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 adbertram/cli-tools --skill cli-tool-browser-expertgit clone --depth 1 https://github.com/adbertram/cli-toolsWrote 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/adbertram/cli-tools/cli-tool-browser-expert)<a href="https://agentmods.dev/skills/adbertram/cli-tools/cli-tool-browser-expert"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/cli-tool-browser-expert/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/adbertram/cli-tools/cli-tool-browser-expert"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/cli-tool-browser-expert.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 | $0.00122 | $0.06526 |
| Opus 5.5 | $0.00049 | $0.02610 |
| Sonnet 5.5 | $0.00024 | $0.01305 |
| Haiku 4.5 | $0.00012 | $0.00653 |
Grade A, and why
cli-tool-browser-expert 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 today.
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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<agent_routing>
When this skill is invoked by a parent Codex or Claude session and the current agent is not cli-tool-expert, delegate the work to cli-tool-expert instead of performing CLI browser lifecycle work inline. Pass the complete user request, relevant file paths, constraints, and required validation.
When the current agent is cli-tool-expert, follow this skill normally.
</agent_routing>
<quick_start> Route based on intent:
| Intent | Route |
|---|---|
| Add browser support to existing CLI | Follow <essential_principles> below, starting from the scaffold at _repo/skills/cli-tool/templates/browser/{{name_underscore}}_cli/browser.py |
| Create new browser CLI from scratch | Use the cli-tool skill with --type browser |
| Fix browser auth issues | Check ## Known Issues below first, then read _repo/cli-tools-shared/cli_tools_shared/auth.py (BrowserAutomation) and auth_verifier.py (AuthVerifier) |
| Understand the architecture | Read _repo/cli-tools-shared/cli_tools_shared/auth.py and auth_verifier.py directly — their docstrings are the source of truth |
| </quick_start> |
<essential_principles>
from cli_tools_shared.auth import BrowserAutomation
from .config import get_config
class MyBrowser(BrowserAutomation):
SESSION_NAME = "myservice"
LOGIN_URL = "https://myservice.com/login"
AUTH_CHECK_URL = "https://myservice.com/dashboard"
AUTH_URL_PATTERN = r"/login|/register"
AUTH_SUCCESS_SELECTOR = 'selector-visible-when-logged-in'
def __init__(self, config=None):
config = config or get_config()
super().__init__(config)
If browser.py has custom methods beyond __init__, something is wrong.
def is_logged_in/def is_authenticated/def check_authdef _ensure_logged_in/def verify_session/def check_sessiondef _check_browser_status/def check_browser_session- Direct
sync_playwright()orasync_playwright()imports - Direct
launch_persistent_contextcalls - Custom
BrowserServiceclasses (legacy pattern)
~/.local/share/cli-tools/_shared/chromium-profile
Resolved by BaseConfig.get_persistent_profile_dir() / uses_shared_chromium_profile().
New browser CLIs need zero per-CLI glue — the shared package owns the path.
Stay isolated when:
- the active auth profile name is not
default(multi-account tools), or CLI_TOOLS_ISOLATE_CHROME_PROFILE=1, or- the config does not declare
CredentialType.BROWSER_SESSION.
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.
- today First seen · 266 lines · 122 tokens per session scan A d2544d696514
cli-tool-browser-expert is a skill published in the GitHub repository adbertram/cli-tools (6 stars, last pushed today), licensed MIT. It adds 122 tokens to every session and 6,526 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 2026-11-07.
cli-tool-browser-expert compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cli-tool-browser-expertadbertram/cli-tools | Skill | 6 | today | MIT | A | 122 | Claude Code, Codex |
| x402browser-use/browser-use | Skill | 120k | yesterday | MIT | A | 175 | Claude Code |
| browser-usebrowser-use/browser-use | Skill | 120k | yesterday | MIT | A | 57 | Claude Code, Codex |
| remote-browserbrowser-use/browser-use | Skill | 120k | yesterday | MIT | A | 22 | Claude Code |
| cloudbrowser-use/browser-use | Skill | 120k | yesterday | MIT | A | 177 | Claude Code |
| opencli-autofixjackwener/OpenCLI | Skill | 31k | yesterday | Apache-2.0 | A | 61 | Claude Code |
| opencli-browserjackwener/OpenCLI | Skill | 31k | yesterday | Apache-2.0 | A | 43 | Claude Code |