principle-guard-the-context-window

Featured

Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.

AI & Automation 333 stars 40 forks Updated 2 days ago MIT

Install

View on GitHub

Quality Score: 91/100

Stars 20%
84
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
40
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Guard the Context Window The context window is finite and non-renewable within a session. Every token should be worth its cost. **Why:** Context overflow degrades reasoning quality, creates compression artifacts, and halts progress. **Pattern:** - **Isolate large payloads.** Route verbose outputs, screenshots, and large documents to subagents. The main context gets summaries, not raw data. - **Don't read what you won't use.** Read selectively based on relevance. If a file isn't needed for the current task, skip it. - **Keep frequently used content inline.** Templates and references used on every invocation belong in the skill file, not in separate files that cost a read each time. - **Size phases and cap scope.** Limit files per phase, set turn budgets, account for mechanism costs.

Details

Author
michael-denyer
Repository
michael-denyer/pstack-claude
Created
3 months ago
Last Updated
2 days ago
Language
TypeScript
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category