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 jtsang4/efficient-coding --skill dev-browsergit clone --depth 1 https://github.com/jtsang4/efficient-codingWrote 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/jtsang4/efficient-coding/dev-browser)<a href="https://agentmods.dev/skills/jtsang4/efficient-coding/dev-browser"><img src="https://agentmods.dev/badge/skills/jtsang4/efficient-coding/dev-browser/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/jtsang4/efficient-coding/dev-browser"><img src="https://agentmods.dev/badge/skills/jtsang4/efficient-coding/dev-browser.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00084 | $0.03192 |
| Opus 5.5 | $0.00034 | $0.01277 |
| Sonnet 5.5 | $0.00017 | $0.00638 |
| Haiku 4.5 | $0.00008 | $0.00319 |
Grade A, and why
dev-browser 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 — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Browser Skill
Browser automation that maintains page state across script executions. Write small, focused scripts to accomplish tasks incrementally. Once you've proven out part of a workflow and there is repeated work to be done, you can write a script to do the repeated work in a single execution.
Choosing Your Approach
- Local/source-available sites: Read the source code first to write selectors directly
- Unknown page layouts: Use
getAISnapshot()to discover elements andselectSnapshotRef()to interact with them - Visual feedback: Take screenshots to see what the user sees
Setup
Two modes available. Ask the user if unclear which to use.
Standalone Mode (Default)
Launches a new Chromium browser for fresh automation sessions.
./skills/dev-browser/server.sh &
Options:
--headless- Run in headless mode (no visible browser window)--stealth- Enable anti-detection mode (default: ON)--no-stealth- Disable stealth mode (use plain browser)--driver [playwright|patchright|auto]- Choose browser driver (default: auto)auto- Auto-install and use patchright, fallback to playwright with patchespatchright- Force use of patchrightplaywright- Use standard playwright
--no-flaresolverr- Disable FlareSolverr auto-start (default: enabled if Docker available)--stop- Stop all dev-browser services and cleanup--help- Show help message
Wait for the Ready message before running scripts.
By default, the server automatically:
- Installs Patchright (if not present) for stealth automation
- Enables stealth mode with browser args and runtime patches
- Starts FlareSolverr Docker container for Cloudflare bypass (requires Docker)
To disable automatic features:
# Disable stealth entirely
./skills/dev-browser/server.sh --no-stealth &
# Disable FlareSolverr auto-start
./skills/dev-browser/server.sh --no-flaresolverr &
# Use plain Playwright without anti-detection
./skills/dev-browser/server.sh --no-stealth --driver playwright &
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.
- bun.lock 46 KB
- package-lock.json 97 KB
- package.json 719 B
- references/scraping.md 5.2 KB
- scripts/start-relay.ts 677 B runs code
- scripts/start-server.ts 6.0 KB runs code
- server.sh 7.4 KB runs code
- src/anti-detection.ts 14 KB runs code
- src/client.ts 18 KB runs code
- src/flaresolverr.ts 9.0 KB runs code
- src/index.ts 10 KB runs code
- src/relay.ts 21 KB runs code
- src/snapshot/browser-script.ts 37 KB runs code
- src/snapshot/index.ts 562 B runs code
- src/snapshot/inject.ts 578 B runs code
- src/types.ts 2.9 KB runs code
- tsconfig.json 849 B
- vitest.config.ts 283 B 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 First seen · 426 lines · 84 tokens per session scan A 0c9e49f3f605
dev-browser is a skill published in the GitHub repository jtsang4/efficient-coding (2 stars, last pushed 8d ago), licensed MIT. It adds 84 tokens to every session and 3,192 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 2026-08-31.
Other skills, from other repositories
browser-use
Control the user's Chrome through the existing persistent Node REPL and the Qwen Browser SDK.
computer-use
A guide to building agents that operate graphical interfaces through screenshots, mouse actions, keyboard input, and waits. It explains how to identify interface elements and safely repeat the observe, decide, and act cycle.
computer-use
Desktop control that picks the right interface per step — app scripting (AppleScript/JXA), accessibility-first observation and actions, pixel fallback, screenshots, zoom, screen recording, and switching between registered computers. Qualified on macOS; Windows, Linux and HarmonyOS backends are experimental.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
unix_computer_use
Local and remote desktop observation/input tools with coordinate normalization (local macOS/Linux by default; optional OSWorld HTTP and SSH Mac backends).
herdr-gpui-browser
Open a browser tab in Herdr GPUI to show the user a web page or an HTML file you wrote, next to the terminal you run in, and get back the notes the user pins on it. Use whenever the user asks to open, start, or show a browser tab, a page, a preview, or a mockup while you run inside Herdr (HERDRENV=1 is set in your…