonnet 5 | $0.00016 | $0.00088 |
| Haiku 4.5 | $0.00008 | $0.00044 |
Grade A, and why
automation-browser-api-workflows 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 2d 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.
Record traffic, identify auth/session headers, replay with curl, minimize payloads, and document stable endpoints plus failure codes. What it actually says
Automation, Browser, and API Workflows
Use this umbrella when the task is to operate an external interface repeatedly or replace brittle UI actions with a more reliable API/tool path.
Core workflow
- Identify the interface: browser page, native macOS UI, interactive terminal app, MCP server, RTSP/ONVIF camera, or HTTP API.
- Prefer structured APIs/CLIs over visual clicking when available.
- If starting from browser automation, capture state, network traffic, and request/response shapes so the workflow can be converted to direct calls.
- Keep credentials out of logs and references; store only redacted examples.
- Build deterministic probes/scripts for repeated actions and verify outputs after each side effect.
Labeled playbooks
Browser automation
Use snapshots/selectors/click/type flows for one-off navigation. For repeated work, graduate to direct HTTP or a specialized CLI.
API learner
Record traffic, identify auth/session headers, replay with curl, minimize payloads, and document stable endpoints plus failure codes.
macOS UI automation
Use screenshot/element capture tools for apps that lack APIs. Verify focus and target window before sending keystrokes.
tmux and interactive CLI control
For long-lived or REPL-like tools, send keystrokes and scrape panes instead of running non-PTY commands that will hang.
MCP tool calling
List servers/tools, inspect schemas, then call with JSON arguments. Generate typed wrappers only after schemas are stable.
Camera capture
Probe stream URLs and capture short frames/clips with ffmpeg-compatible tools; avoid assuming camera availability.
Reference files
Exact CLI commands and session-specific endpoint notes are stored in references/from-*.md.
What ships with it
7 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.
- references/from-openclaw-imports-agent-browser.md 12 KB
- references/from-openclaw-imports-api-learner.md 3.6 KB
- references/from-openclaw-imports-camsnap.md 1.4 KB
- references/from-openclaw-imports-mcporter.md 2.0 KB
- references/from-openclaw-imports-openclaw-browser-auto.md 2.3 KB
- references/from-openclaw-imports-peekaboo.md 6.1 KB
- references/from-openclaw-imports-tmux.md 9.6 KB
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.
- 2d ago First seen · 47 lines · 82 tokens per session scan A 43d87098c0d5
automation-browser-api-workflows is a skill published in the GitHub repository davidtoby/agent-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 438 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
web-skills-protocol
Auto-discover and use Web Skills Protocol (WSP) skills when interacting with websites. Use this skill whenever the user asks you to interact with, use, or perform actions on a website or web service — such as searching a site, placing an order, deploying an app, or calling a web API. Before scraping HTML or guessing…
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.
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
当用户明确希望连接到已运行的 Chrome 浏览器、扫描本地 CDP 端口、显式指定 cdpport，或让多个 agent / 工具共享同一个浏览器时，使用本 skill。browser 默认不开放调试端口；仅当用户明确希望其他本地工具附加时才显式传入 cdpport。.
browser_visible
当用户需要控制 browser 的浏览器启动方式时，使用本 skill。browser 默认由 Playwright 直接管理、不开放调试端口（需让其他本地工具附加时显式传 cdpport）；headed 控制是否显示窗口，privatemode 保留用于兼容、不再改变默认行为，browserargs 传入额外的 Chromium 启动参数，executablepath 指定自定义浏览器可执行文件路径。.
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…