Agent Skillsrohitg00/pro-workflow › compact-guard

compact-guard

GitHub

在上下文压缩前保存关键状态与文件,压缩后恢复,防止信息丢失。提供预检查清单、微压缩策略及防丢失技巧,确保任务连续性。

skills/compact-guard/SKILL.md rohitg00/pro-workflow

Trigger Scenarios

执行 /compact 命令前 触发自动压缩警告时

Install

npx skills add rohitg00/pro-workflow --skill compact-guard -g -y
More Options

Use without installing

npx skills use rohitg00/pro-workflow@compact-guard

指定 Agent (Claude Code)

npx skills add rohitg00/pro-workflow --skill compact-guard -a claude-code -g -y

安装 repo 全部 skill

npx skills add rohitg00/pro-workflow --all -g -y

预览 repo 内 skill

npx skills add rohitg00/pro-workflow --list

SKILL.md

Frontmatter
{
    "name": "compact-guard",
    "description": "Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual compact or when auto-compact triggers.",
    "user-invocable": true
}

Compact Guard

Protect important context through compaction cycles. Based on Claude Code internals: compaction restores max 5 files with 5K tokens each, within a 50K total budget.

Trigger

Use before /compact or when auto-compact warning appears.

Key Constants (from Claude Code source)

  • POST_COMPACT_MAX_FILES_TO_RESTORE = 5 — only 5 files survive
  • POST_COMPACT_TOKEN_BUDGET = 50K — total restore budget
  • POST_COMPACT_MAX_TOKENS_PER_FILE = 5K — per-file limit
  • Auto-compact fires at context_window - 13K buffer

Pre-Compact Checklist

Before compacting, save these to memory or a scratch file:

  1. Current task — What are you working on? One sentence.
  2. Files in progress — Which files are being edited? (max 5 — compaction only restores 5)
  3. Decisions made — Any architectural choices made this session
  4. Blockers — What's preventing progress?
  5. Next steps — What to do immediately after compact

Strategy: Microcompact First

Before full compaction, try microcompact:

  • Large tool results (test output, grep results) can be trimmed
  • File reads that are no longer relevant can be dropped
  • Use subagents for heavy exploration to keep main context clean

Post-Compact Recovery

After compaction, immediately:

  1. Re-read the top-priority file (the one you're actively editing)
  2. Check task list for current progress
  3. Review any scratch notes saved pre-compact
  4. Resume from next steps

Prevention Strategies

Strategy Token Savings When
Delegate grep/search to subagent 30-60% per search Always for broad searches
Read only needed lines (offset/limit) 50-90% per read Large files
Compact at task boundaries Preserves coherence Between logical steps
Use /resume for fresh start 100% Unrelated new task

Output

After running compact-guard:

COMPACT GUARD
  Files to preserve: [list top 5]
  Task state: [one sentence]
  Decisions: [key choices]
  Next step: [immediate action after compact]

  Ready to compact. Run /compact now.

Rules

  • Always save state before compacting — never compact blind
  • Prioritize the file you're actively editing as #1 to restore
  • If auto-compact fires unexpectedly, immediately re-read your working file
  • Keep CLAUDE.md under 60 lines to leave room for actual context

Version History

  • 7f7209d Current 2026-07-24 11:39

Same Skill Collection

skills/agent-teams/SKILL.md
skills/auto-setup/SKILL.md
skills/batch-orchestration/SKILL.md
skills/bug-capture/SKILL.md
skills/context-engineering/SKILL.md
skills/context-optimizer/SKILL.md
skills/cost-tracker/SKILL.md
skills/design-engineering/SKILL.md
skills/deslop/SKILL.md
skills/domain-modeling/SKILL.md
skills/file-watcher/SKILL.md
skills/improve-architecture/SKILL.md
skills/insights/SKILL.md
skills/learn-rule/SKILL.md
skills/llm-council/SKILL.md
skills/llm-gate/SKILL.md
skills/mcp-audit/SKILL.md
skills/orchestrate/SKILL.md
skills/parallel-worktrees/SKILL.md
skills/permission-tuner/SKILL.md
skills/plan-interrogate/SKILL.md
skills/replay-learnings/SKILL.md
skills/safe-mode/SKILL.md
skills/session-handoff/SKILL.md
skills/skill-router/SKILL.md
skills/smart-commit/SKILL.md
skills/sprint-status/SKILL.md
skills/tdd/SKILL.md
skills/thoroughness-scoring/SKILL.md
skills/token-efficiency/SKILL.md
skills/wiki-builder/SKILL.md
skills/wiki-query/SKILL.md
skills/wiki-research-loop/SKILL.md
skills/wiki-viewer/SKILL.md
skills/wrap-up/SKILL.md
skills/writing-guidelines/SKILL.md
skills/pro-workflow/SKILL.md
skills/skill-optimizer/SKILL.md
skills/survey-generator/SKILL.md

Metadata

Files
0
Version
7f7209d
Hash
ac14353e
Indexed
2026-07-24 11:39

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-06 16:24
浙ICP备14020137号-1 $방문자$