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/vinta/hal-9000/hal-voice-togglegit clone --depth 1 https://github.com/vinta/hal-9000What 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 | $0.00010 | $0.00179 |
| Opus 5 | $0.00005 | $0.00089 |
| Sonnet 5 | $0.00002 | $0.00036 |
| Haiku 4.5 | $0.00001 | $0.00018 |
Grade A, and why
hal-voice-toggle scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Toggle the hal-voice plugin on or off by flipping enabled in config.json.
Run this command:
python3 -c "
import json
from pathlib import Path
config_path = Path('${CLAUDE_PLUGIN_ROOT}') / 'config.json'
try:
config = json.loads(config_path.read_text())
except (FileNotFoundError, json.JSONDecodeError):
config = {}
config['enabled'] = not config.get('enabled', True)
config_path.write_text(json.dumps(config, indent=2))
state = 'enabled' if config['enabled'] else 'disabled'
print(f'hal-voice: sounds {state}')
"
Print the output to the user exactly as returned.
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.
- yesterday First seen · 31 lines · 10 tokens per session scan A 8d5d7ef12006
hal-voice-toggle is a command published in the GitHub repository vinta/hal-9000 (125 stars, last pushed 3d ago), licensed MIT. It adds 10 tokens to every session and 179 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
add-endpoint
Scaffold a new API endpoint with full layering.
review
Review code changes against project conventions.
analytics
You are tasked with generating a comprehensive analytics dashboard for the Claude Code workflow opti.
coverage-gaps
You are tasked with generating a visual coverage gaps dashboard for the mcp-server-langgraph project.
benchmark
Execute performance benchmarks and analyze results.
deploy
You are tasked with deploying the mcp-server-langgraph application to various targets. This command.