Skip to content

Latest commit

 

History

3 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 

Repository files navigation

VELA logo

VELA

VELA Enables Lazy Architects
A document-driven harness specification repository for AI coding agents.

Language: English · 简体中文


Table of Contents


Project Positioning

VELA is a harness-builder specification project.

Its purpose is not to ship a prebuilt harness package directly. Instead, it provides a strict BUILDER specification so that an agent can generate the full VELA Harness runtime in a stable and reproducible way.

In other words:

  • This repository primarily defines how VELA Harness should be generated.
  • The actual runtime harness is generated by an agent from the BUILDER.
  • The README explains the intent, usage, and output structure for humans.

What This Repository Contains

The current repository structure is:

README.md
README_zh.md
VELA_HARNESS_BUILDER.md
assets/
└── vela-logo.svg

Where:

  • README.md: English documentation.
  • README_zh.md: Simplified Chinese documentation.
  • VELA_HARNESS_BUILDER.md: the core build specification that defines how to generate AGENTS.md, CLAUDE.md, and .vela/.
  • assets/vela-logo.svg: project logo.

What This Repository Does Not Contain

This repository does not upload a prebuilt harness package.

That means the repository normally does not include:

AGENTS.md
CLAUDE.md
.vela/

Why:

  1. Single source of truth: the BUILDER stays the only authoritative generation source.
  2. Reproducibility: anyone can regenerate the full harness from the same BUILDER.
  3. Less drift: generated artifacts can drift away from the specification, while the BUILDER remains authoritative.
  4. Cleaner iteration: when rules change, only the BUILDER and the READMEs need to be updated.

Core Philosophy

VELA is built around five design ideas:

  1. Documentation before code.
  2. Goals before boundaries; boundaries before architecture; architecture before development.
  3. North Star document v0.0.1 is the only valid entry input.
  4. When boundaries are unclear, the agent must use a question protocol instead of making things up.
  5. Once development starts, software code must converge under project/.

This makes VELA more like a development process constraint layer than a normal template repository.


Quick Start

Build the harness according to VELA_HARNESS_BUILDER.md.

1. Get the repository contents

Clone or download the repository and obtain:

README.md
README_zh.md
VELA_HARNESS_BUILDER.md
assets/vela-logo.svg

2. Give the BUILDER to an agent

Provide VELA_HARNESS_BUILDER.md to an AI coding agent that supports file input, and explicitly ask it to:

  • generate the full VELA Harness according to the BUILDER,
  • generate only the files defined by the specification,
  • perform the required self-checks,
  • and stop after the Builder stage rather than entering project development.

3. Let the agent generate the runtime harness

According to the BUILDER, the generated output should be:

AGENTS.md
CLAUDE.md
.vela/

Important: these are generated outputs, not files that this repository ships by default.

4. Put the generated output into a target workspace

After generation, place the following into the root of your target project workspace:

AGENTS.md
CLAUDE.md
.vela/

Then let Codex or Claude Code run inside that workspace.


What the Generated Harness Produces

According to the BUILDER, the generated VELA Harness runtime contains:

AGENTS.md
CLAUDE.md
.vela/
├── SKILL.md
├── README.md
├── harness.yaml
├── CHANGELOG.md
├── rules/
├── templates/
├── schemas/
├── checklists/
└── extensions/

Key responsibilities:

  • AGENTS.md: Codex discovery adapter that delegates to .vela/SKILL.md.
  • CLAUDE.md: Claude Code discovery adapter that delegates to .vela/SKILL.md.
  • .vela/SKILL.md: the canonical runtime entrypoint.
  • .vela/harness.yaml: the highest authority for structure and file inventory.
  • .vela/rules/: stage rules, protocol rules, and quality rules.
  • .vela/templates/: document templates.
  • .vela/schemas/: structural constraints; higher priority than templates.
  • .vela/checklists/: self-check and stage-completion checklists.

How to Use the Generated Harness

1. Provide a North Star document v0.0.1

The only valid runtime input entry for VELA is a user-provided North Star document v0.0.1.

Minimum recommended shape:

# North Star Document v0.0.1
## 1. Project Goal
## 2. Target Users
## 3. Core Usage Scenarios
## 4. MVP Boundary
## 5. Non-goals
## 6. Technical / Platform Constraints
## 7. Core Feature Directions
## 8. Open Questions
## 9. Decision Records
## 10. Changelog

2. Make the agent read the entry adapters

  • For Codex: read AGENTS.md at the workspace root
  • For Claude Code: read CLAUDE.md at the workspace root

Both must continue to delegate to .vela/SKILL.md. They must not branch into a second rule system.

3. Advance through the stages

VELA does not allow jumping straight into coding. It requires a fixed stage progression until TODO.md can be generated and development can be executed legally.


Runtime Stages

VELA uses a fixed stage machine:

Stage Meaning
S0 Entry validation
S1 North Star completion
S2 Frontend / backend boundary discovery
S3 System boundary confirmation
S4 System boundary document generation
S5 Architecture specification generation
S6 TODO execution track generation
S7 Development execution
S8 Conflict resolution

Stages must not be skipped. README must not be treated as the execution rule source, and development must not start before boundary and architecture work is complete.


Key Constraints

Only valid entry input

  • The runtime entry input must be a user-provided North Star document v0.0.1.
  • The agent must not infer project goals from code, the project name, or the tech stack.

Question protocol

  • When boundaries are unclear, the question protocol must be used.
  • Each question should include recommended options.
  • The user may respond with “use all recommended options”.
  • High-risk boundaries require second confirmation.

TODO track

  • TODO.md is the only execution track for project development.
  • Each TODO must have its own plan.
  • By default, only one current TODO is advanced at a time.

project/ code-root policy

  • The Builder stage must not create project/.
  • During runtime, all generated or modified software code must stay under project/ at the workspace root.
  • docs/, TODO.md, decision records, boundary documents, and architecture specs are not part of the software code root.

Adapter-entry policy

  • AGENTS.md and CLAUDE.md must live at the workspace root.
  • They are only default discovery adapters.
  • The real canonical entrypoint is always .vela/SKILL.md.

Rule Priority

From highest to lowest, VELA can be understood as:

  1. .vela/harness.yaml: highest authority for structure and file inventory.
  2. .vela/SKILL.md: highest authority for runtime entry behavior.
  3. .vela/rules/stages/: stage-execution rules.
  4. .vela/rules/protocols/: cross-stage protocol rules.
  5. .vela/rules/quality/: quality acceptance rules.
  6. .vela/schemas/: structural constraints, higher than templates.
  7. .vela/templates/: formatting only, not rule authority.
  8. AGENTS.md / CLAUDE.md: adapter entrypoints, not core rule authorities.
  9. .vela/README.md: human-facing explanation, not an execution rule source.

FAQ

Why not commit .vela/ directly into the repository?

Because this repository is meant to maintain the build specification, not a generated artifact that may drift away from that specification.

What should I copy into a real project?

You do not copy the whole repository as-is. Instead, first let an agent generate the harness from VELA_HARNESS_BUILDER.md, and then place the generated:

AGENTS.md
CLAUDE.md
.vela/

into your target workspace.

Is the README a rule source?

No. The README explains the project to humans. The true rule sources are the BUILDER and, after generation, .vela/SKILL.md, .vela/rules/, .vela/schemas/, and .vela/checklists/.

Who is this repository for?

It is for people who want to constrain AI coding agents into a stable, document-first, stage-driven development workflow.


For the Chinese version, see README_zh.md.

About

A document-first harness builder specification for AI coding agents.

Resources

Stars

3 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors