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.
- Installs
- 64
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/johnlindquist/claude --skill packx- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads packx automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
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 |
FAQ
What does the packx skill do?
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.
How do I install packx?
Run npx skills add https://github.com/johnlindquist/claude --skill packx in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/packx/ (personal) or .claude/skills/packx/ (project).
Which AI agents can use packx?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is packx safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains packx?
It is published by johnlindquist in johnlindquist/claude. It has 64 recorded installs.
More from johnlindquist/claude
gemini-image
johnlindquist/claude
Analyze images using Gemini's vision capabilities. Use for image analysis, text extraction from screenshots, and visual content understanding.
memory
johnlindquist/claude
Persistent knowledge storage using basic-memory CLI. Use to save notes, search memories semantically, and build context for topics across sessions.
brainstorm
johnlindquist/claude
Generate ideas and explore possibilities with AI. Use for creative problem solving, generating alternatives, and expanding on concepts.
deepwiki
johnlindquist/claude
Query DeepWiki for repository documentation and structure. Use to understand open source projects, find API docs, and explore codebases.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available