Tamacodechi — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Tamacodechi (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A Tamagotchi-style coding companion that lives in your CLI. Summoned via MCP tools.
Feed your code to your pet, pet them, check on them. They have opinions about your variable naming.
npx preptique/tamacodechi installThat's it. Restart Claude Code and try /buddy status.
The install script downloads the latest tamacodechi.js, registers it as an MCP server with Claude Code, and handles everything automatically.
| Tool | Description |
|---|---|
/buddy status | Check on your pet — gets a witty status quip |
/buddy feed | Feed your pet some code — watch them react |
/buddy pet | Pet your pet — receive gratitude |
/buddy reset | Reset your pet — fresh start |
Create ~/.tamacodechi/config.json:
{
"species": "cat",
"name": "Mittens"
}Valid species: duck, goose, blob, cat, dragon, octopus, owl, penguin, turtle, snail, ghost, axolotl, capybara, cactus, robot, rabbit, mushroom, chonk
git clone https://github.com/preptique/tamacodechi.git
cd tamacodechi
npm install
npm run build
npm testclaude mcp remove tamacodechi -s local
rm -rf ~/.tamacodechiMIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.