Context Engineering
A practical guide for keeping LLM agents from choking on their own context windows. You get concrete strategies for the four main escape hatches: write externally, select what matters, compress aggressively, or isolate across sub-agents. The metrics are helpful (start compacting at 70% token utilization, aim for 50-70% reduction). What's refreshing is the focus on token efficiency as a first-class concern rather than an afterthought. The anti-patterns section alone will save you from common mistakes like burying critical information in the middle where attention drops off. Best used when you're building agent systems that need to stay coherent across long sessions or coordinate multiple agents without blowing your token budget.
- skills.sh installs
- 199
- GitHub stars
- 22
- last updated
- Aug 21, 2026
Install
$ npx -y skills add siviter-xyz/dot-agent --skill context-engineering --agent claude-codeInstalls into .claude/skills of the current project.
Files
Context Engineering
Context engineering curates the smallest high-signal token set for LLM tasks. The goal: maximize reasoning quality while minimizing token usage.
When to Activate
- Designing/debugging agent systems
- Context limits constrain performance
- Optimizing cost/latency
- Building multi-agent coordination
- Implementing memory systems
- Evaluating agent performance
- Developing LLM-powered pipelines
Core Principles
- Context quality > quantity - High-signal tokens beat exhaustive content
- Attention is finite - U-shaped curve favors beginning/end positions
- Progressive disclosure - Load information just-in-time
- Isolation prevents degradation - Partition work across sub-agents
- Measure before optimizing - Know your baseline
Key Metrics
- Token utilization: Warning at 70%, trigger optimization at 80%
- Token variance: Explains 80% of agent performance variance
- Multi-agent cost: ~15x single agent baseline
- Compaction target: 50-70% reduction, <5% quality loss
- Cache hit target: 70%+ for stable workloads
Four-Bucket Strategy
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/siviter-xyz/dot-agent
- Categories
- AI & Agent Building, Debugging, Design & UI/UX
- First seen
- Jun 3, 2026
More from siviter-xyz/dot-agent
All 11Recommended
More AI & Agent Building
component-interface-designqodex-ai/ai-agent-skillsDesign interfaces using component libraries and design systems. Creates cohesive UIs with pre-built accessible component primitives.182skills.sh installs
browse-and-evaluatemoizibnyousaf/ai-agent-skillsIf you've ever installed a skill and immediately regretted the context window explosion, this is your guardrail.177skills.sh installs
