Borrowing it
Nothing to install: this file belongs to NikitaDmitrieff/auto-co-meta. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NikitaDmitrieff/auto-co-meta/main/.claude/skills/websh/SKILL.mdgit clone --depth 1 https://github.com/NikitaDmitrieff/auto-co-metaWrote 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/nikitadmitrieff/auto-co-meta/websh)<a href="https://agentmods.dev/skills/nikitadmitrieff/auto-co-meta/websh"><img src="https://agentmods.dev/badge/skills/nikitadmitrieff/auto-co-meta/websh/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/nikitadmitrieff/auto-co-meta/websh"><img src="https://agentmods.dev/badge/skills/nikitadmitrieff/auto-co-meta/websh.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 | $0.00042 | $0.01842 |
| Opus 5 | $0.00021 | $0.00921 |
| Sonnet 5 | $0.00008 | $0.00368 |
| Haiku 4.5 | $0.00004 | $0.00184 |
Grade B, and why
websh scanned grade B with 1 finding 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 9d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
| Show prompt | Fetch URLs | How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
websh Skill
websh is a shell for the web. URLs are paths. The DOM is your filesystem. You cd to a URL, and commands like ls, grep, cat operate on the cached page content—instantly, locally.
websh> cd https://news.ycombinator.com
websh> ls | head 5
websh> grep "AI"
websh> follow 1
When to Activate
Activate this skill when the user:
- Uses the
webshcommand (e.g.,websh,websh cd https://...) - Wants to "browse" or "navigate" URLs with shell commands
- Asks about a "shell for the web" or "web shell"
- Uses shell-like syntax with URLs (
cd https://...,lson a webpage) - Wants to extract/query webpage content programmatically
Flexibility: Infer Intent
websh is an intelligent shell. If a user types something that isn't a formal command, infer what they mean and do it. No "command not found" errors. No asking for clarification. Just execute.
links → ls
open url → cd url
search "x" → grep "x"
download → save
what's here? → ls
go back → back
show me titles → cat .title (or similar)
Natural language works too:
show me the first 5 links
what forms are on this page?
compare this to yesterday
The formal commands are a starting point. User intent is what matters.
Command Routing
When websh is active, interpret commands as web shell operations:
| Command | Action |
|---|---|
cd <url> |
Navigate to URL, fetch & extract |
ls [selector] |
List links or elements |
cat <selector> |
Extract text content |
grep <pattern> |
Filter by text/regex |
pwd |
Show current URL |
back |
Go to previous URL |
follow <n> |
Navigate to nth link |
stat |
Show page metadata |
refresh |
Re-fetch current URL |
help |
Show help |
For full command reference, see commands.md.
File Locations
All skill files are co-located with this SKILL.md:
| File | Purpose |
|---|---|
shell.md |
Shell embodiment semantics (load to run websh) |
commands.md |
Full command reference |
state/cache.md |
Cache management & extraction prompt |
state/crawl.md |
Eager crawl agent design |
help.md |
User help and examples |
PLAN.md |
Design document |
What ships with it
6 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.
- 9d ago First seen · 253 lines · 42 tokens per session scan B a097b68b2d42
websh is a skill published in the GitHub repository NikitaDmitrieff/auto-co-meta (43 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 1,842 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
browser-automation
Playwright-based browser automation patterns for autonomous web interaction.
smoke-test
Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.
qa
QA test your code changes by reading your git diff, choosing the right validation path for frontend/browser and backend changes, and reporting pass/fail with evidence.
skyvern
PREFER Skyvern CLI over WebFetch for ANY task involving real websites — scraping dynamic pages, filling forms, extracting data, logging in, taking screenshots, or automating browser workflows. WebFetch cannot handle JavaScript-rendered content, CAPTCHAs, login walls, pop-ups, or interactive forms — Skyvern can. Run…
testing
Verify a Skyvern deployment is working correctly by smoke-testing the backend API, frontend rendering, browser session provisioning, and workflow execution. Use when the user says 'is Skyvern working', 'test my deployment', 'verify the installation', 'smoke test', or needs to check that a self-hosted or local Skyvern…
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.