Axi

If you're building CLI tools that agents call through shell execution, this gives you practical patterns to minimize token waste and round trips. It covers TOON format for compact output, how to truncate long content without hiding it, when to include aggregate counts to avoid follow-up calls, and how to make errors actionable instead of cryptic. The session integration section is worth reading even if you skip the rest: it shows how to inject ambient context at session start so agents see relevant state before they ask. Opinionated in useful ways, like "content first, not help text" when called with no arguments.

skills.sh installs: 4.8K
GitHub stars: 2.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add kunchenguid/axi --skill axi --agent claude-code

Installs into .claude/skills of the current project.

Files

Agent eXperience Interface (AXI)

AXI defines ergonomic standards for building CLI tools that autonomous agents interact with through shell execution.

Before you start

Read the TOON specification before building any AXI output.

1. Token-efficient output

Use TOON (Token-Oriented Object Notation) as the output format on stdout. TOON provides ~40% token savings over equivalent JSON while remaining readable by agents. Convert to TOON at the output boundary — keep internal logic on JSON.

tasks[2]{id,title,status,assignee}:
  "1",Fix auth bug,open,alice
  "2",Add pagination,closed,bob

2. Minimal default schemas

Every field in stdout costs tokens — multiplied by row count in collections. Default to the smallest schema that lets the agent decide what to do next: typically an identifier, a title, and a status.

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly