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.
git clone --depth 1 https://github.com/EmpiricaAI/empiricaWrote 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/empiricaai/empirica/chrome-health)<a href="https://agentmods.dev/commands/empiricaai/empirica/chrome-health"><img src="https://agentmods.dev/badge/commands/empiricaai/empirica/chrome-health/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/commands/empiricaai/empirica/chrome-health"><img src="https://agentmods.dev/badge/commands/empiricaai/empirica/chrome-health.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 | $0.00020 | $0.00752 |
| Opus 5 | $0.00010 | $0.00376 |
| Sonnet 5 | $0.00004 | $0.00150 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade C, and why
chrome-health scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/claude-mcp-browser-bridge-$(whoami)/ How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/chrome-health — Chrome MCP Health Monitor
Arguments: status (default) | monitor | stop
Chrome MCP connections die silently in long-lived Empirica sessions (known bug: anthropics/claude-code#25956). This command detects dead connections and sets up periodic monitoring.
For /chrome-health or /chrome-health status:
Run the health check script and report results:
python3 ~/.claude/plugins/local/empirica/scripts/chrome_health_check.py
Interpret the output:
| Status | Meaning | Action |
|---|---|---|
healthy |
Chrome MCP is connected and working | No action needed |
degraded |
Warnings present (stale sockets, multiple processes) | Clean up stale resources |
dead |
Chrome MCP connection is broken | Follow recovery instructions in output |
unknown |
Cannot determine status (Chrome may not be enabled) | Check if session was started with --chrome |
If status is dead, display the recovery instructions from the JSON output.
If status is degraded, offer to clean up stale resources automatically.
For /chrome-health monitor:
Set up a recurring health check using CronCreate. This polls every 10 minutes while the session is idle.
-
First check if there's already a monitoring cron job:
- Use
CronListto see existing jobs - If a chrome-health job exists, inform the user and skip
- Use
-
Create the monitoring job:
- Use
CronCreatewith cron"*/10 * * * *"and prompt:Run the Chrome MCP health check silently. Execute: python3 ~/.claude/plugins/local/empirica/scripts/chrome_health_check.py If the status is "dead" or "degraded", warn me immediately with the details and recovery steps. If the status is "healthy", say nothing — just continue silently. - Tell the user: "Chrome MCP health monitoring active. Checks every 10 minutes. Auto-expires after 3 days (CronCreate limit). Run
/chrome-health stopto cancel."
- Use
For /chrome-health stop:
- Use
CronListto find the chrome-health monitoring job - Use
CronDeletewith the job ID to cancel it - Confirm: "Chrome MCP health monitoring stopped."
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.
- 13d ago First seen · 78 lines · 20 tokens per session scan C 2277a747c5ce
chrome-health is a command published in the GitHub repository EmpiricaAI/empirica (246 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 752 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
iai-directive
Record, list, or remove a standing order the user typed themselves.
ship
Deploy feature through automated staging validation to production with rollback testing.
help
Analyze workflow state and provide context-aware guidance with visual progress indicators and recommended next steps.
everme-help
Print a concise EverMe plugin status + reference card.
q-research
Read the research-mode skill's SKILL.md for the full ruleset before proceeding. Follow all constraints, the source lookup cascade, the token budget, and the "what counts as cited" rules exactly.
task-verify
PitWay: Run an inprogress task's approved verification command and persist evidence.