lean-context
Skill3 starsChanged 6 months agoMITView on GitHub
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.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- OrionicsLtd/claude-skillstheir own version, first seen Nov 1, 2026
- EARTH157/claude-skillstheir own version, first seen Oct 25, 2026
- liujiarui0918/claude-code-codex-strongesttheir own version, first seen Oct 13, 2026
- wangxiaohuiboy/lean-agent-skillstheir own version, first seen Sep 10, 2026
- sayeediftekhar/lean-contexttheir own version, first seen Jul 28, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- liujiarui0918/claude-code-codex-strongest★ 1same name
- OrionicsLtd/claude-skills★ 1same name
- EARTH157/claude-skills★ 0same name
- sayeediftekhar/lean-context★ 0same name
- wangxiaohuiboy/lean-agent-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- ai-commercialSkill
- frontend-designSkill
- intro-trailerSkill
- reviewSkill
- superteamSkill
- token-disciplineSkill
- ux-designerSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Checkpoint summary: Write a 2-3 sentence summary of everything accomplished so far and what remains.
- Distinctive: line 21
Keep all responses to 1-3 sentences unless showing code
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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)
- Checkpoint summary: Write a 2-3 sentence summary of everything accomplished so far and what remains. This creates a "save point" that survives compaction.
- 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.
- Remaining work estimate: List what's left to do. If multiple independent tasks remain, suggest parallel agent delegation to keep the main context lean.
- 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
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.