Skip to main content
command CX Codex

open-source — Claude Code command: find a library before you build

Finds existing open-source libraries and tools for the problem at hand, checks whether they are still maintained, and says whether to use one or build your own.

MIT ★ 1,988 updated 2026-04-01

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add glittercowboy/taches-cc-resources
/plugin install taches-cc-resources@taches-cc-resources
Open on GitHub

What open-source does

The command opens with a short round of questions: language and framework, license needs, how much maintenance matters, what the pick has to plug into. It only asks about gaps your request left. Then you choose: search now, answer more questions, or add context yourself.

The search does not stop at the first hit. Every candidate gets its repo checked for the last commit date, how quickly issues get answered, and how many people contribute. A project where one person makes every commit, or where issues sit unanswered, is flagged. License compatibility is checked on its own. What comes back is a comparison table and a plain build-versus-use call.

Results land in artifacts/research/ as YYYY-MM-DD-[topic]-open-source.md, and the reply points at that file. Leave the argument empty and the command works from whatever you have open.

What it helps with

  • find a maintained library instead of writing your own
  • spot an abandoned project before it becomes a dependency
  • filter out candidates with the wrong license
  • compare three options side by side
  • keep the research in artifacts/research/ for later

Example prompts for the agent

  • /open-source I need a Python library for PDF parsing, MIT or Apache only
  • /open-source what could replace our hand-rolled job queue in Go
  • /open-source with no argument, work from the task I have open

How to install open-source

1Plugin marketplace

/plugin marketplace add glittercowboy/taches-cc-resources
/plugin install taches-cc-resources@taches-cc-resources

2Manually: put the files in place

.claude/commands/open-source.md

Call it with /open-source. For all projects use ~/.claude/commands/

Questions about open-source

How do I install open-source in Claude Code?

From the plugin marketplace: run /plugin marketplace add glittercowboy/taches-cc-resources, then /plugin install taches-cc-resources@taches-cc-resources.

What does the open-source command do?

It hunts down open-source libraries and tools that fit your problem, checks license and maintenance health, and returns a comparison table plus a use-it-or-build-it recommendation.

Can I run it without an argument?

Yes. With no argument it works from the task currently in context. The report still goes to artifacts/research/ as YYYY-MM-DD-[topic]-open-source.md.

Source text

open-source.md · MIT
---
description: Find open-source solutions - libraries, tools, projects that solve this
argument-hint: [problem/need or leave blank for current context]
---

<objective>
Find open-source solutions for $ARGUMENTS (or the current topic if no arguments provided).

Search for existing libraries, tools, and projects that solve the problem. Don't build what already exists.
</objective>

<intake_gate>

<context_analysis>
First, analyze $ARGUMENTS to extract what's already provided:
- What problem needs solving
- Language/framework requirements
- License requirements
- Integration constraints

Only ask about genuine gaps - don't re-ask what's already stated.
</context_analysis>

<initial_questions>
Use AskUserQuestion to ask 2-4 questions based on actual gaps:

**If language unclear:**
- "What language/framework?" with options: Python, JavaScript/Node, Swift, Go, Rust, Language agnostic, Other

**If license unclear:**
- "License requirements?" with options: Any open source, Permissive only (MIT/Apache), GPL OK, Commercial use required, Other

**If maintenance unclear:**
- "How important is maintenance?" with options: Must be actively maintained, Recent activity OK, Abandoned OK if it works, Other

**If integration unclear:**
- "Must integrate with?" with options: Nothing specific, Existing codebase, Specific framework, Other

Skip questions where $ARGUMENTS already provides the answer.
</initial_questions>

<decision_gate>
After receiving answers, use AskUserQuestion:

Question: "Ready to search for open-source solutions, or would you like me to ask more questions?"

Options:
1. **Start search** - I have enough context
2. **Ask more questions** - There are details to clarify
3. **Let me add context** - I want to provide additional information

If "Ask more questions" → generate 2-3 contextual follow-ups, then present decision gate again
If "Let me add context" → receive input, then present decision gate again
If "Start search" → proceed to research
</decision_gate>

</intake_gate>

<process>
After intake complete:

1. Define what we need (problem, requirements, constraints)
2. Search for open-source options
3. Evaluate each option
4. Verify maintenance status for each option:
   - Check last commit date (not just "last updated" on package registry)
   - Check issue response time (open recent issue, see if maintainers respond)
   - Check contributor count and bus factor (is it one person or a team?)
   - Flag if: last commit >1 year OR all commits from 1 person OR issues go unanswered
5. Assess build vs. use tradeoffs
6. Recommend best option or confirm need to build
</process>

<output_format>
## Open Source Research: [Need]

### Strategic Summary
[2-3 sentences: what's available, recommendation, key consideration]

### What we need
[Problem to solve, key requirements]

### License requirements
[MIT/Apache/GPL-compatible/etc.]

### Options Found

**[Option 1: package-name]**
- **Repo:** [GitHub URL]
- **What it does:** [Brief description]
- **Stars/Downloads:** [Popularity indicators]
- **Last commit:** [Date - from repo, not registry]
- **Contributors:** [Count - note if 1-person project]
- **Issue response:** [Active/Slow/Inactive - check recent issues]
- **License:** [License type]
- **Fits our need:** [Yes/Partial/No] - [why]
- **Concerns:** [Issues, gaps, risks]

