JuliusBrussee/cavekit

COLLECTIONcommunity
JuliusBrusseeMITUpdated 3mo agoGitHub

A Claude Code plugin that turns natural language into blueprints, blueprints into parallel build plans, and build plans into working software with automated iteration, validation, and cross-model peer review.

compressed spec-driven development for claude code one file · three commands · zero sub-agents Plan-then-execute forgets. SDD remembers — but most SDD frameworks bury that value under agent swarms, dashboards, and ceremony that costs more tokens than it saves. Cavekit 4 is a rewrite from the ground up. It keeps only what earns its durable spec — at repo root survives context resets. caveman…

This collection bundles
5 skills3 commands

⚠ The trust score below reflects the collection's repository only. The bundled units are not individually verified or scanned — review them before use.

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
1kGitHub stars
71Forks
3mo agoLast update
Package
AuthorJuliusBrussee
LicenseMIT
Sourcegithub
Trust Status
B
60/100Good
Listed in Forge index+10/10
Publisher identity verified+0/30
Publisher: run `forge publish` from the repo to claim ownership
Domain verification+0/10
Not currently available for this listing type — the domain-verification check only runs for npm-backed packages today, so this row cannot be earned here yet regardless of what's hosted at the domain.
Prompt-injection scan · clean+30/30
Obfuscation / exfil scan · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain
Provenance
DependenciesNot audited
Tool surface
Security scan✓ CleanvHEAD · 2mo ago
EvalsNone
IndexedJun 14, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts — it cannot prove the absence of malicious code.

About

compressed spec-driven development for claude code one file · three commands · zero sub-agents Plan-then-execute forgets. SDD remembers — but most SDD frameworks bury that value under agent swarms, dashboards, and ceremony that costs more tokens than it saves. Cavekit 4 is a rewrite from the ground up. It keeps only what earns its durable spec — at repo root survives context resets. caveman encoding — ~75% fewer tokens than prose. Symbols, fragments, pipe tables for repeating records. backprop…

Keywords
claude-codeparallel-agentsskillsspec-driven-developmenttest-driven-developmentcollection