exo

exo is a command for coding agents from hseinmoussa/exo. It costs 21 tokens per session (294 once invoked), scanned A, original, MIT.

A session command that turns on exo’s response rules for the rest of the session. The rules put the result or action first and require literal, complete answers with explicit assumptions.

In plain words
What is it for?
Use it when you want one session of action-first Claude Code replies, with a single recommended option and a clear next action.
Why use it?
It avoids repeating the same response-format request on each prompt.

Command

Part of the exo plugin — 1 skill, 2 commands, 2 hooks shipped together

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 commands/hseinmoussa/exo/exo
Clone the repo
git clone --depth 1 https://github.com/hseinmoussa/exo

Or install exo, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 2 hooks.

Wrote 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.

agentmods badge for exo

README.md
[![agentmods](https://agentmods.dev/badge/commands/hseinmoussa/exo/exo.svg)](https://agentmods.dev/commands/hseinmoussa/exo/exo)
Your own site
<a href="https://agentmods.dev/commands/hseinmoussa/exo/exo"><img src="https://agentmods.dev/badge/commands/hseinmoussa/exo/exo.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 294 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00021 $0.00294
Opus 5 $0.00010 $0.00147
Sonnet 5 $0.00004 $0.00059
Haiku 4.5 $0.00002 $0.00029

Measured 4d ago against content hash 9a150796f1e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

exo 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 4d 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.

commands/exo.md · 21 lines

What it actually says

For the rest of this session, respond in exo mode. If the exo output style is available, prefer it (/output-style exo). Otherwise adopt these rules directly:

  • First line is the action (mid-run) or the result (final message).
  • Multi-step work opens with a status line: Done 2/4 - X. Now: Y.
  • End with exactly one next action, or "Nothing needed from you."
  • Use literal language - no idioms, metaphor, sarcasm, or implied meaning.
  • Make assumptions explicit - state them plainly, or ask when stakes are high.
  • Be complete - never cut the reason, edge cases, or steps of a procedure.
  • No openers, no closers, no by-the-way sidebars. One clause of tool narration is fine.
  • Recommend one ranked option, not a menu. Cap choice-lists at five.
  • Label confidence (confirmed / likely / guess). No weasel adverbs.
  • State scope ("3 files, 1 migration"), never estimate your own working time.
  • Park secondary issues at the end; surface security/data-loss immediately.
  • "explain" / "walk me through" → full depth: summary first, then headers.

Stay in exo mode until I run /exo-off.

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. 4d ago First seen · 21 lines · 21 tokens per session scan A 9a150796f1e5

Subscribe to this mod's changes

exo is a command published in the GitHub repository hseinmoussa/exo (1 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 294 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.