compact-guard skill

by rohitg00·rohitg00/pro-workflow·2.9k stars

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.

A100/100content scan

Is the compact-guard skill safe?

Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-09-28.

No findings.

Install the compact-guard skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.

git clone --depth 1 https://github.com/rohitg00/pro-workflow.git /tmp/pro-workflow
mkdir -p ~/.claude/skills
cp -r /tmp/pro-workflow/skills/compact-guard ~/.claude/skills/compact-guard

available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

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)

POSTCOMPACTMAXFILESTO_RESTORE = 5 — only 5 files survive
POSTCOMPACTTOKEN_BUDGET = 50K — total restore budget
POSTCOMPACTMAXTOKENSPER_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:

Current task — What are you working on? One sentence.
Files in progress — Which files are being edited? (max 5 — compaction only restores 5)
Decisions made — Any architectural choices made this session
Blockers — What's preventing progress?
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:

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

Prevention Strategies

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

More skills from rohitg00/pro-workflow

Aagent-teamsCoordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.
Aauto-setupAuto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.
Abatch-orchestrationDecompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.
Cbug-captureCapture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue. Use when the user reports a bug conversationally, runs a QA pass, or says "file an issue", "log this as a bug", "capture this".
Acontext-engineeringMaster the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.
Acontext-optimizerOptimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.
Acost-trackerTrack session costs, set budget alerts, and optimize token spend. Use to check costs mid-session or set spending limits.
Adesign-engineeringApply interface craft when building or reviewing UI - motion, easing, timing, springs, component feel, and visual foundations. Use when building a component, animation, transition, hover or press state, modal, drawer, toast, or when polishing an interface so it feels right. Says "make this feel better", "add an animation", "polish the UI", "review this component".
AdeslopRemove AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff. Cleans up boilerplate, simplifies abstractions, strips defensive code, and in skill-file mode lints SKILL.md files for quality. Use when cleaning up code, simplifying, removing boilerplate, before committing, or when reviewing a skill before promoting it.
Adomain-modelingBuild the project's shared language and bounded contexts before writing code, so names stay consistent and the agent stops paraphrasing domain concepts. Produces a CONTEXT.md glossary and decision records. Use at the start of a project or feature, or when the codebase and the people describing it speak different languages.
Afile-watcherConfigure file watching hooks to auto-react to config changes, env file updates, and dependency modifications. Use to set up reactive workflows.
Aimprove-architectureAudit an area of the codebase and propose the smallest structural moves that improve it - untangle boundaries, kill duplication, fix seams, break cycles. Produces a prioritized plan and decision records, not a rewrite. Use when a codebase feels tangled, hard to change, or is becoming a ball of mud, or when asked to improve or refactor architecture.

All agent skills → · MCP servers