AgentOps Operating Model

AgentOps is the operational layer for coding agents.

Publicly, it gives you four things:

• Bookkeeping — captured learnings, findings, and reusable context
• Validation — plan and code review before work ships
• Primitives — single skills, hooks, and CLI surfaces
• Flows — named compositions like /research, /validation, and /rpi

Technically, AgentOps acts as a context compiler: raw session signal becomes reusable knowledge, compiled prevention, and better next work.

Core Flow: RPI

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

Research Phase

/research <topic>      # Deep codebase exploration
ao search "<query>"    # Search existing knowledge
ao search "<query>" --cite retrieved  # Record adoption when a search result is reused
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/

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 /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.

Start Here (12 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 promotes learnings and patterns into .agents/ so future /research starts with better context instead of zero.

Runtime Modes

AgentOps has four runtime modes. Do not assume hook automation exists everywhere.

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

Startup Context Loading

Hook-capable runtimes

1. session-start.sh (or equivalent) can run at session start.
2. In manual mode, MEMORY.md is auto-loaded and the hook points to on-demand retrieval (ao search, ao lookup).
3. In lean mode, the hook extracts pending knowledge and injects prior learnings with a reduced token budget.
4. This skill can be injected automatically into session context.

Codex (v0.115.0+: native hooks, older: hookless fallback)

1. v0.115.0+: hooks fire automatically — same behavior as hook-capable runtimes above.
2. Pre-v0.115.0: run ao codex start explicitly, use ao lookup for citations, end with ao codex stop.

Result: The agent gets the RPI workflow, prior context, and a citation path in all modes.

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