principle-guard-the-context-window

Teaches AI agents to send big outputs to helper agents instead of keeping them in the main conversation, so the main agent stays sharp.

Installation

Run `npx skills add "https://github.com/michael-denyer/pstack-claude" --skill "principle-guard-the-context-window"` to install this skill, then follow its SKILL.md instructions for my next request.

Paste this into Claude Code, Cursor, or any agent that can run commands.

SKILL.mdShow the author's original SKILL.md

---
name: principle-guard-the-context-window
description: "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."
user-invocable: false
---

# Guard the Context Window

**Why:** Context overflow degrades reasoning quality, creates compression artifacts, and halts progress.

**Pattern:**
- **Size phases and cap scope.** Limit files per phase, set turn budgets, account for mechanism costs.

Mirrored from the author's public source. Install counts from the open skills registry.