shellnium CLAUDE.md

Repository instructions for Shellnium, a tool that controls web browsers from Bash or Zsh through Selenium WebDriver. They explain the folders, commands, examples, and container-based checks.

In plain words
What is it for?
Use them when working on the shell library, browser automation examples, Bats tests, ShellCheck validation, or Docker-based development and smoke tests.
Why use it?
They show how to set up, lint, test, and run the project without relying on undocumented local assumptions.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/rasukarusan/shellnium/claude-md
Clone the repo
git clone --depth 1 https://github.com/Rasukarusan/shellnium
Per session 642 This file is loaded in full into every session.
When invoked 642 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00642 $0.00642
Opus 5 $0.00321 $0.00321
Sonnet 5 $0.00128 $0.00128
Haiku 4.5 $0.00064 $0.00064

Measured 3d ago against content hash 12d68cca8c5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shellnium CLAUDE.md scanned grade A 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Shellnium is a Selenium WebDriver implementation for Bash/Zsh. It enables browser automation directly from the terminal using W3C WebDriver protocol over curl + jq.
CLAUDE.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Overview

Shellnium is a Selenium WebDriver implementation for Bash/Zsh. It enables browser automation directly from the terminal using W3C WebDriver protocol over curl + jq.

Repository Structure

  • lib/ — Core library (core.sh, setup.sh, selenium.sh, util.sh)
  • tests/ — Bats test suite (unit tests + syntax/shellcheck validation)
  • examples/ — Practical usage examples (scraping, form fill, login, etc.)
  • demo.sh, demo2.sh, demo3.sh — Demo scripts
  • scripts/ — CI/sandbox setup scripts

Common Commands

Bootstrap

# Install optional local runtime dependencies for running demos on the host
make bootstrap

Linting

# ShellCheck on repository shell scripts
make lint

Testing

# Run the standard Docker-first verification pipeline
make ci

# Run lint and tests locally only if the host already has shellcheck and bats
make ci-local

Docker

# Build image
make docker-build

# Run ShellCheck + tests inside container
make docker-test

# Run browser smoke test inside container
make docker-smoke

Claude Code on the Web

ShellCheck and Bats are not pre-installed in the cloud sandbox environment (Claude Code on the Web). Run the setup script first.

# 1. Setup (install ShellCheck + Bats)
SANDBOX=1 bash scripts/sandbox-setup.sh

# 2. Standard verification
make ci

Notes:

  • scripts/sandbox-setup.sh runs when the env var CLAUDE_CODE_REMOTE=true or SANDBOX=1 is set
  • Docker is unavailable in the sandbox due to network restrictions. Run Docker tests in CI (GitHub Actions) instead
  • Setup logs are written to /tmp/shellnium-setup/

Code Style

  • Quote all variable expansions: "${var}" not $var
  • Use local for function-scoped variables
  • Use snake_case for function names
  • No stray echo debug output
  • Shell dialect: Bash (-s bash for ShellCheck)
  • Exclude SC1091 (source not followed) in ShellCheck: shellcheck -s bash -e SC1091

Architecture Notes

Read the full file on GitHub · 88 lines

Changes

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.

  1. 3d ago First seen · 88 lines · 642 tokens per session scan A 12d68cca8c5e

Subscribe to this mod's changes

shellnium CLAUDE.md is an instructions file published in the GitHub repository Rasukarusan/shellnium (182 stars, last pushed 5mo ago), licensed MIT. It adds 642 tokens to every session, about $0.0032 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.