automaton/.rules.md

.rules.md

Task-Driven Development

• All changes must go through a task in tasks/{name}/ with SPEC.md → phases → VERDICT.md
• All task creation must use python ~/.automaton/scripts/status.py --create-task {name} --project {project} — never create task directories manually
• All phase transitions must use python ~/.automaton/scripts/status.py --transition {phase} --task {name} --project {project}
• All phase approvals must use python ~/.automaton/scripts/status.py --approve --task {name} --project {project}
• Never edit files directly without a corresponding task

State Enforcement (v2.0)

• The .state file is the single source of truth for a task's current phase
• status.py --validate-folder --task {name} --project {project} must be run before starting work on any phase
• Approval gates (research, decomposition, design, test_design) require explicit user sign-off via status.py --approve --project {project}
• FORBIDDEN actions in each phase prompt must be respected — even in autopilot mode
• status.py --audit --project {project} should be run at session start to check for violations
• Tasks without .state files are UNTRACKED — all commands refuse to operate on them. Run status.py --upgrade --project {project} to bootstrap

Project Scoping

• Always pass --project {project} to status.py commands — never rely on CWD alone
• When working on the automaton framework, --project should be ~/.automaton or the framework directory
• When working on a project using the framework, --project should be the project root directory
• status.py will error if it cannot find a project and --project is not specified

VRAM-Aware Task Sizing

• Before creating or scoping a task, check ~/.automaton/config.md for VRAM limits
• Verify the task fits within max peak context (default: 12k tokens)
• If no config exists, default to 8k with 25% headroom

Changelog

• When a task reaches Resolution (VERDICT.md written), append an entry to CHANGELOG.md
• Use the format: - description (#task-name) under the appropriate [unreleased] section

Self-Improvement

• Add one rule per observed failure mode with a concrete example
• Consolidate contradictions monthly. Remove stale rules.
• No rule without a real example of the problem it prevents

Session Discipline

• After writing a SPEC.md for a new task, transition to research:awaiting_approval and wait for user approval via status.py --approve
• Do not implement a task in the same session it was created unless explicitly told to
• Past failure: agent created pre-commit-hook task, wrote SPEC.md, then immediately built and committed the hook without waiting — bypassing review 3 times in one session despite promises to follow the process

Scope Confinement

• Only work on tasks in the current project's .automaton/tasks/ directory
• Never scan, read, or modify tasks in other projects on the system
• The {project} in the Orchestrator prompt is the project root where the session started — do not broaden scope
• Past failure: agent scanned tasks in ~/ai-env/projects/invest-copilot/ while working on the automaton framework itself, wasting time on unrelated work across project boundaries

Artifact Integrity

• Write task artifacts atomically to avoid partial reads by the dashboard or other agents
• Prefer writing to a temporary file and renaming it into place
• Avoid leaving empty or malformed artifacts in the task folder

Self-Documenting UI Names

• All user-facing labels must be self-documenting and free of internal jargon
• A user should understand what something is without knowing the codebase internals
• Terms like "tick", "loop", "state", or "phase transition" are internal terminology — never use them directly in UI elements
• Pick names that describe what something does, not what it's called in code
• Past failure (1): "Loop Tick" in the Background tab — user asked "What is loop tick?" because it's scheduler jargon
• Past failure (2): "Loop" — still too vague, user said "I don't know what the loop is"
• Past failure (3): "Loop Agent" — user asked "How do I differentiate between agents with different roles?" because the name described the mechanism (loop) not the purpose
• Past failure (4): "Background" tab — the tab name described the location (background), not the content (agents). Renamed to "Agent" tab.
• Past failure (5): Group headers + agent type pill badge + icon + name all repeated the same info ("🧹 Cleanup" seen 3 times per card). Removed group headers and pill badges — only icon + name on each card.
• Past failure (6): "Cleanup" agent was vague — renamed to "Completed Task Archiver" which describes what it actually does.
• Rule: Every agent type must have a self-documenting name ending with its function (e.g., "Archiver", "Scanner", "Processor"). If multiple instances exist, list each instance card.
• Agent types with no active instances render as dimmed placeholder cards rather than being hidden, so the user always sees the full roster of available agents.