rohitg00/compact-guard
skills/compact-guard/SKILL.md
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.
$ install --global
skillsauthnpx skillsauth add rohitg00/pro-workflow compact-guardInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 18, 2026, 5:37 AM54.7s1 file scanned
SKILL.md
- 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.
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 survivePOST_COMPACT_TOKEN_BUDGET = 50K— total restore budgetPOST_COMPACT_MAX_TOKENS_PER_FILE = 5K— per-file limit- Auto-compact fires at
context_window - 13Kbuffer
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
| 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
Related Skills
rohitg00/skill-optimizer
devops
VerifiedTrustedCommunity
SkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably improve the score. Inspired by Microsoft SkillOpt's ReflACT pipeline (rollout → reflect → aggregate → select → update → evaluate) adapted to pro-workflow's SQLite store. Use when a skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better, not just longer.
2,270SKILL.mdUpdated Jun 4, 2026
rohitg00/safe-mode
tools
VerifiedTrustedCommunity
Prevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict edits to one directory), and clear (remove restrictions). Uses PreToolUse matchers for Bash, Edit, and Write.
2,245SKILL.mdUpdated Apr 27, 2026
rohitg00/pro-workflow
development
VerifiedTrustedCommunity
Complete AI coding workflow system. Orchestration patterns, 18 hook events, 5 agents, cross-agent support, reference guides, and searchable learnings. Works with Claude Code, Cursor, and 32+ agents.
2,245SKILL.mdUpdated Apr 27, 2026
rohitg00/permission-tuner
data-ai
VerifiedTrustedCommunity
Analyze permission denial patterns and generate optimized alwaysAllow and alwaysDeny rules. Use when permission prompts are slowing you down or after sessions with many denials.
2,245SKILL.mdUpdated Apr 27, 2026