Skip to content

fora22/vexo

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

VEXO

Verified Execution with eXploration Operations

A behavioral protocol that steers AI coding agents to explore before deciding and verify before shipping.

Quick StartWhy VEXOHow It WorksIDE SetupCustomizationDesign Philosophy

🇰🇷 한국어 문서


Why VEXO

AI coding agents are powerful, but they have predictable failure modes:

Problem What happens
Premature convergence AI locks onto the first "good enough" solution and skips exploring alternatives
No verification Code is generated without validation plans — bugs ship silently
One-size-fits-all responses Simple questions get over-structured answers; complex ones get shallow treatment
Context window waste Loading all rules at once burns tokens on irrelevant instructions

VEXO addresses these by giving AI agents a structured behavioral protocol — not just coding rules, but a decision-making framework.

Before / After

Without VEXO — "Add a caching layer to the user API"

Here's how to add Redis caching:
[immediately writes code with one approach, no verification]

With VEXO — Same prompt

[Explore] Three approaches to consider:

Option A (Industry standard): Redis with TTL-based invalidation
- Pros: Mature ecosystem, team familiarity
- Cons: Additional infrastructure

Option B: In-memory cache (node-cache)
- Pros: Zero infra cost, simple
- Cons: Not shared across instances

Option C: HTTP caching (ETag/Cache-Control)
- Pros: No server-side state
- Cons: Limited control over invalidation

→ Which direction fits your constraints?

[After selection → Execution plan + Verification plan + Failure conditions]

How It Works

VEXO uses a core + lazy-load architecture inspired by AWS AI-DLC:

rules/
├── vexo.md                    ← Always loaded (entry point)
│
└── rule-details/              ← Loaded on demand by task type
    ├── modes/
    │   ├── implementation.md  ← Build: code, architecture, data
    │   ├── exploration.md     ← Ideate: brainstorm, plan, explore
    │   └── review.md          ← Review: audit existing work
    │
    └── domains/
        ├── data.md            ← Data migration, ETL, aggregation
        ├── backend.md         ← Service API, business logic, infra
        └── ai-agent.md       ← LLM integration, agents, prompts

Core principles (always active)

  1. No result without verification. Execution plans and verification plans are designed together.
  2. Explore before deciding. Options are explored before committing to an approach — preventing design fixation.
  3. Industry standards first. Mainstream solutions are preferred to minimize team adoption cost. Non-standard choices require explicit justification.
  4. Ideal → Realistic. The ideal architecture is presented first, followed by a pragmatic alternative with trade-offs.
  5. Test ROI awareness. When test cost exceeds 1.5× implementation cost, only essential tests are performed with skipped items and risks documented.

Automatic task classification

Users just write naturally. VEXO classifies the request and loads only the relevant rules:

Type Trigger pattern Rules loaded
Implementation "build this", "how to implement", architecture/code design modes/implementation.md + domain file
Exploration "what do you think about", "should we try", idea discussion modes/exploration.md
Learning "what is", "why does this work", concept/principle questions (no rule-details needed)
Quick answer Simple fact check, obvious error, minor fix (no rule-details needed)
Review "review this code", "how's this structure", existing work audit modes/review.md + domain file

Explore → Decide workflow

Inspired by HAICo's divergent/convergent thinking model, VEXO separates idea exploration from decision-making:

  • Explore phase: Generate 3–5 genuinely different approaches (not minor variations). Stay in this phase until the user signals a direction.
  • Decide phase: Lock in the chosen approach, detail trade-offs, and transition to implementation.

The AI prefixes responses with [Exploring] or [Decided] so the current phase is always visible.


Quick Start

Minimal setup (just the core)

Copy vexo.md into your AI IDE's rules directory. This single file contains all core principles and task classification logic.

# Example for Kiro
mkdir -p .kiro/steering
cp rules/vexo.md .kiro/steering/

Full setup (core + rule-details)

Copy both the core file and the rule-details directory for domain-specific guidance.

# Example for Kiro
mkdir -p .kiro/steering
cp rules/vexo.md .kiro/steering/
cp -r rules/rule-details .kiro/

IDE Setup

VEXO works with any AI coding agent that supports rule/steering files. Below are setup instructions for popular IDEs.

