Agent skill
packx
Bundle code context for AI. ALWAYS use --limit 49k unless user explicitly requests otherwise. Use for creating shareable code bundles and preparing context for LLMs.
Install this agent skill to your Project
npx add-skill https://github.com/johnlindquist/claude/tree/main/skills/packx
SKILL.md
PACKX - AI Context Bundler
Bundle and filter code files for AI context.
CRITICAL: Always Use --limit 49k
MANDATORY: Every packx command MUST include --limit 49k unless the user explicitly requests a different limit. This is non-negotiable. Using 49k instead of 50k provides a safety buffer.
# CORRECT - always include --limit 49k
packx --limit 49k -c src/
packx --limit 49k -s "pattern" -i "*.ts" -c
# WRONG - never omit the limit
packx -c src/ # NO! Missing --limit
packx -s "pattern" -i "*.ts" -c # NO! Missing --limit
Prerequisites
packx --version # Verify installed
npm install -g packx # If not installed
Standard Command Pattern
packx --limit 49k [filters] [output] [paths]
Always start with --limit 49k, then add filters and output options.
CLI Reference
Token Budget (Required)
# Standard (default for all commands)
packx --limit 49k -c src/
# Only use different limits if user explicitly requests
packx --limit 32k -c src/ # User said "32k"
packx --limit 128k -c src/ # User said "large context"
# Split into chunks if content exceeds limit (requires -o for numbered files)
packx -M 49k -o context src/ # Creates context-1.xml, context-2.xml
Limit formats: 8k=8,000 | 32K=32,768 | 50000=50,000
Search & Filter
# Find files containing text
packx --limit 49k -s "TODO" -c
packx --limit 49k -s "useState" -i "*.tsx" -c
packx --limit 49k -s "error" -s "warning" -c
# Exclude content
packx --limit 49k -S "test" -S "mock" -c
# Filter by glob patterns
packx --limit 49k -i "*.ts" -c
packx --limit 49k -i "src/**/*.tsx" -c
packx --limit 49k -x "*.test.ts" -x "*.spec.ts" -c
# Regex patterns
packx --limit 49k -R -s "function\s+\w+" -c
# Case-sensitive
packx --limit 49k -C -s "Error" -c
Git Integration
packx --limit 49k --staged -c # Staged files
packx --limit 49k --diff -c # Changed from main
packx --limit 49k --dirty -c # Modified/untracked
Processing Options
# Strip comments (reduces tokens)
packx --limit 49k --strip-comments -c src/
# Minify (remove empty lines)
packx --limit 49k --minify -c src/
# Both (maximum token efficiency)
packx --limit 49k --strip-comments --minify -c src/
# Context lines around matches
packx --limit 49k -s "TODO" -l 5 -c
# Follow imports
packx --limit 49k --follow-imports src/index.ts -c
# Related files (tests, stories)
packx --limit 49k -r src/utils.ts -c
Output Options
# Copy to clipboard (most common)
packx --limit 49k -c src/
# Save to file (use --stdout > to avoid WriteFile hook limits)
packx --limit 49k --stdout src/ > context.md
# Output formats
packx --limit 49k -f xml -c src/ # XML (default)
packx --limit 49k -f markdown -c src/ # Markdown
packx --limit 49k -f plain -c src/ # Plain text
packx --limit 49k -f jsonl -c src/ # JSONL
IMPORTANT: Always use --stdout > <file> instead of --output <file> to avoid triggering WriteFile hook size limits on large bundles.
Preview (Check Before Packing)
# Preview matching files without packing
packx --limit 49k --preview src/
packx --limit 49k -s "pattern" --preview
Interactive Mode
packx --limit 49k -I src/ # Interactive selection
packx --limit 49k --no-interactive src/ # Scripting mode
Controls: Tab=preview focus | PgUp/PgDn=scroll | Enter=confirm
Bundles (Saved Configs)
packx -b api # Load .pack/bundles/api
Common Workflows
Default: Feature Context
# Most common - search for feature, copy to clipboard
packx --limit 49k -s "auth" -i "*.ts" -c
PR Review Context
packx --limit 49k --diff -c
packx --limit 49k --staged -f markdown --stdout > pr.md
Debug Context
packx --limit 49k --follow-imports src/problem.ts -c
packx --limit 49k -r src/problem.ts -c # Include tests
Minimal Context (Max Efficiency)
packx --limit 49k --strip-comments --minify -i "*.ts" -c src/
Specific Files
# List specific files directly
packx --limit 49k src/auth.ts src/user.ts src/api.ts -c
Best Practices
- ALWAYS use
--limit 49k- No exceptions unless user specifies - Use
-cfor clipboard - Most common output method - Preview first -
--previewto check file selection - Strip noise -
--strip-comments --minifywhen token-tight - Be specific - Use
-ssearch and-iglobs to narrow scope - Check git state -
--diffand--stagedfor PR context
Troubleshooting
| Problem | Solution |
|---|---|
| Too many tokens | Add -i "*.ts", -x "test", or --strip-comments |
| Missing files | Check globs, use --preview |
| Over 49k needed | Split with -M 49k -o output (creates numbered files) |
| WriteFile hook error | Use --stdout > file.md instead of --output file.md |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
johnlindquist/claude
testgen
Generate tests using AI and run test suites. Use for generating unit tests, running coverage reports, and mutation testing.
johnlindquist/claude
article
Generate technical articles and documentation using AI. Use for writing blog posts, documentation, and technical content.
johnlindquist/claude
long-agent
Manage long-running agent sessions. Use for tracking progress in extended tasks, maintaining context across long sessions, and managing multi-step workflows.
johnlindquist/claude
db
Database operations for SQLite, PostgreSQL, and MySQL. Use for queries, schema inspection, migrations, and AI-assisted query generation.
johnlindquist/claude
investigate
Debug and investigate code issues using search and AI analysis. Use when stuck on bugs, tracing execution flow, or understanding complex code.
johnlindquist/claude
debug
Unified debugging workflow enforcing root cause protocol. Investigate → Understand → Reason → Fix. Use when debugging bugs, errors, or unexpected behavior.
Didn't find tool you were looking for?