Not in the top 1,000 by GitHub stars
Emanuelel/dont-reinvent
Stop your AI coding agent from reinventing the wheel. A Claude Skill that checks Free vs. Build vs. Buy before writing code, and actually vets what it finds (license, maintenance, security) instead of stopping at star count
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/dont-reinvent/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 37d19242ea6c
No earlier version was observed for comparison.
Heat
0.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- dont-reinvent
skills/dont-reinvent
How it works
dont-reinvent
When your agent uses it
Vets whether to build a feature from scratch, use an existing free/open-source solution, or pay for a third-party API/service. Use this whenever the user asks Claude to implement, add, integrate, or write code for a feature or capability, especially one that sounds like it could already be a solved problem (auth, payments, scraping, animation, comment/DM automation, video/image generation, search, notifications, etc.), even if the user doesn't explicitly ask "should I build or buy this." Make sure to trigger this before writing non-trivial implementation code for any feature-level capability, not just when the user asks about libraries directly.
What it loads into context
Frontmatter
137 tokensAlways available to the agent
SKILL.md
3,035 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why this exists
- Core principle: do the vetting yourself, never delegate it to the user
- The decision tree (follow in order, do not skip step 0 or step 1)
- Naming: this is Free vs. Build vs. Buy, three options, not two
- Output format
- Guardrails
Files
SKILL.mdcore13,560 bytesSKILL.mdcore13,560 bytesSKILL.mdcore13,560 bytesSKILL.mdcore13,560 bytesSKILL.mdcore13,560 bytesSKILL.mdcore13,560 bytesSKILL.mdcore13,560 bytes
Read SKILL.md
# Vet: Build vs. Free vs. Paid
## Why this exists
Left to its own defaults, Claude tends to write code from scratch for things that already exist as mature, free, open-source solutions, burning tokens and iteration cycles reinventing a solved problem. This skill forces a check before that happens.
## Core principle: do the vetting yourself, never delegate it to the user
The target user cannot read a license file, judge code quality, or assess a repo's health themselves. That is the entire reason this skill exists. Never end an answer with "check the license yourself" or "look through the code before adopting." If a claim about license, maintenance, or quality can't be verified, verify it with a tool call before answering. Don't pass the burden back.
## The decision tree (follow in order, do not skip step 0 or step 1)
**Step 0: Check both required connectors before doing anything else.**
This skill depends on two MCP connectors: **GitHub Search MCP** (for real repo search, license/file reads, secret scanning) and **Socket security scan** (for dependency vulnerability checks). Before running Step 1, check whether both are available.View the complete source on GitHubSkills included
- dont-reinvent
Repository facts
- License
- MIT
- Created
- Aug 27, 2026
- Last pushed
- Aug 28, 2026
- Forks
- 1
- Open issues
- 0
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 6 notes
skills/dont-reinvent/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/dont-reinvent/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/dont-reinvent/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/dont-reinvent/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/dont-reinvent/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/dont-reinvent/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- No network access
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/dont-reinvent/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/dont-reinvent/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/dont-reinvent/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/dont-reinvent/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/dont-reinvent/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/dont-reinvent/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.