ai-nhancement

Anvil — AI skill for Claude Code

AI community

Anvil is a single, self-contained AI coding agent for the terminal.

How to install Anvil

This entry records only its repository, not the path inside it, so there is no exact command to give. Open ai-nhancement/Anvil and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Anvil does

Anvil is a single, self-contained AI coding agent for the terminal. The coder is a real agent — it reads, writes, edits, and runs your project itself (like Claude Code, Cursor, or Aider) — but Anvil wraps it in a disciplined two-gate review workflow so a long vibe-coding session can't quietly drift off the rails.

Alternatives in AI

Repomix — 📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file 22.7k ★
Claude Squad — by smtg-ai - Claude Squad is a terminal app that manages multiple Claude Code, Codex (and other local agents i 6.5k ★
Ante — Ghost in your shell 1.9k ★

README

Anvil

![Anvil logo](anvil_logo.png)

**Forge the Workflow.** *Structure for vibe coding.*

Anvil is a single, self-contained AI coding agent for the terminal. The coder is a **real agent** — it reads, writes, edits, and runs your project itself (like Claude Code, Cursor, or Aider) — but Anvil wraps it in a **disciplined two-gate review workflow** so a long vibe-coding session can't quietly drift off the rails.

What makes Anvil different isn't the coder — everyone has one of those now. It's the **workflow**: at two human gates, two *different model families* review the work — once on the plan, once on each phase's `git diff` — in a sequential **review → fix → re-review** loop. You approve; the coder does the work; a genuine cross-vendor second opinion keeps it honest.

One Rust binary. Model-agnostic. Installs in one line and updates itself.

**Status: Public Beta.** Anvil is feature-complete for its core workflow and installs/updates cleanly — but it's early. It's been field-tested mostly on **Windows** (macOS/Linux build in CI but haven't been run in anger yet); several big pieces landed recently; and the review-gate flow is verified by hand rather than an automated suite. Expect rough edges, and please [file issues](https://github.com/ai-nhancement/Anvil/issues) — that feedback is exactly what the beta is for. For the best experience, use a capable **tool-calling** model for the coder role.

Highlights

🔨 Two human gates, cross-vendor review — the plan and each build phase are critiqued by two different model families. Exactly two reviews per gate; no R3+, no drift.
🔁 Sequential review loop — R1 reviews → the coder applies fixes → you review → R2 reviews → the coder applies fixes → summary → you approve. R2 deliberately re-reviews after R1's fixes, catching bugs those fixes introduce.
🔍 Review anything, not just gates — /review runs the same briefing → critical-review → fix loop on any ad-hoc change that doesn't