> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/thiagofinch/mega-brain/llms.txt
> Use this file to discover all available pages before exploring further.

# Slash Commands

> Complete reference for Claude Code slash commands

# Slash Commands

Mega Brain extends Claude Code with 40+ slash commands for knowledge management, agent orchestration, and pipeline processing.

## Quick Reference

| Command              | Alias | Category     | Description                  |
| -------------------- | ----- | ------------ | ---------------------------- |
| `/jarvis`            | -     | System       | Activate JARVIS orchestrator |
| `/agents`            | `/a`  | Agents       | Show agent status and memory |
| `/conclave`          | -     | Deliberation | Multi-agent council session  |
| `/inbox`             | `/i`  | Pipeline     | List pending files           |
| `/process-jarvis`    | -     | Pipeline     | Run 5-phase processing       |
| `/extract-knowledge` | -     | Knowledge    | Extract insights from source |
| `/create-agent`      | -     | Agents       | Create new cargo agent       |
| `/save`              | -     | Session      | Save current session         |
| `/resume`            | -     | Session      | Resume previous session      |

***

## JARVIS (Orchestrator)

### /jarvis

Activate the JARVIS meta-agent orchestrator.

**Syntax:**

```bash theme={null}
/jarvis [subcommand]
```

<ParamField path="subcommand" type="string" optional>
  Optional subcommand: `status`, `resume`, `checkpoint`, `rollback`, `diagnose`, `log`, `decisions`, `suggest`, `pending`, `explain`, `pause`, `force`, `clear-pending`
</ParamField>

**Behavior:**

* Loads state from `/.claude/jarvis/STATE.json`
* Displays system status with visual timeline
* Auto-resumes if process in progress
* Provides context preservation and error recovery

**Subcommands:**

<Expandable title="/jarvis status">
  Show detailed system state with metrics, pending items, and recent decisions.
</Expandable>

<Expandable title="/jarvis resume">
  Continue processing from last checkpoint.
</Expandable>

<Expandable title="/jarvis checkpoint">
  Create manual snapshot of current state to `/.claude/jarvis/CHECKPOINTS/`.
</Expandable>

<Expandable title="/jarvis rollback {CP-ID}">
  Restore from specific checkpoint ID.
</Expandable>

<Expandable title="/jarvis diagnose">
  Run complete system health analysis.
</Expandable>

**Files:**

* `/.claude/jarvis/STATE.json` - Current state (never edit manually)
* `/.claude/jarvis/CONTEXT-STACK.json` - Context history (max 50)
* `/.claude/jarvis/DECISIONS-LOG.md` - All autonomous decisions
* `/.claude/jarvis/PENDING.md` - Items requiring resolution
* `/.claude/jarvis/SESSION-*.md` - Per-session logs

**Source:** `.claude/commands/jarvis.md:1-213`

***

## Agents

### /agents

Show status of all agents and their memory freshness.

**Syntax:**

```bash theme={null}
/agents [--outdated | --knowledge "person" | --category CATEGORY]
```

<ParamField path="--outdated" type="flag" optional>
  List agents with memory not updated in 3+ days
</ParamField>

<ParamField path="--knowledge" type="string" optional>
  Find agents with knowledge about specific person
</ParamField>

<ParamField path="--category" type="string" optional>
  Filter by category: `SALES`, `C-LEVEL`, `OPERATIONS`, `MARKETING`
</ParamField>

**Output:**

```
═══════════════════════════════════════
           AGENTS STATUS
═══════════════════════════════════════
🤖 AGENTES ATIVOS: 22

C-LEVEL:
  CRO      │ MEMORY: 2026-03-01 │ 12 pessoas
  CFO      │ MEMORY: 2026-02-28 │ 8 pessoas
  CMO      │ MEMORY: 2026-03-02 │ 15 pessoas
  COO      │ MEMORY: 2026-03-01 │ 10 pessoas

SALES:
  CLOSER   │ MEMORY: 2026-03-05 │ 25 pessoas
  BDR      │ MEMORY: 2026-03-04 │ 18 pessoas
  ...
```

**Source:** `.claude/commands/agents.md:1-162`

***

### /create-agent

Create new cargo agent from detected role.

