Quick start

You do not need to adopt every optional tool on day one. Start with the smallest loop that creates durable state:

0. Make GitHub reachable

Session continuity depends on both sides being able to read and update repository-scoped GitHub Issues.

ChatGPT needs GitHub repository access for Work Packet creation/update.
Cursor /resume needs an available GitHub integration or authenticated gh.
If neither is available, stop and configure access instead of rebuilding state from pasted historical handoffs.

1. Add the repository entrypoint

A base Engineering System adoption needs:

AGENTS.md
.engineering/project.yaml
.engineering/tests.yaml
.engineering/release.yaml

Use the canonical templates from: github.com/datarelay-labs/engineering-system Pin the Engineering System version in the repository instead of silently following an unknown future version.

2. Add session continuity only if you use it

For ChatGPT ↔ Cursor resume workflow, add:

.cursor/commands/resume.md
.github/ISSUE_TEMPLATE/ai-work-packet.md

The optional repository Cursor rule can also point agents at the canonical Engineering System.

3. Keep ChatGPT instructions short

ChatGPT does not need a copy of the entire standard in Custom Instructions. The global instruction only needs to route work correctly:

identify the target repository first
use the canonical Engineering System
load minimal task-relevant context
use the repository Work Packet for handoff/resume
verify current Git/GitHub state before acting
never claim unexecuted or different-HEAD evidence as PASS

4. Run the first workflow

ChatGPT:
"Cursor에 넘겨줘"

Cursor:
/resume

ChatGPT:
"Cursor 끝났어. 계속"

If the same workstream continues without a giant pasted prompt, the continuity path is working.

5. Add optional layers when they solve a real problem

Desktop Commander

Add direct development-server audit when GitHub alone cannot prove local runtime or worktree state.

Athena

Add searchable decision/history knowledge when rationale must be recovered across projects.

tmux + Phone SSH

Add a persistent remote execution path when work must continue away from the desk.

Add completion notifications when long-running implementation or tests should run unattended.

Before implementation

The owner and AI should know:

change type
affected domain
public contract
persisted state
security boundary
operational impact
required tests

Then make the smallest correct change and run the cheapest deterministic check that can disprove it.

The owner retains product scope, final decisions, release approval, and human UX judgment. AI assists the engineering process; it does not silently broaden product scope.

Start Here

System

Adoption & Lessons

Quick Start

Quick start

0. Make GitHub reachable

1. Add the repository entrypoint

2. Add session continuity only if you use it

3. Keep ChatGPT instructions short

4. Run the first workflow

5. Add optional layers when they solve a real problem

Desktop Commander

Athena

tmux + Phone SSH

Telegram

Before implementation

​Quick start

​0. Make GitHub reachable

​1. Add the repository entrypoint

​2. Add session continuity only if you use it

​3. Keep ChatGPT instructions short

​4. Run the first workflow

​5. Add optional layers when they solve a real problem

Desktop Commander

Athena

tmux + Phone SSH

Telegram

​Before implementation

Quick start

0. Make GitHub reachable

1. Add the repository entrypoint

2. Add session continuity only if you use it

3. Keep ChatGPT instructions short

4. Run the first workflow

5. Add optional layers when they solve a real problem

Before implementation