Files
automaton/ONBOARDING.md
T

67 lines
2.1 KiB
Markdown
Raw Normal View History

# Onboarding a Project
2026-05-30 23:27:09 -04:00
This document defines the **Agent Protocol** for initializing a new project. When the agent is asked to "Onboard a project," it must follow these steps.
2026-05-30 23:27:09 -04:00
## The Exploration Ritual
2026-05-30 23:27:09 -04:00
The agent's first task in any project is to perform an "Initial Exploration" to establish context.
2026-05-30 23:27:09 -04:00
### Step 1: Discovery
The agent must:
1. Explore the project root using `ls` and `find`.
2. Read `.agent-framework/AGENT.md`
3. Read `.agent-framework/RULES.md`
4. Read the global `~/.agent-framework/AGENT.md`
2026-05-30 23:27:09 -04:00
### Step 2: Reporting
The agent must report back with:
- Confirmation that the framework files were found and read.
- A summary of the project rules.
- The expected workflow for this project.
- Key observations from the project structure.
---
## The Lifecycle of a Project
2026-05-30 23:27:09 -04:00
Once onboarded, the project moves through these phases. The agent should use the provided prompts to transition between them.
2026-05-30 23:27:09 -04:00
### Phase 1: Research
**Template**: `prompts/research.md`
**Output**: `SPEC.md`
**Trigger**: *"Research {task-description}"*
2026-05-30 23:27:09 -04:00
### Phase 2: Implementation
**Template**: `prompts/implement.md`
**Output**: Code changes + test results
**Trigger**: *"Implement the {task-name} task"*
2026-05-30 23:27:09 -04:00
### Phase 3: Bug Finding
**Template**: `prompts/bug_finder.md`
**Output**: `BUG_REPORT.md`
**Trigger**: *"Find bugs in the {task-name} task"*
2026-05-30 23:27:09 -04:00
### Phase 4: Adversarial Verification
**Template**: `prompts/adversarial_bug_find.md`
**Output**: `ADVERSARIAL_BUG_REPORT.md`
**Trigger**: *"Perform adversarial bug find for {task-name}"*
2026-05-30 23:27:09 -04:00
### Phase 5: Referee
**Template**: `prompts/referee.md`
**Output**: `VERDICT.md`
**Trigger**: *"Review the {task-name} task"*
2026-05-30 23:27:09 -04:00
## Prompt Rendering Convention
2026-05-30 23:27:09 -04:00
All prompts are stored as template files in `~/.agent-framework/prompts/`. They use `{placeholder}` syntax.
2026-05-30 23:27:09 -04:00
### Placeholders
- `{project}`: Absolute path to the project root.
- `{task-name}`: The task folder name (kebab-case).
- `{task-description}`: A brief, clear summary of the current work.
2026-05-30 23:27:09 -04:00
When the agent receives a trigger command, it must:
1. Read the corresponding template file.
2. Replace all `{placeholders}` with the actual project values.
3. Execute the rendered prompt.