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 agentmods add commands/lttr/claude-marketplace/setupgit clone --depth 1 https://github.com/lttr/claude-marketplaceWrote 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/commands/lttr/claude-marketplace/setup)<a href="https://agentmods.dev/commands/lttr/claude-marketplace/setup"><img src="https://agentmods.dev/badge/commands/lttr/claude-marketplace/setup.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00565 |
| Opus 5 | $0.00000 | $0.00282 |
| Sonnet 5 | $0.00000 | $0.00113 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade B, and why
setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
SCRIPTS_DIR=$(find ~/.claude/plugins -type d -path "*/browser-tools/skills/browser-tools/scripts" 2>/dev/null | head -1) What it actually says
Set up browser-tools plugin by installing dependencies and creating global symlinks.
Execution steps:
Step 1: Find the plugin scripts directory
Locate the browser-tools scripts directory (search in ~/.claude/plugins for browser-tools plugin):
SCRIPTS_DIR=$(find ~/.claude/plugins -type d -path "*/browser-tools/skills/browser-tools/scripts" 2>/dev/null | head -1)
Verify it was found:
echo "Found scripts at: $SCRIPTS_DIR"
Step 2: Install dependencies
cd "$SCRIPTS_DIR" && pnpm install
Step 3: Create ~/bin directory
mkdir -p ~/bin
Step 4: Make scripts executable
chmod +x "$SCRIPTS_DIR"/browser-*.js
Step 5: Create symlinks (WITHOUT .js extension)
IMPORTANT: Symlink names should NOT have .js extension:
ln -sf "$SCRIPTS_DIR/browser-start.js" ~/bin/browser-start
ln -sf "$SCRIPTS_DIR/browser-nav.js" ~/bin/browser-nav
ln -sf "$SCRIPTS_DIR/browser-eval.js" ~/bin/browser-eval
ln -sf "$SCRIPTS_DIR/browser-screenshot.js" ~/bin/browser-screenshot
ln -sf "$SCRIPTS_DIR/browser-pick.js" ~/bin/browser-pick
ln -sf "$SCRIPTS_DIR/browser-cookies.js" ~/bin/browser-cookies
ln -sf "$SCRIPTS_DIR/browser-console.js" ~/bin/browser-console
Step 6: Verify PATH
Check if ~/bin is in PATH:
case "$PATH" in
*"$HOME/bin"*) echo "✓ ~/bin is in PATH" ;;
*) echo "⚠ WARNING: Add ~/bin to PATH in your shell profile" ;;
esac
Summary
After completion, report:
- Dependencies installed: ✓
- Symlinks created: browser-start, browser-nav, browser-eval, browser-screenshot, browser-pick, browser-cookies, browser-console
- PATH status: (OK or needs manual addition)
The browser-tools skill is now ready! Ask me to test web pages, take screenshots, or interact with browsers.
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 First seen · 93 lines · 0 tokens per session scan B 97f25afff048
setup is a command published in the GitHub repository lttr/claude-marketplace (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 565 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
new
Starts a new end-to-end need (preflight, team, spawn OR).
resume
Resumes an interrupted workflow at the current step.
waterfall:quit
Cleanly stops the active workflow (shutdown teammates, marker cleanup, state preservation).
README
Git workflow and quality assurance commands for the claude-skills repository.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
sync
Manually trigger plan-sync to update downstream task specs after implementation drift.