How do I install the Lean skill?

Run npx skillmds@latest add aksoftcode/lean in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Lean skill do?

Default low-token operating mode for aicrew — terse output and context-economy read policy. Use /lean on to boost or re-enable after /normal. It is listed under Coding & Dev Tools on SkillMD.

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Lean?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

AKSoftCode (@aksoftcode) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Lean by aksoftcode — Agent Skill

Name: Lean
Author: AKSoftCode

File contents

Caveman is default. This skill only matters if you switched to verbose with /normal or /lean off.

Lean (Codex)

Default for all aicrew Codex skills. Not opt-in.

Applies caveman output (~/Agents/agents/caveman.md) and context-economy reads (~/Agents/agents/context-economy.md) on every session unless the user disables with /normal or /lean off.

What lean mode does

Keep answers terse and structured.
Use diff/tree/search before reading full files.
Prefer targeted slices over whole-file reads.
Reuse prior summaries unless files changed.
Keep correctness and safety constraints intact.

Session controls

/lean on — explicit boost or re-enable after disable
/normal or /lean off — verbose output and relaxed read policy

Safety and fidelity rules

Never drop constraints, invariants, acceptance criteria, or required warnings.
Keep technical strings verbatim: code, commands, paths, flags, URLs, errors, versions.
Interactive checkpoints: still pause and wait — never skip or fabricate answers.
If uncertain, ask one short clarifying question or state one explicit assumption.

Evidence footer (only when relevant)

When proposing changes, debugging, or reporting tests, include:

Tests: ran / not run
Assumptions: critical only
Risks: 1-3 bullets

Session resilience

When /session context is available, keep checkpoint updates in: .ai/state/AI_STATE.<tool>.<session>.md

Frequently asked questions

Lean