**Syntax:**

```bash theme={null}
/create-agent <role-name>
```

<ParamField path="role-name" type="string" required>
  Name of the role (e.g., "ACCOUNT-EXECUTIVE", "PRODUCT-MANAGER")
</ParamField>

**Behavior:**

* Checks role mention threshold (10+ weighted mentions)
* Generates agent files: `AGENT.md`, `SOUL.md`, `MEMORY.md`
* Updates `AGENT-INDEX.yaml`
* Assigns DNA from knowledge base

**Source:** `.claude/commands/create-agent.md:1-12`

***

## Conclave (Multi-Agent Deliberation)

### /conclave

Run full council session with debate, critic, devil's advocate, and synthesizer.

**Syntax:**

```bash theme={null}
/conclave "<decision or question>"
```

<ParamField path="decision" type="string" required>
  Strategic decision or question to deliberate
</ParamField>

**Example:**

```bash theme={null}
/conclave "Should we change closer commission from 10% to 15%?"
/conclave "Invest R$500k in Q1 team expansion?"
```

**Phases:**

1. **Constitutional Foundation** - Invoke core principles (Empiricism, Pareto, Inversion, Antifragility)
2. **Debate** - Multi-agent discussion between relevant roles (CRO, CFO, etc.)
3. **Critic** - Methodological quality assessment (score 0-100)
4. **Devil's Advocate** - Challenge assumptions, identify risks
5. **Synthesis** - Unified recommendation with confidence score

**Output:**

```
═══════════════════════════════════════
DECISÃO RECOMENDADA: [recommendation]
CONFIANCA: 85%

RISCOS RESIDUAIS:
• Risk 1: Mitigation strategy
• Risk 2: Mitigation strategy

PRÓXIMOS PASSOS:
1. Action - Owner - Deadline
2. Action - Owner - Deadline
```

**Anti-loop Rule:** Council runs once per query. If confidence \< 60%, escalates to human decision.

**Source:** `.claude/commands/conclave.md:1-197`

***

### /debate

Run debate between specific agents (without full council).

**Syntax:**

```bash theme={null}
/debate <agent1>,<agent2>[,<agent3>] "<topic>"
```

<ParamField path="agents" type="string" required>
  Comma-separated agent IDs (e.g., "cro,cfo,cmo")
</ParamField>

<ParamField path="topic" type="string" required>
  Topic or decision to debate
</ParamField>

**Example:**

```bash theme={null}
/debate cro,cfo "Reduce CAC by 30% in Q2"
```

**Source:** `.claude/commands/debate.md:1-10`

***

## Pipeline Processing

### /inbox

List files pending processing in inbox.

**Syntax:**

```bash theme={null}
/inbox [--all | --pending | --person "Name" | --organize [--execute]]
```

<ParamField path="--all" type="flag" optional>
  Show both processed and pending files
</ParamField>

<ParamField path="--pending" type="flag" optional>
  Show only pending files (default)
</ParamField>

<ParamField path="--person" type="string" optional>
  Filter by person name
</ParamField>

<ParamField path="--organize" type="flag" optional>
  Auto-organize files into correct folders (dry-run)
</ParamField>

<ParamField path="--execute" type="flag" optional>
  Execute auto-organization (requires --organize)
</ParamField>

**Auto-Organization:**

* Detects person from filename/content
* Classifies content type (PODCASTS, COURSES, MASTERMINDS, etc.)
* Standardizes naming (UPPERCASE, \[youtube link])
* Moves to `{PERSON}/{TYPE}/` structure

**Output:**

```
═══════════════════════════════════════
           INBOX STATUS
═══════════════════════════════════════
📥 AGUARDANDO PROCESSAMENTO: 5

1. COLE-GORDON/PODCASTS/farm-system.txt
   ├─ Added: 2 days ago | ~5,400 words
   └─ Command: /process-jarvis "inbox/..."
```

**Source:** `.claude/commands/inbox.md:1-297`

***

### /process-jarvis

Run 5-phase pipeline processing on source file.

