context-hygiene
Skill0 starsChanged 7 months agoMITView on GitHub
Reference for Claude Code context management. Use /by-the-way for side questions, /fork for path exploration, and context:fork in skills for isolated execution. Trigger on "context is getting large", "session feels slow", "Claude forgot what we were doing", "how do I manage context".
5 other projects use a version of this.
Adopted by
Most recently taken up by
- getcargohq/cargo-manifesttheir own version, first seen Nov 1, 2026
- emanueledenaro/claude-skillstheir own version, first seen Oct 15, 2026
- wrg32786/aigent-ostheir own version, first seen Oct 13, 2026
- Leostruka/devin-bundletheir own version, first seen Aug 15, 2026
- lightarktech/founder-coding-skillstheir own version, first seen Jul 26, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- wrg32786/aigent-os★ 25same name
- getcargohq/cargo-manifest★ 11same name
- lightarktech/founder-coding-skills★ 1same name
- emanueledenaro/claude-skills★ 0same name
- Leostruka/devin-bundle★ 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 repository24 other files it gives its agents.
- aarSkill
- agent-cost-modelSkill
- banana-makerSkill
- bitter-lesson-scorecardSkill
- boot-tax-monitorSkill
- compensating-complexity-auditorSkill
- context-fork-guideSkill
- counterargument-stress-testSkill
- dark-code-auditSkill
- executive-briefingSkill
- failure-asymmetrySkill
- failure-postmortemSkill
- file-intelSkill
- geopolitical-signal-enricherSkill
- get-api-docsSkill
- gh-reviewSkill
- model-routerSkill
- optimize-descriptionSkill
- prompt-rewriterSkill
- skill-auditSkill
- skill-maintenanceSkill
- spec-gap-detectorSkill
- token-burn-auditorSkill
- what-am-i-forgettingSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Use these proactively — context bloat is gradual and invisible until quality degrades.
- Distinctive: line 26
When you want to try a different approach without risking your current progress:
- Very specific: line 40
Add context: fork to any SKILL.md frontmatter to run heavy skills in an isolated context window.
“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
Context Hygiene — 3 Shields
Three techniques for keeping Claude Code sessions focused and performant. Use these proactively — context bloat is gradual and invisible until quality degrades.
Shield 1: /by-the-way (Side Questions)
For quick lookups that don't deserve main context space:
- "What was that Calendly link?"
- "How many slides in the last deck?"
- "What's the standard meeting length?"
Usage: Type /by-the-way then your question. Answer returns without polluting
the main conversation thread.
Best for: Static data retrieval, FAQ-style questions, quick lookups from CLAUDE.md or project files.
Shield 2: /fork (Path Exploration)
When you want to try a different approach without risking your current progress:
- "Let me try a completely different design"
- "What if we used a different tech stack?"
- "Create version 2 from scratch"
Usage: Type /fork — creates a new conversation branch with full history.
Returns a resume command to get back to the original conversation.
Best for: A/B testing approaches, exploring risky changes, version comparison.
Pro tip: Run multiple forks in parallel terminal sessions for simultaneous exploration.
Shield 3: context: fork (Skill Isolation)
Add context: fork to any SKILL.md frontmatter to run heavy skills in an
isolated context window. See the context-fork-guide skill for full details.
When Context Gets Large
Signs your context is bloated:
- Slower responses
- Claude "forgets" earlier decisions
- Suggestions become less relevant
Recovery:
/forkto start fresh with history preserved/compactto summarize and compress context- For future sessions: apply
context: forkto heavy skills proactively
Context Budget Rule of Thumb
- Light session (single file edits, Q&A): 50K-100K tokens, no shields needed
- Medium session (multi-file feature work): 100K-300K tokens, use /by-the-way for side queries
- Heavy session (research + build): 300K+, fork skills and /fork for exploration branches
Source
Extracted from: 3 Claude Code Features You'll Wish You Knew Sooner by Mark Kashef (AI Automation Society), March 19, 2026.
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.