Quality gates and evidence verification for AI coding agents.
Your agent writes code fast. Meta-Architect makes it prove each stage first. Design, evidence, logic, security, experience, build. Each gate stays locked until the one before it passes.
Quick Start · Demo · Verified Coverage · Contributing · Issues
Note
Meta-Architect is a workflow layer for teams that want architecture, evidence, review, and release discipline before build execution. Meta-Architect does not replace your coding runtime. It wraps that runtime with architecture, evidence, gate enforcement, and release-sensitive workflow control.
| ✅ Recommended | 🧰 All available installation commands |
|---|---|
Use the signed jsDelivr installer on macOS, Linux, WSL, or Git Bash.curl -fsSLo install.sh https://cdn.jsdelivr.net/gh/JustineDevs/meta-architect@latest/scripts/install.shcurl -fsSLo install.sh.sha256 https://cdn.jsdelivr.net/gh/JustineDevs/meta-architect@latest/scripts/install.sh.sha256sed 's#scripts/install.sh#install.sh#' install.sh.sha256 | sha256sum -c -sh install.shma --madmax --high$maestro I want to build: [your project idea] |
npm globalnpm i -g @openai/codex@latest @jstn-sdk/ma@latestMeta-Architect only npm i -g @jstn-sdk/ma@latestWindows PowerShell npm i -g @openai/codex@latest @jstn-sdk/ma@latestDebian / Ubuntu sudo apt install ./meta-architect_<version>_all.debArch Linux sudo pacman -U ./meta-architect-<version>-1-any.pkg.tar.xzFedora / openSUSE sudo dnf install ./meta-architect-<version>-1.noarch.rpm |
Copy and paste this prompt into your AI coding agent:
Install Meta-Architect for this project.
1. Detect the current AI host and its native project configuration surface.
2. Install or update `@jstn-sdk/ma@latest` using the host's supported package manager.
3. Set `MA_AGENT` to the detected host ID when a host-specific surface is available.
4. Run `ma setup` and accept the detected project scope and targets.
5. Verify the generated `.ma/` state and native host artifacts.
6. Report the installed version, selected host, generated files, and any unsupported capabilities.
Do not overwrite user-owned files, modify unrelated configuration, or claim a host is supported without verification.
More install options: docs/getting-started.md
Uninstall Meta-Architect: npm uninstall -g @jstn-sdk/ma
Uninstall Meta-Architect and Codex: npm uninstall -g @jstn-sdk/ma @openai/codex
Install Meta-Architect once, then select the host surface before launch. The
pre-launch step detects installed hosts and writes the selected scope and
targets to .ma/prelaunch.json.
# Codex (reference host)
npm i -g @openai/codex@latest @jstn-sdk/ma@latest
ma --madmax --high
# Claude Code
MA_AGENT=claude-code npm i -g @jstn-sdk/ma@latest
MA_AGENT=claude-code ma --madmax --high
# Cursor
MA_AGENT=cursor npm i -g @jstn-sdk/ma@latest
MA_AGENT=cursor ma --madmax --high
# Any registered host surface
MA_AGENT=<host-id> npm i -g @jstn-sdk/ma@latest
MA_AGENT=<host-id> ma --madmax --highMA installs or reuses the native skill/configuration surface for the selected host and keeps the canonical workflow unchanged. See the host compatibility evidence for supported surfaces.
The repository includes a hosted Claude Code marketplace for the existing
plugins/meta-architect bundle:
/plugin marketplace add JustineDevs/meta-architect
/plugin install meta-architect@meta-architect
🔌 All 33 plugins & features
The plugin and feature inventory is maintained in the support bundle manifest and skills manifest, with verification in the coverage documentation.
Why do AI coding agents need gates?
Your agent writes code faster than you review it. Studies and dev surveys keep finding the same failures:
- Plausible code with wrong logic
- Imports of packages which don't exist
- Outdated APIs from training cutoffs
- "Done" claims with zero proof
Meta-Architect blocks each one:
- No architecture without a decision record.
$archwrites the blueprint and the trade-offs. - No stack claims without evidence.
$sagegrades every dependency claim VERIFIED, PARTIAL, or MISSING against upstream repos through GitMCP. - No build while a gate is red. Logic, security, and DX reviews fail closed.
- No release claims without proof. Releases need issue-linked, production-verified evidence.
An open-source workflow governor for AI coding agents. You install it as a skill package in your agent host. It adds six gated lanes plus $maestro, a bounded manager which routes your work through them. It doesn't replace your agent, runtime, or model. It governs what they produce.
| Fact | Value |
|---|---|
| Type | Skill and plugin package for AI coding agent hosts |
| Reference host | Codex (full support) |
| Compatibility scope | Codex, OpenCode, Gemini CLI, Amp, Claude Code, Goose, Hermes, Pi, Cursor, Windsurf, Cline, Continue, Roo, Kiro CLI, Junie, GitHub Copilot, and Antigravity (coverage evidence) |
| Runtime | Node.js 20+ |
| Install | npm i -g @jstn-sdk/ma |
| Evidence sources | GitMCP / MCP endpoints |
| License | MIT |
State your intent once. $maestro picks the next safe step and stops when something fails.
$maestro I want to build: a multi-tenant analytics API for logistics customers
Meta-Architect Status
=====================
Idea: CLEAR
Architecture: APPROVED
Evidence: VERIFIED
Logic: GREEN
Security: GREEN
Experience: GREEN
Build: LOCKED
Build stays LOCKED until every upstream gate passes. Red stays red.
| Lane | Question it answers | Gate |
|---|---|---|
$arch |
What are you building, and why this shape? | architecture_status |
$sage |
Do your stack choices trace to real upstream evidence? | evidence_status |
$flow |
Do the logic and state transitions hold? | logic_status |
$vet |
Does it survive security and dependency review? | security_status |
$vibe |
Will developers and users tolerate it? | experience_status |
$build |
What's the narrowest safe thing to build now? | build_status |
Four helpers support the lanes without moving gates: $align, $diagnose, $tdd, $cleanup.
Spec-driven tools structure what your agent writes. Meta-Architect enforces what your agent proves.
| Spec Kit | BMAD | Agent OS | Meta-Architect | |
|---|---|---|---|---|
| Structured workflow | Yes | Yes | Yes | Yes |
| Gates which block | No | No | No | Yes |
| External evidence verification | No | No | No | Yes, GitMCP-graded |
| Learning loop with promotion rules | No | No | No | Yes |
| Multi-host | Yes | Yes | Yes | Codex today, expanding |
Already using a spec tool? Keep it. Their specs become inputs. MA's gates verify the execution.
- Solo builders shipping with AI agents who want release discipline without enterprise process
- OSS contributors who need stack decisions they defend in review
- Skip it if you want an unattended agent writing code. MA governs your agent. It isn't one.
- Open an issue before a PR. It saves rework.
- Start here: issues labeled
triage - Branch from
dev.mainis protected and release-facing. - Run
npm testbefore you submit. Follow AGENTS.md. - AI-assisted PRs welcome. Explain every line you submit or expect a close.
- Getting Started
- Skills Reference
- Demo
- Coverage Matrix: the proof behind every claim on this page
- Release Spec
- Disk-Bounded Test and Review Runs
- MCP Setup
- ChatGPT Integration: deployment requirements and publication boundary
MIT. Built by @JustineDevs. Shaped by ideas from the oh-my-codex ecosystem.
Found a bad claim before it shipped? Star the repo. It helps other developers find it.
