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 desplega-ai/agent-swarm --skill agent-browsergit clone --depth 1 https://github.com/desplega-ai/agent-swarmWrote 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/desplega-ai/agent-swarm/agent-browser)<a href="https://agentmods.dev/skills/desplega-ai/agent-swarm/agent-browser"><img src="https://agentmods.dev/badge/skills/desplega-ai/agent-swarm/agent-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/desplega-ai/agent-swarm/agent-browser"><img src="https://agentmods.dev/badge/skills/desplega-ai/agent-swarm/agent-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 | $0.00125 | $0.01677 |
| Opus 5.5 | $0.00050 | $0.00671 |
| Sonnet 5.5 | $0.00025 | $0.00335 |
| Haiku 4.5 | $0.00013 | $0.00168 |
Grade A, and why
agent-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 5d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-browser
agent-browser (vercel-labs) is the swarm's browser-automation CLI. It drives a headless Chromium over CDP and returns accessibility-tree snapshots with compact @eN refs. Use it for any browser task: verify a UI change, take a screenshot, walk a page, fill a form, extract page text, reproduce a frontend bug, or attach UI evidence to a PR, issue, Linear comment, or Slack thread.
Do not use qa-use. It is not installed in the worker image any more.
Step 0: check that the CLI is present
The full worker image (agent-swarm-worker:latest) ships agent-browser and a headless Chromium. The slim image (:slim) has neither. The first command of any browser work is:
command -v agent-browser
If it prints nothing, you are on the slim image. Say so in your progress report ("agent-browser is not available on this worker image") and fall back to manual QA: write the exact steps a human should run and mark the browser test cases as Blocked, not failed. Do not install a browser or the CLI yourself.
Step 1: load the version-matched guide
The CLI bundles its own usage guide. Load it once per task before the first browser command. Do not guess flags from memory.
agent-browser skills get core # overview + common patterns
agent-browser skills get core --full # adds the full command reference
agent-browser skills list # specialized guides (dogfood, electron, slack, ...)
Step 2: the core loop
agent-browser open <url>
agent-browser snapshot -i # accessibility tree, interactive elements only, @eN refs
agent-browser click @e12 # act on refs from the snapshot
agent-browser fill @e7 "text"
agent-browser screenshot /tmp/<name>.png
agent-browser close
- Re-run
snapshotafter every navigation or state change. Refs are only valid for the snapshot that produced them. - Run one browser session at a time. Call
store-progressbetween page batches so the heartbeat watchdog sees you. - The browser is headless. Local servers inside the worker container are reachable at
http://localhost:<port>. - The image launches Chromium with
--no-sandbox,--disable-dev-shm-usagethroughAGENT_BROWSER_ARGS. If you pass your own--args, include--no-sandboxagain or Chrome will not start.
What ships with it
2 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.
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.
- 5d ago Changed affc9550242c
- 12d ago Changed · +2 lines 291a58991ba7
- 13d ago Changed · +6 tokens per session 52f589b422bf
- 15d ago Changed · +5 lines 3d236b663835
- 21d ago Changed · +1 lines e38405af90dd
- 1mo ago First seen · 85 lines · 119 tokens per session scan A 57e2a78b2a16
agent-browser is a skill published in the GitHub repository desplega-ai/agent-swarm (910 stars, last pushed today), licensed MIT. It adds 125 tokens to every session and 1,677 once invoked, about $0.0005 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 2026-09-19.
Other skills, from other repositories
security-observability
A read-only tool for examining security events already saved by agent-sec-cli, a command-line security log. It can connect those events to an agent session, run, or trace.
add-backend
Guide for adding a backend (Rust or Python) to the agent-sec-core security middleware. Use when creating new backends, integrating Rust or Python code into the security middleware, or extending with new backend actions.
skill-ledger
A security record for agent skills, which are reusable instruction packages for coding agents. It shows their status, reviews risk exposure, and can certify them with quick or user-approved deeper scans.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
pr-body
A tool that reviews all commits on the current branch and creates or updates a pull request title and description. A pull request is a proposed code change submitted for review.
prompt-scanner
A scanner for text sent to an AI agent, looking for prompt injection and jailbreak attempts. Prompt injection is text that tries to override an agent's instructions; a jailbreak tries to bypass its safety limits.