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 marchatton/agent-skills --skill dev-browsergit clone --depth 1 https://github.com/marchatton/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/marchatton/agent-skills/dev-browser)<a href="https://agentmods.dev/skills/marchatton/agent-skills/dev-browser"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/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/marchatton/agent-skills/dev-browser"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/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 | $0.01688 |
| Opus 5.5 | $0.00034 | $0.00675 |
| Sonnet 5.5 | $0.00017 | $0.00338 |
| Haiku 4.5 | $0.00008 | $0.00169 |
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.
This is a copy
94% identical to dev-browser — 13 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 215 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.
Run all commands from the installed dev-browser skill directory (folder containing this SKILL.md).
In Codex this is typically: $CODEX_HOME/skills/dev-browser/.
Standalone Mode (Default)
Launches a new Chromium browser for fresh automation sessions.
cd "$CODEX_HOME/skills/dev-browser" && ./server.sh &
Add --headless flag if user requests it. Wait for the Ready message before running scripts.
Extension Mode
Connects to user's existing Chrome browser. Use this when:
- The user is already logged into sites and wants you to do things behind an authed experience that isn't local dev.
- The user asks you to use the extension
Important: The core flow is still the same. You create named pages inside of their browser.
Start the relay server:
cd "$CODEX_HOME/skills/dev-browser" && npm i && npm run start-extension &
Wait for Waiting for extension to connect... followed by Extension connected in the console. To know that a client has connected and the browser is ready to be controlled.
Workflow:
- Scripts call
client.page("name")just like the normal mode to create new pages / connect to existing ones. - Automation runs on the user's actual browser session
If the extension hasn't connected yet, tell the user to launch and activate it. Download link: https://github.com/SawyerHood/dev-browser/releases
What ships with it
17 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 3.6 KB runs code
- server.sh 521 B runs code
- src/client.ts 14 KB runs code
- src/index.ts 8.1 KB runs code
- src/relay.ts 21 KB runs code
- src/snapshot/__tests__/snapshot.test.ts 5.6 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 726 B runs code
- tsconfig.json 844 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 · 215 lines · 84 tokens per session scan A 27f16957d4f7
dev-browser is a skill published in the GitHub repository marchatton/agent-skills (5 stars, last pushed 7mo ago), licensed MIT. It adds 84 tokens to every session and 1,688 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to dev-browser, differing in 13 lines, and is treated as a copy.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts with the existing agent-browser CLI, including screenshots and keyboard or interaction checks. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser automation.