一键导入
strategic-compact
Context compaction strategy for long sessions
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Context compaction strategy for long sessions
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Demo pipeline state machine — 7-phase autonomous sequence with delegation context templates, phase transition logic, BLOCKED recovery strategies, and demo-state.json schema. Used exclusively by demo-conductor.
Cinematic narration style guide for demo-conductor — ANSI-coloured banner formats, live pipeline scoreboard, audience-facing language, phase summaries, and error narration patterns. Keeps the demo presentation-quality throughout.
Standardized completion and escalation protocol for subagent responses. Ensures the conductor can machine-parse every subagent return. Use when reporting completion status back to the orchestrator.
Cross-session learnings lifecycle — schema, storage, retrieval, and pruning of lessons learned during orchestrator sessions. Use when managing learnings via the /learn command.
Agent Teams assembly and task injection — selects appropriate team, validates prerequisites, estimates cost, injects tasks into the shared task list, and manages team lifecycle.
Token and cost tracking with model tier enforcement
| name | strategic-compact |
| description | Context compaction strategy for long sessions |
| argument-hint | <current-session-state> |
| user-invocable | false |
/clear or major topic shiftBefore running /compact, ensure:
artifacts/memory/activeContext.mdartifacts/plans/The PreCompact hook (hooks/scripts/pre-compact.js) handles this automatically.
When compacting, prioritize retaining:
Deprioritize:
The PostCompact hook restores state from artifacts/memory/activeContext.md. After compaction:
activeContext.md explicitlyCLAUDE_AUTOCOMPACT_PCT_OVERRIDE=50 — Compact earlier (default: 80%).claude/settings.json → env or via CLI