**Syntax:**

```bash theme={null}
/process-jarvis "<file-path>"
```

<ParamField path="file-path" type="string" required>
  Path to source file in inbox (e.g., "inbox/COLE-GORDON/PODCASTS/farm-system.txt")
</ParamField>

**Phases:**

1. **Chunking** - Split into semantic chunks (500-1500 words)
2. **Entity Resolution** - Normalize persons, themes, roles
3. **Insight Extraction** - Extract DNA layers, frameworks, heuristics
4. **Narrative Synthesis** - Create coherent narratives per person/theme
5. **Cascade** - Update agent memories, dossiers, and knowledge base

**Checkpoints:**

* Each phase creates checkpoint in `/.claude/jarvis/CHECKPOINTS/`
* Auto-resume from last checkpoint on interruption
* Rollback support via `/jarvis rollback`

**Output Artifacts:**

* `/processing/chunks/{source-id}.json` - Chunks with metadata
* `/processing/canonical/CANONICAL-MAP.json` - Entity mappings
* `/processing/insights/INSIGHTS-STATE.json` - Extracted insights
* `/processing/narratives/NARRATIVES-STATE.json` - Synthesized narratives
* `/knowledge/dossiers/persons/{person}.md` - Updated dossiers
* `/agents/{category}/{agent}/MEMORY.md` - Updated agent memories

**Source:** `.claude/commands/process-jarvis.md:1-144`

***

### /ingest

Ingest new material (URL, file, or folder) into inbox.

**Syntax:**

```bash theme={null}
/ingest <source> [--type TYPE]
```

<ParamField path="source" type="string" required>
  URL, file path, or folder path to ingest
</ParamField>

<ParamField path="--type" type="string" optional>
  Content type: `podcast`, `course`, `mastermind`, `blueprint`, `vsl`, `script`
</ParamField>

**Supported Sources:**

* YouTube URLs (auto-transcription)
* Google Drive files/folders
* Local files (.txt, .md, .pdf, .docx)
* Audio files (.mp3, .wav, .m4a)

**Behavior:**

* Downloads/copies to inbox
* Extracts transcriptions (audio/video)
* Detects person and content type
* Registers in `INBOX-REGISTRY.md`

**Source:** `.claude/commands/ingest.md:1-4`

***

### /extract-knowledge

Extract insights from source and populate knowledge base.

**Syntax:**

```bash theme={null}
/extract-knowledge "<file-path>" [--mode MODE]
```

<ParamField path="file-path" type="string" required>
  Path to source file or "auto" to use NARRATIVES-STATE.json
</ParamField>

<ParamField path="--mode" type="string" optional>
  Extraction mode: `legacy` (direct from file) or `narratives` (from pipeline output)
</ParamField>

**Modes:**

<CodeGroup>
  ```bash Legacy Mode theme={null}
  /extract-knowledge "inbox/source.txt"
  # Reads raw file directly
  # Extracts insights without pipeline
  ```

  ```bash Narratives Mode (Recommended) theme={null}
  /extract-knowledge "auto"
  # Uses NARRATIVES-STATE.json from pipeline
  # Includes priority scoring and context
  ```
</CodeGroup>

**Extraction Categories:**

1. `01-ESTRUTURA-TIME` - People structure, roles
2. `02-PROCESSO-VENDAS` - Selling process, techniques
3. `03-CONTRATACAO` - Hiring, onboarding
4. `04-COMISSIONAMENTO` - Compensation, commissions
5. `05-METRICAS` - Performance metrics
6. `06-FUNIL-APLICACAO` - Lead qualification, pipeline
7. `07-PRICING` - Pricing strategy
8. `08-FERRAMENTAS` - Tools, tech stack
9. `09-GESTAO` - Management practices
10. `10-CULTURA-GAMIFICACAO` - Culture, motivation
11. `99-SECUNDARIO` - Other insights

**Output Structure:**

```
/knowledge/SOURCES/{SOURCE-NAME}/{CATEGORY}/{topic}.md
```

**Source:** `.claude/commands/extract-knowledge.md:1-508`

***

## Knowledge Management

### /dossiers

View or update person/theme dossiers.

