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 forest/agent-skills --skill web-cligit clone --depth 1 https://github.com/forest/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/forest/agent-skills/web-cli)<a href="https://agentmods.dev/skills/forest/agent-skills/web-cli"><img src="https://agentmods.dev/badge/skills/forest/agent-skills/web-cli/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/forest/agent-skills/web-cli"><img src="https://agentmods.dev/badge/skills/forest/agent-skills/web-cli.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 | $0.00138 | $0.01061 |
| Opus 5.5 | $0.00055 | $0.00424 |
| Sonnet 5.5 | $0.00028 | $0.00212 |
| Haiku 4.5 | $0.00014 | $0.00106 |
Grade A, and why
web-cli 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 2mo 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Browser Tool
You have the ability to browse the web with a full browser via the system shell.
Always use the built-in bash CLI tool web to interact with and test web apps as you build features.
This should be your GO-TO TOOL for verifying functionality, build status, etc.
Basic Usage
web <url> [options]
By default the page is converted to markdown and displayed to stdout:
web example.com
web localhost:4000/dashboard
You can redirect output to a file:
web example.com --raw > output.html
web example.com --raw > output.json
Never pass --raw or --truncate-after unless the user asks, or if it makes sense (e.g., fetching JSON from an API).
Options
| Option | Description |
|---|---|
--raw |
Output raw HTML/JSON instead of markdown |
--truncate-after <n> |
Truncate after n characters (default: 100000) |
--screenshot <path> |
Save screenshot to filepath |
--profile <name> |
Use named session profile (default: "default") |
--js <code> |
Execute JavaScript after page loads |
--form <id> |
Target form by ID for submission |
--input <name> |
Field name to fill (repeatable) |
--value <value> |
Value for preceding --input |
--after-submit <url> |
URL to load after form submission |
Session Persistence
Each invocation of web uses a shared session — cookie sessions and other state are preserved across separate invocations. This means you can log in to a site and then issue another web command to view or interact with a logged-in page.
Use the optional --profile argument to browse under unique profiles, which is useful for testing multiple logins or sessions:
web http://localhost:4000 --profile "user1"
web http://localhost:4000 --profile "user2"
Common Patterns
Verify a Page Works
web localhost:4000/users
Authenticated Session
# 1. Login and establish session
web localhost:4000/login \
--form login_form \
--input email --value [email protected] \
--input password --value secret \
--profile app_session
# 2. Access protected pages with same session
web localhost:4000/dashboard --profile app_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.
- 2mo ago First seen · 140 lines · 138 tokens per session scan A 28a46eb9cecc
web-cli is a skill published in the GitHub repository forest/agent-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 138 tokens to every session and 1,061 once invoked, about $0.0006 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
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
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.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…