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/hseinmoussa/exo/exo-offgit clone --depth 1 https://github.com/hseinmoussa/exoWrote 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/hseinmoussa/exo/exo-off)<a href="https://agentmods.dev/commands/hseinmoussa/exo/exo-off"><img src="https://agentmods.dev/badge/commands/hseinmoussa/exo/exo-off.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 | $0.00013 | $0.00056 |
| Opus 5 | $0.00006 | $0.00028 |
| Sonnet 5 | $0.00003 | $0.00011 |
| Haiku 4.5 | $0.00001 | $0.00006 |
Grade A, and why
exo-off 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 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.
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
Exit exo mode. Return to your normal, default response style for the rest of this session. If the exo output style is active, switch back with /output-style default.
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 · 6 lines · 13 tokens per session scan A 457b48354b9a
exo-off is a command published in the GitHub repository hseinmoussa/exo (1 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 56 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 2026-08-31.
Other commands, from other repositories
voice-status
Show effective voice + notification state, mute, and per-layer breakdown.
voice-mute
Time-bound mute for both voice + notifications (default 30m). --global for user scope.
voice-test
Fire a test "Claude ready" + "Claude waiting" so you can verify sound, voice, and notifications.
voice-when-focused-on
Announce voice even when terminal/IDE is focused (project scope by default; --global for user scope).
notify-off
Disable OS desktop notifications (project scope by default; --global for user scope).
notify-on
Enable OS desktop notifications (project scope by default; --global for user scope).