**Syntax:**

```bash theme={null}
/dossiers [--person "Name" | --theme "topic" | --list]
```

**Source:** `.claude/commands/dossiers.md:1-6`

***

### /view-dna

View DNA structure for person or agent.

**Syntax:**

```bash theme={null}
/view-dna <person-or-agent-name> [--layer LAYER]
```

<ParamField path="name" type="string" required>
  Person or agent name
</ParamField>

<ParamField path="--layer" type="string" optional>
  Specific DNA layer: `L1` (PHILOSOPHIES), `L2` (MENTAL-MODELS), `L3` (HEURISTICS), `L4` (FRAMEWORKS), `L5` (METHODOLOGIES)
</ParamField>

**DNA Layers:**

* **L1: PHILOSOPHIES** - Core beliefs, worldview
* **L2: MENTAL-MODELS** - Thinking frameworks
* **L3: HEURISTICS** - Practical rules, shortcuts
* **L4: FRAMEWORKS** - Structured methodologies
* **L5: METHODOLOGIES** - Step-by-step implementations

**Source:** `.claude/commands/view-dna.md:1-8`

***

## Session Management

### /save

Save current session state.

**Syntax:**

```bash theme={null}
/save [session-name]
```

<ParamField path="session-name" type="string" optional>
  Custom session name. If omitted, uses timestamp.
</ParamField>

**Saved State:**

* JARVIS state and context stack
* Processing phase and position
* Pending decisions and items
* Conversation history

**Location:** `/.claude/jarvis/SESSION-{timestamp}.md`

**Source:** `.claude/commands/save.md:1-9`

***

### /resume

Resume previous session.

**Syntax:**

```bash theme={null}
/resume [session-id]
```

<ParamField path="session-id" type="string" optional>
  Specific session ID to resume. If omitted, resumes most recent.
</ParamField>

**Source:** `.claude/commands/resume.md:1-5`

***

## System Commands

### /system-digest

Generate system health and metrics digest.

**Syntax:**

```bash theme={null}
/system-digest [--full]
```

<ParamField path="--full" type="flag" optional>
  Include detailed breakdown per agent and knowledge domain
</ParamField>

**Metrics:**

* Total agents: minds (5), cargo (14), conclave (3)
* Knowledge base: sources, dossiers, themes
* Pipeline status: processed files, pending items
* Agent memory freshness
* Recent errors and warnings

**Source:** `.claude/commands/system-digest.md:1-8`

***

### /verify

Run 6-level verification protocol.

**Syntax:**

```bash theme={null}
/verify [--level LEVEL] [--fix]
```

<ParamField path="--level" type="string" optional>
  Specific level: `L1` (syntax), `L2` (schema), `L3` (references), `L4` (consistency), `L5` (completeness), `L6` (semantic)
</ParamField>

<ParamField path="--fix" type="flag" optional>
  Auto-fix detected issues where possible
</ParamField>

**Verification Levels:**

1. **L1: Syntax** - File structure, YAML validity, JSON schemas
2. **L2: Schema** - Compliance with core schemas
3. **L3: References** - Foreign key integrity, broken links
4. **L4: Consistency** - Cross-file consistency, entity canonicalization
5. **L5: Completeness** - Required fields, minimum thresholds
6. **L6: Semantic** - Logical coherence, narrative quality

**Source:** `.claude/commands/verify.md:1-9`

***

## Notes

<Note>
  All slash commands are defined in `.claude/commands/` and auto-indexed by `skill_router.py`.
</Note>

<Warning>
  Commands that modify state (create-agent, process-jarvis) create automatic backups in `/.claude/jarvis/CHECKPOINTS/`.
</Warning>