open-gitagent/opengap

# Document Review

## Instructions
When reviewing a financial document:

1. **Classify the document** — Determine document type (prospectus, ADV, customer agreement, marketing material, etc.)
2. **Identify applicable rules** — Map to FINRA 2210 (communications), SEC disclosure requirements, etc.
3. **Check required elements** — Verify all required disclosures, disclaimers, and content are present
4. **Assess accuracy** — Flag potentially misleading, exaggerated, or promissory statements
5. **Check balance** — Per FINRA 2210, ensure risks and benefits are presented in a balanced manner
6. **Review formatting** — Verify required prominence of disclosures

## Key Checks
- [ ] All required disclosures present

# Regulatory Analysis

## Instructions
When analyzing a document or process for regulatory compliance:

1. **Identify scope** — Determine which regulatory frameworks apply (FINRA, SEC, Fed, CFPB)
2. **Map to rules** — Identify specific rules, notices, and guidance documents relevant to the subject
3. **Assess compliance** — Evaluate the subject against each applicable requirement
4. **Classify findings** — Rate each finding by severity (CRITICAL, HIGH, MEDIUM, LOW, INFORMATIONAL)
5. **Recommend remediation** — Provide specific, actionable steps to address each finding
6. **Assess confidence** — Rate your confidence in each finding (HIGH, MEDIUM, LOW)
7. **Validate citations** — Verify all cited rules exist and are current before finalizing

## Regulatory Priority Order

# Create & Configure Agents

## Quick Start

1. Create directory structure: `mkdir -p my-agent/skills`
2. Write `agent.yaml` with required fields (see below)
3. Create `SOUL.md` with agent identity
4. Add skills, tools, and knowledge as needed
5. Validate: `opengap validate -d ./my-agent`

## agent.yaml Reference

### Required Fields
```yaml

# Export & Import Agents

## Verify Export

After exporting, check the output matches expectations:

```bash
# Verify export file was created and contains agent name
opengap export -f system-prompt -d ./my-agent | head -5
```

## Export

Convert a gitagent definition to another framework:

# Get Started with gitagent

## When to Use
When a user is new to gitagent, wants to set up their first agent, or asks "how do I start?"

## Instructions

### Installation
```bash
npm install -g @open-gitagent/opengap
opengap --version
```

### Create Your First Agent

# Manage Skills

## When to Use
When a user wants to find skills, install them, create new ones, or understand the skills system.

## Verify Installation

After installing a skill, confirm it's available:

```bash
opengap skills list -d ./my-agent | grep "code-review"
```

## Search Skills

# Run Agents

## When to Use
When a user wants to run an agent locally, from a git repo, or with a specific adapter/framework.

## Troubleshooting

If you see authentication errors:
- **Claude**: Ensure Claude Code is authenticated (`claude auth status`)
- **OpenAI**: Verify `OPENAI_API_KEY` is set and valid
- **GitHub**: Check `GITHUB_TOKEN` has correct permissions
- **Lyzr**: Confirm `LYZR_API_KEY` is active

## Basic Usage

# Compute Ladder

## Tier Definitions

```
Tier 0 — Local (never dies, zero cost)
  ollama/qwen3-coder:latest    primary, MoE, 128 TPS, 64k ctx
  ollama/gpt-oss:20b           fallback, 32k ctx HARD LIMIT

Tier 1 — Fast Free Cloud (up to 2100 TPS)
  cerebras/qwen-3-235b-a22b-instruct-2507   235B MoE, fast free
  cerebras/llama3.1-8b                      8B, ultra-fast light tasks

Tier 2 — Free Cloud (normal latency)

# Narco-Check — Memory Integrity Audit

## When This Runs

1. **Failure trigger:** 2 consecutive failures on the same task or tool
2. **End-of-day trigger:** Nightly deep dive audit (~3 AM)

## Audit Model

Must use `openrouter/anthropic/claude-opus-4.6`. Never run narco-check on a tier-0 or tier-1 model.

```bash
openclaw agent --model openrouter/anthropic/claude-opus-4.6 \
  --message "$(cat ~/.openclaw/workspace/skills/narco-check/audit-prompt.md)" \

# Packet Factory

The packet factory is the gatekeeper between intent and execution. Nothing with a side effect runs without an APPROVED packet.

## Commands

```bash
# Create a new packet (DRAFT status)
skills/packet-factory/new-packet.sh \
  --intent "Post daily update to Slack #arc-angels" \
  --source "Ludo DM 2026-04-01 09:00" \
  --destination "Slack #arc-angels"

# Review a packet (set APPROVED or REJECTED)

# Wiki Ingest

Process a new source document and integrate its knowledge into the wiki.

## Workflow

### Step 1: Read the source
Read the full source document from `knowledge/`. Identify:
- Key entities (people, organizations, concepts, technologies)
- Main claims and findings
- Relationships between entities
- Data points and statistics
- Contradictions with or confirmations of existing knowledge

# Wiki Lint

Audit the wiki for quality and consistency issues.

## Workflow

### Step 1: Read the full index
Read `memory/wiki/index.md` to get the complete page catalog.

### Step 2: Check each category

**Contradictions**
- Scan pages that reference the same entities or concepts
- Flag claims that conflict across pages

# Wiki Query

Answer questions by searching and synthesizing from the wiki.

## Workflow

### Step 1: Search the wiki
1. Read `memory/wiki/index.md` to find relevant pages
2. Use Grep to search for specific terms across `memory/wiki/`
3. Read the most relevant pages (usually 3-10)

### Step 2: Synthesize an answer
- Combine information from multiple wiki pages
- Cite sources: reference both wiki pages and the underlying raw documents

# Research

## Instructions
When researching a topic:
1. Identify the core question or area of interest
2. Break it into 3-5 key subtopics
3. For each subtopic, provide factual information with reasoning
4. Note areas of uncertainty or debate
5. Synthesize findings into a coherent summary

## Output Format
```
## TL;DR
[Brief summary]

# Knowledge Retrieval

Perform semantic search over a pre-ingested document collection using Retrieval-Augmented Generation (RAG). Backed by LlamaIndex with ChromaDB or NVIDIA Foundational RAG.

## When to Use

- Searching internal or pre-ingested documents and reports
- Finding information in PDFs, whitepapers, or technical documentation
- Retrieving domain-specific knowledge not available on the open web
- This is the **highest priority** source — check the knowledge base first before web or paper searches

## How to Use

1. Formulate a semantic search query describing the information needed

# Paper Search

Search for academic papers and scholarly articles via Google Scholar using the Serper API.

## When to Use

- Finding peer-reviewed research on a topic
- Locating seminal papers and their citation counts
- Searching for systematic reviews and meta-analyses
- Grounding claims in academic literature

## How to Use

1. Formulate an academic-style search query

# Web Search

Search the web for current information on any topic using the Tavily search API.

## When to Use

- Searching for recent news, articles, blog posts, and web content
- Finding current statistics, data, and factual information
- Retrieving information that may not be in academic papers or the knowledge base
- Verifying claims with multiple web sources

## How to Use

1. Formulate a specific, targeted search query (max 400 characters)

# Code Review

## Instructions
When reviewing code:
1. Read the full diff or file provided
2. Check for security vulnerabilities (OWASP Top 10)
3. Evaluate error handling completeness
4. Assess code complexity and readability
5. Verify naming conventions and code style
6. Look for performance issues
7. Check for proper input validation

## Output Format
```