All skills
cursor avatar

/principle-guard-the-context-window

@b0b9c7a
by cursorcursor/plugins9.1k stars
857

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.

Use this Skill: https://skilld.dev/gh/cursor/plugins/principle-guard-the-context-window

This session only. Nothing lands on disk.

SKILL.md

≈52 tokens always: the name and description. ≈168 when used: this file.

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.
  • 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.

Source: SKILL.md on GitHub

No alerts7d3 checks · Risk SAFE
  • Gen Agent Trust Hub7d

    This skill provides purely instructional principles for managing the context window. It contains no executable code, tool definitions, or security risks.

  • Socket7d

    No alerts

  • Snyk7d

    Risk: LOW · No issues

Signed by skilld at b0b9c7a. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated last week
disable-model-invocation
true

README badge

README badge for cursor/plugins/principle-guard-the-context-window