kevinchamplin/claude-skills

lean-context

Activate strict context-saving mode mid-conversation. Use when conversations are getting long, before starting large tasks, or when the user says /lean. Audits conversation state and creates a checkpoint summary.

First seen Jun 10, 2026

Installation

$ npx skills add kevinchamplin/claude-skills --skill lean-context

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from kevinchamplin/claude-skills.

npx skills add kevinchamplin/claude-skills

Browse all from kevinchamplin/claude-skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 3
License LICENSE
Default branch main
Open issues 0
Status Active

Skill metadata

Parsed from SKILL.md frontmatter.

Declared agents claude-code

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,375 B
  • docs SUMMARY.md 232 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 33 installs

SKILL.md

Lean Context Mode

Context efficiency rules are already enforced globally via CLAUDE.md. This skill adds conversation-specific actions when things are getting long.

Actions (do all of these immediately)

  1. Checkpoint summary: Write a 2-3 sentence summary of everything accomplished so far and what remains. This creates a "save point" that survives compaction.
  1. Stale context audit: Identify any large tool outputs earlier in the conversation that are no longer needed (old file reads, long bash outputs, superseded diffs). Note them — they'll be compressed first.
  1. Remaining work estimate: List what's left to do. If multiple independent tasks remain, suggest parallel agent delegation to keep the main context lean.
  1. Strict mode reminder: For the rest of this conversation:

- Re-read nothing — reference earlier checkpoint summaries instead - Delegate ANY research to Explore agents - Keep all responses to 1-3 sentences unless showing code

Output

Respond with:

  • The checkpoint summary
  • "Lean mode active" confirmation
  • Any specific suggestions for the current task