using-agentops

# 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`, `/validate`, 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

```bash
/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

```bash
/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

```bash
/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

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

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

## Phase-to-Skill Mapping

| Phase | Primary Skill | Supporting Skills |
|-------|---------------|-------------------|
| **Discovery** | `/discovery` | `/brainstorm`, `/research`, `/plan`, `/pre-mortem` |
| **Implement** | `/crank` | `/implement` (single issue), `/swarm` (parallel execution) |
| **Validate** | `/validate` | `/vibe`, `/post-mortem`, `/forge` |

**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 `/validate` for the **validation phase only** (vibe → post-mortem → forge).
- Use `rpi` for **full lifecycle** — delegates to `/discovery` → `/crank` → `/validate`.
- 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.

| Skill | Purpose |
|-------|---------|
| `/quickstart` | Guided onboarding — run this first |
| `/bootstrap` | One-command full AgentOps setup — fills gaps only |
| `/research` | Deep codebase exploration |
| `/council` | Multi-model consensus review + finding auto-extraction |
| `/validate` | Canonical PASS/WARN/FAIL verdict over an artifact, plan, code change, PR, or gate |
| `/vibe` | Code validation (classification + suppression + domain checklists) |
| `rpi` | Full RPI lifecycle orchestrator (`/discovery` → `/crank` → `/validate`) |
| `/implement` | Execute single issue |
| `/post-mortem --quick` | Quick-capture a single learning into the flywheel |
| `/status` | Single-screen dashboard of current work and suggested next action |
| `/goals` | Maintain GOALS.yaml fitness specification |
| `/push` | Atomic test-commit-push workflow |

## Advanced Skills (when you need them)

| Skill | Purpose |
|-------|---------|
| `/compile`, `/flywheel` | Active knowledge intelligence and flywheel health — Mine → Grow → Defrag cycle |
| `/curate` | Canonical miner role for transcripts, `.agents/`, bd, git, skill diffs, and rare wiki entries |
| `/curate --mode=harvest` | Cross-rig knowledge consolidation — sweep, dedup, promote to global hub (folded the retired harvest lane) |
| `/inject` | Operationalize a mature `.agents` corpus into beliefs, playbooks, briefings, and gap surfaces (folded the retired knowledge-activation lane) |
| `/brainstorm` | Structured idea exploration before planning |
| `/discovery` | Full discovery phase orchestrator (brainstorm → search → research → plan → pre-mortem) |
| `/plan` | Epic decomposition into issues |
| `/design` | Product validation gate — goal alignment, persona fit, competitive differentiation |
| `/pre-mortem` | Failure simulation (error/rescue, scope modes, temporal, predictions) |
| `/post-mortem` | Validation + streak tracking + prediction accuracy + retro history |
| `/bug-hunt` | Root cause analysis |
| `/release` | Pre-flight, changelog, version bumps, tag |
| `/crank` | Autonomous epic loop (uses swarm for each wave) |
| `/swarm` | Fresh-context parallel execution (Ralph pattern) |
| `/using-atm` | Run AgentOps loops out of session on an ATM tmux swarm (the ATM leg of the substrate) |
| `evolve` | Goal-driven fitness-scored improvement loop |
| `/burndown` | Bounded epic-completion loop — drive a finite target to all-merged, then stop |
| `/eval-outcomes` | Grade via Outcomes as a holdout-safe projection of the locked eval substrate — one bar, many runtimes |
| `/operating-loop-workflow` | Install + run the operating-loop multi-agent Workflow (seven-move loop) |
| `/autodev` | PROGRAM.md autonomous development contract setup and validation |
| `agy-rules-workflows` | Install AGY-native rules, loop workflow, and scheduled goal controls |
| `/curate --mode=dream` | Out-of-session knowledge compounding lane |
| `/doc` | Documentation generation — repo docs (def