Kiro

mkdir -p .kiro/steering
cp rules/vexo.md .kiro/steering/
cp -r rules/rule-details .kiro/

Directory structure:

<project-root>/
├── .kiro/
│   ├── steering/
│   │   └── vexo.md
│   └── rule-details/
│       ├── modes/
│       └── domains/

Cursor

mkdir -p .cursor/rules
cp rules/vexo.md .cursor/rules/
cp -r rules/rule-details .cursor/

Claude Code

cp rules/vexo.md .claude/CLAUDE.md
cp -r rules/rule-details .claude/rule-details/

Note: Claude Code uses CLAUDE.md as its primary instruction file. You may need to rename or adjust the entry point.

OpenAI Codex

mkdir -p .codex
cp rules/vexo.md .codex/instructions.md
cp -r rules/rule-details .codex/rule-details/

Note: Codex CLI reads from .codex/instructions.md. Adjust file references in vexo.md if your IDE uses different paths for rule-details.


Customization

Adding a new domain

Create a new file in rule-details/domains/. Follow the existing pattern:

# rule-details/domains/your-domain.md

## Risk defaults

| Task | Default risk | Min verification level |
| ---- | ------------ | ---------------------- |
| ...  | ...          | ...                    |

## Verification checklist

- [ ] ...

## Industry standard patterns

| Area | Standard approach |
| ---- | ----------------- |
| ...  | ...               |

Then add the domain to the classification table in vexo.md.

Adjusting verification levels

Edit the verification levels in rule-details/modes/implementation.md:

  • L1 (Basic): count, null check — low risk
  • L2 (Standard): L1 + sampling + before/after diff — medium risk
  • L3 (Strict): L2 + checksum + full validation — high risk

Removing domains you don't need

Simply delete the domain file from rule-details/domains/. The core workflow will skip it automatically since it's never referenced.


Design Philosophy

See docs/design-philosophy.md for the full story, including:

  • How VEXO evolved from a ChatGPT custom instruction into a structured framework
  • The influence of HAICo's divergent/convergent thinking model
  • Why the AI-DLC core + lazy-load architecture was adopted
  • The "ask first" principle and why AI agents need explicit permission to clarify

Project Structure

vexo/
├── README.md                  ← You are here
├── LICENSE                    ← Apache 2.0
├── CHANGELOG.md               ← Version history
├── CONTRIBUTING.md            ← How to contribute
│
├── rules/
│   ├── vexo.md                ← Core rules (always loaded)
│   └── rule-details/          ← Extended rules (lazy loaded)
│       ├── modes/
│       │   ├── implementation.md
│       │   ├── exploration.md
│       │   └── review.md
│       └── domains/
│           ├── data.md
│           ├── backend.md
│           └── ai-agent.md
│
└── docs/
    ├── design-philosophy.md   ← Background and design decisions
    └── ko/
        ├── README.md              ← 한국어 README
        └── design-philosophy.ko.md ← 한국어 설계 철학

Roadmap

  • Evaluation framework — Structured methods to measure how well VEXO rules affect AI agent behavior (before/after scoring, consistency metrics)
  • Additional domain files (frontend, mobile, DevOps)
  • IDE-specific installation scripts
  • Community-contributed rule packs

Contributing

VEXO is designed to absorb good ideas from other frameworks and harness engineering techniques. If you've found patterns that make AI agents more reliable — whether it's a new domain, a better verification checklist, or an entirely different approach — we want to hear about it.

See CONTRIBUTING.md for guidelines on adding domains, modes, and improvements. PRs and issues are very welcome.


Acknowledgments

VEXO's design is informed by:

  • HAICo — Divergent/convergent thinking separation for human-AI co-creation. The insight that AI tends toward premature convergence directly shaped VEXO's Explore → Decide workflow.
  • AWS AI-DLC (GitHub) — The core + lazy-load rule architecture pattern. AI-DLC's approach of always-loaded core rules with conditionally-loaded details inspired VEXO's file structure.

License

Apache License 2.0 — see LICENSE for details.

About

A behavioral protocol for AI coding agents — explore before deciding, verify before shipping, load rules only when needed. A lightweight harness for Kiro, Cursor, Claude Code, and Codex.

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors