principle-guard-the-context-window

어떤 스킬인가요?

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.

설치 방법

프로젝트 폴더에서 아래 명령어를 실행하고, 설치할 에이전트를 선택하세요.

설치 명령을 직접 실행해야 적용됩니다. 지원 에이전트와 필요한 권한·라이선스는 제작자의 안내를 확인하세요.

스킬 원문 파일

# Runtime pointer

Before any multi-agent step, read the sibling **pstack** skill:

1. `pstack/references/capability-contract.md`
2. The matching adapter under `pstack/references/adapters/` for the active host (`claude-code`, `codex`, `droid`, `opencode`, `cursor`, or `generic`).

Map capability verbs through that adapter. Do not invent tool parameters from another host. If spawning is unavailable, execute on the lead agent and say so.

---
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."
license: MIT
compatibility: Works with Agent Skills-compatible coding agents. Multi-agent optional; see pstack adapters.
---

# Guard the Context Window

## Portability (required)

This skill is part of the portable **pstack** pack.

1. Read the `pstack` capability contract and the adapter for the active coding agent before any helper delegation.
2. Prefer capability verbs (`explore`, `implement`, `review`, `parallel`, `ask_user`, `verify`, `model_role`) over vendor tool names.
3. Resolve models through `model_role`. Never require a vendor-specific model identifier.
4. When helper spawning is unavailable, run the work on the lead agent and state that fan-out was collapsed.

The context window is finite and non-renewable within a session. Every token that enters should earn its place.

**Why:** Context overflow degrades reasoning quality, creates compression artifacts, and halts progress. Unlike compute or time, context spent inside a session cannot be reclaimed.

**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.