RPI Workflow

You have access to workflow skills for structured development.

The RPI Workflow

Research → Plan → Implement → Validate
    ↑                            │
    └──── Knowledge Flywheel ────┘

Research Phase

/research <topic>      # Deep codebase exploration
ao search "<query>"    # Search existing knowledge
ao lookup <id>         # Pull full content of specific learning
ao lookup --query "x"  # Search knowledge by relevance

Output: .agents/research/<topic>.md

Plan Phase

/pre-mortem <spec>     # Simulate failures (error/rescue map, scope modes, prediction tracking)
/plan <goal>           # Decompose into trackable issues

Output: Beads issues with dependencies

Implement Phase

/implement <issue>     # Single issue execution
/crank <epic>          # Autonomous epic loop (uses swarm for waves)
/swarm                 # Parallel execution (fresh context per agent)

Output: Code changes, tests, documentation

Validate Phase

/vibe [target]         # Code validation (finding classification + suppression + domain checklists)
/post-mortem           # Validation + streak tracking + prediction accuracy + retro history
/retro                 # Quick-capture a single learning

Output: .agents/learnings/, .agents/patterns/

Release Phase

/release [version]     # Full release: changelog + bump + commit + tag
/release --check       # Readiness validation only (GO/NO-GO)
/release --dry-run     # Preview without writing

Output: Updated CHANGELOG.md, version bumps, git tag, .agents/releases/

Phase-to-Skill Mapping

Choosing the skill:

• Use /implement for single issue execution. Now defaults to TDD-first — writes failing tests before implementing. Skip with --no-tdd.
• Use /crank for autonomous epic execution (loops waves via swarm until done). Auto-generates file-ownership maps to prevent worker conflicts.
• Use /swarm directly for parallel execution without beads (TaskList only).
• Use /discovery for the discovery phase only (brainstorm → search → research → plan → pre-mortem).
• Use /validation for the validation phase only (vibe → post-mortem → retro → forge).
• Use /rpi for full lifecycle — delegates to /discovery → /crank → /validation.
• Use /ratchet to gate/record progress through RPI.

Available Skills

Start Here (11 starters)

These are the skills every user needs first. Everything else is available when you need it.

Advanced Skills (when you need them)

Expert Skills (specialized workflows)

Knowledge Flywheel

Every /post-mortem feeds back to /research:

1. Learnings extracted → .agents/learnings/
2. Patterns discovered → .agents/patterns/
3. Research enriched → Future sessions benefit

Issue Tracking

This workflow uses beads for git-native issue tracking:

bd ready              # Unblocked issues
bd show <id>          # Issue details
bd close <id>         # Close issue
bd vc status          # Inspect Dolt state if needed (JSONL auto-sync is automatic)

Examples

SessionStart Context Loading

Hook triggers: session-start.sh runs at session start

What happens:

1. In manual mode (default): MEMORY.md is auto-loaded by Claude Code; hook emits a pointer to on-demand retrieval (ao search, ao lookup)
2. In lean mode: hook extracts pending knowledge and injects prior learnings with a reduced token budget
3. Hook injects this skill automatically into session context
4. Agent loads RPI workflow overview, phase-to-skill mapping, trigger patterns
5. User says "check my code" → agent recognizes /vibe trigger naturally

Result: Agent knows the full skill catalog and workflow from session start. MEMORY.md is auto-loaded by default (manual mode). Set AGENTOPS_STARTUP_CONTEXT_MODE=lean for automatic knowledge injection alongside MEMORY.md.

Workflow Reference During Planning

User says: "How should I approach this feature?"

What happens:

1. Agent references this skill's RPI workflow section
2. Agent recommends Research → Plan → Implement → Validate phases
3. Agent suggests /research for codebase exploration, /plan for decomposition
4. Agent explains /pre-mortem for failure simulation before implementation
5. User follows recommended workflow with agent guidance

Result: Agent provides structured workflow guidance based on this meta-skill, avoiding ad-hoc approaches.

Troubleshooting