**[Option 2: package-name]**
[Same structure...]

**[Option 3: package-name]**
[Same structure...]

### Comparison
| Aspect | Option 1 | Option 2 | Option 3 |
|--------|----------|----------|----------|
| Solves problem | Y/Partial/N | | |
| Maintained | Y/N | | |
| License OK | Y/N | | |
| Easy to integrate | Y/N | | |

### Build vs. Use Analysis
**Use existing:**
- Pros: [Proven solution, community support, faster start]
- Cons: [Less control, potential bloat, dependency risk]

**Build custom:**
- Pros: [Exact fit, full control, no dependencies]
- Cons: [Complexity to build, maintenance burden]

**Recommendation:**
[Use Option X / Build custom] because [reasoning]

### Implementation Context
<claude_context>
<if_use>
- package: [exact package name and version]
- install: [installation command]
- docs: [documentation URL]
- examples: [example code or reference]
- gotchas: [known issues, quirks, workarounds]
</if_use>
<if_build>
- scope: [what to build]
- approach: [technical approach]
- reference: [can use Option X as reference for patterns]
- complexity: [S/M/L]
</if_build>
<integration>
- imports: [how to import/require]
- patterns: [usage patterns]
- testing: [how to test integration]
</integration>
</claude_context>

**Next Action:** Prototype with chosen library, evaluate deeper, or spec out custom build

### Sources
- [Source name/package]: [URL] - [date accessed]
- [Source name/package]: [URL] - [date accessed]
</output_format>

<artifact_output>
Save the research to a file:

1. Create directory structure if it doesn't exist:
   - `[current-working-directory]/artifacts/research/`

2. Generate filename from topic:
   - Get current date in YYYY-MM-DD format
   - Slugify the topic (lowercase, hyphens for spaces)
   - Format: `YYYY-MM-DD-[topic]-open-source.md`
   - Example: `2025-01-15-midi-libraries-open-source.md`

3. Write the complete research to the file

4. Report to user: "Saved to `artifacts/research/[filename]`"
</artifact_output>

<success_criteria>
- Search is thorough (not just first result)
- Maintenance status is verified (not abandoned)
- License compatibility is checked
- Build vs. use tradeoff is honest
- Implementation context has exact package info Claude needs
- Recommendation saves complexity without creating technical debt
- Output saved to artifacts/research/ directory
</success_criteria>

© Lex Christopherson · MIT · glittercowboy/taches-cc-resources

Similar slash commands

All slash commands for Agent setup: memory, context, orchestration →
open-source-company-strategy Samuel Berthe open-source-company-strategy — a skill that walks a company through deciding which assets ship under an open license and which stay closed. Useful when the question is framed as one big yes or no. CX Codex +1 13,800installs open-source-librarian jarrodwatts The open-source-librarian subagent investigates open-source libraries and codebases, tracing implementations and linking to exact GitHub lines. Use it for source-level and change-history questions. CX Codex ★ 1,064repo stars Open Source Release Checklist Builder (YAML) f Open Source Release Checklist Builder (YAML) is a ChatGPT and Claude.ai prompt that turns an open-source release plan into a YAML checklist for versions, tests, artifacts, security, and announcements. GP ChatGPT ★ 178,201repo stars open-source-marketing jonathimer open-source-marketing is a Claude Code skill for planning open-source promotion through GitHub and community work, and clarifying the contributor path. It requires an audience context file before starting. CX Codex +1 ★ 88repo stars open-images-for-free-use peter-duffy95 open-images-for-free-use — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode that finds images with verified free licenses. Triggers on phrases like 'find an image', 'need a banner photo', 'get a picture for'. CX Codex +1 1,400installs dependency-license-checker official github dependency-license-checker — a GitHub Copilot hook that scans newly added dependencies at session end and flags copyleft licenses before they get committed. ★ 41,430repo stars

From the same set48

The whole set →
feasibility feasibility is a command that assesses whether a project can meet its constraints and recommends whether to proceed, revise terms, or stop. CX Codex +1 ★ 1,988repo stars landscape Maps a domain landscape: identifies key players, available tools, trends and gaps. Takes a domain name or works in current context without arguments. CX Codex +1 ★ 1,988repo stars build-iphone-apps build-iphone-apps builds native iPhone apps in Swift using SwiftUI and UIKit via terminal commands without opening the Xcode IDE. Handles everything from code to App Store shipping. CX Codex +1 ★ 1,988repo stars run-prompt This command sends prompts from ./prompts/ to fresh sub-task contexts, one at a time or in parallel. Use it to run independent work concurrently or keep dependent tasks in order. CX Codex +1 ★ 1,988repo stars create-mcp-servers create-mcp-servers guides development of Model Context Protocol servers in Python and TypeScript for Claude Code, covering architecture, secrets isolation, and debugging. CX Codex +1 ★ 1,988repo stars slash-command-auditor slash-command-auditor audits Claude Code slash-command .md files for structure, arguments, context loading, tool scope, and security issues. CX Codex ★ 1,988repo stars create-hooks The create-hooks skill explains how Claude Code hooks work and gives ready configs for blocking dangerous commands, logging, and auto-formatting. CX Codex +1 ★ 1,988repo stars subagent-auditor subagent-auditor audits Claude Code subagent configurations against structured best practices. Catches malformed XML, unneeded tool permissions, and weak boundary constraints. CX Codex ★ 1,988repo stars

Project sponsors

Companies that keep this analytics open