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.
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 Nothing lands on disk. Nothing to clean up.
Edit a local copy. It keeps the author and licence.
≈52 tokens for metadata: the name and description. ≈63 when used: this file.
Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.
This Skill turns off automatic use in Claude Code. Its description stays out of the automatic Skill list by default.
The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.
Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.
Why: Context overflow degrades reasoning quality, creates compression artifacts, and halts progress.
Pattern:
Source: SKILL.md on GitHub
No rule matched.
skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.
skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.
This skill provides architectural guidelines for managing the agent's context window. It contains no executable code or security risks.
No alerts
Risk: LOW · No issues
Signed by skilld at 0b46ec3. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.
Last checked against GitHub yesterday.