Developer Tools●Mid
Zsh helpers for LLM Git diff review
Zsh wrapper around existing LLM APIs; Claude Code and Copilot already do diff review.
Ship It
ackdesha
103mo ago
Back to browse
GitHub Repository
A CLI for generating LLM-backed metrics for deciding how closely to review code
3 starsTypeScript
FKS2G – LLM-backed metrics for deciding how closely to review code
by kmdupree·May 21, 2026·2 points·0 comments
AI Analysis
●MidShip ItBold Bet
Quantifies review effort with git history and LLMs, but Copilot already scores risk.
Strengths
- •Combines git change frequency with embedding similarity for richer context.
- •Focuses on review effort allocation instead of just bug detection.
- •CLI-first workflow fits into existing terminal-based development habits.
Weaknesses
- •Author admits it's 0.X software not ready for prime-time usage.
- •Risk scoring already exists in Copilot, CodeRabbit, and GitHub Advanced Security.
Category
Target Audience
Engineering leads, senior developers managing large PRs
Similar To
CodeRabbit · GitHub Copilot · Reviewable
Similar Projects
Developer Tools●Mid
Codiff, a local diff review tool
GUI wrapper around git diff with LLM walkthrough, but delta and GitHub already do this.
Ship It
cpojer
31211mo ago
Developer Tools○Pass
Lines of Bash to automate LLM code review and fixes
Bash wrapper around Claude API when CodeRabbit and Cursor already exist.
Ship It
yding
212mo ago
AI/ML●●Solid
Open-source, model-agnostic alternative to Claude Code Review
Model-agnostic code reviews with zero LLM markup beats Claude Code Review on cost.
Solve My ProblemSlick
edvaldodfreitas
403mo ago
Developer Tools●●Solid
Vibe-coded – Rust CLI to discover LLM-assisted Git repositories
Handy CLI that actually pulls a repo and runs a battery of concrete heuristics — repo age, README keywords/emoji counts, commit velocity, presence of LLM-tool files, and simple commit-statistics — to guess whether code was prompt-expanded. The rule set is intentionally arbitrary and extensible, which makes this a useful starting point for audits or CI checks, but expect false positives and plan to tune or add rules for your context.
Niche GemShip It
xlii
104mo ago
Developer Tools●Mid
Night Watch, zero-dependency DevOps agent
LLM agent chains cloud CLIs and git logs, but needs runbook guardrails to avoid catastrophic mistakes.
Bold Bet
sudoapps
203mo ago