Skip to content
FunCoding

Search

Search docs, Skills and MCP

compact-guard

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.

AI 与智能体2.9kskills/compact-guard/SKILL.md

Install

Send this to Claude Code, Codex or Cursor. The agent checks the Skill for safety first and installs it only after you confirm.

读取 https://funcoding.ai/skills/rohitg00/pro-workflow/compact-guard/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.md

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

StrategyToken SavingsWhen
Delegate grep/search to subagent30-60% per searchAlways for broad searches
Read only needed lines (offset/limit)50-90% per readLarge files
Compact at task boundariesPreserves coherenceBetween logical steps
Use /resume for fresh start100%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

Similar Skills

brand-guidelines
anthropics/skills180k

brand-guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

AI & agents

internal-comms
anthropics/skills180k

internal-comms

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

AI & agents

template-skill
anthropics/skills180k

template-skill

Replace with description of the skill and when Claude should use it.

AI & agents

mcp-builder
anthropics/skills180k

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

AI & agents

algorithmic-art
anthropics/skills180k

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

AI & agents

academy-guide
anthropics/skills180k

academy-guide

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

AI & agents