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
delegate_task workers. 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.
This repository (Asymmetric-al/core)
Vendored from p3-stack (MIT) at commit 09909eb. Provenance is in references/upstream.md. On conflict, the current user request, root AGENTS.md, the nearest nested AGENTS.md, and the matching docs/ai/rules/* rulebook win over this skill.
- Explicit invocation only: use it when the user invokes
/principle-guard-the-context-window (Claude Code, Cursor, T3 Code) or $principle-guard-the-context-window (Codex), or when an invoked p3-stack skill routes here. Do not route other work to it.
- The T3 Code tools named above map to Claude Code, Codex, and Cursor in
docs/ai/skills/p3-mode/references/core-adapter.md. Read it before you delegate, watch a PR, schedule work, or drive a preview outside T3 Code.
- Confirm before outward-facing or hard-to-reverse actions such as pushing, merging, deploying, deleting, or posting messages, unless the user authorized that action for this task.
Edit this canonical copy in docs/ai/skills/principle-guard-the-context-window/, then run bun run skills:sync and bun run skills:verify.
1---2name: principle-guard-the-context-window3description: "Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to delegated tasks; keep summaries in the main thread, not raw payloads."4disable-model-invocation: true5metadata:6 source: https://skillmd.com/skills/asymmetric-al/principle-guard-the-context-window7---89# Guard the Context Window1011The context window is finite and non-renewable within a session. Every token should be worth its cost.1213**Why:** Context overflow degrades reasoning quality, creates compression artifacts, and halts progress.1415**Pattern:**1617- **Isolate large payloads.** Route verbose outputs, screenshots, and large documents to `delegate_task` workers. The main context gets summaries, not raw data.18- **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.19- **Size phases and cap scope.** Limit files per phase, set turn budgets, account for mechanism costs.2021<!-- CORE-OVERLAY-START -->2223## This repository (Asymmetric-al/core)2425Vendored from [p3-stack](https://github.com/uzairansaruzi/p3-stack) (MIT) at commit `09909eb`. Provenance is in `references/upstream.md`. On conflict, the current user request, root `AGENTS.md`, the nearest nested `AGENTS.md`, and the matching `docs/ai/rules/*` rulebook win over this skill.2627- Explicit invocation only: use it when the user invokes `/principle-guard-the-context-window` (Claude Code, Cursor, T3 Code) or `$principle-guard-the-context-window` (Codex), or when an invoked p3-stack skill routes here. Do not route other work to it.28- The T3 Code tools named above map to Claude Code, Codex, and Cursor in `docs/ai/skills/p3-mode/references/core-adapter.md`. Read it before you delegate, watch a PR, schedule work, or drive a preview outside T3 Code.29- Confirm before outward-facing or hard-to-reverse actions such as pushing, merging, deploying, deleting, or posting messages, unless the user authorized that action for this task.3031Edit this canonical copy in `docs/ai/skills/principle-guard-the-context-window/`, then run `bun run skills:sync` and `bun run skills:verify`.3233<!-- CORE-OVERLAY-END -->