isomorphic-hunter

name	isomorphic-hunter
description	Cross-domain isomorphic pattern forge. Dokkado Five Rings x meta-pattern 3+ domain validation, with arxiv evidence hunting and smithery tool discovery. RSI-refined. Finds what's ACTUALLY universal.
tier	e
morpheme	tau
dewey_id	e.3.1.15
composition	true
version	1
dependencies	["dokkado","meta-pattern-recognition","recursive-refiner","arxiv-search","gremlin-brain-v2"]
parents	["dokkado (Five Rings backbone)","meta-pattern-recognition (3+ domain gate)"]

Isomorphic Hunter

The skill that hunts what's real across domains.

Collision offspring: dokkado x meta-pattern-recognition, armed with arxiv search and smithery tool discovery, refined by recursive-refiner RSI loops.

Not "this looks similar." IS this the same structure? Prove it or kill it.

---

The Hunt Protocol

Phase 0: ARM (Load Tools)

Before hunting, check what weapons are available.

# Search arxiv for prior art on the target pattern
# (uses arxiv-mcp-server or direct API)
arxiv_search() {
    local query="$1"
    # MCP server if available
    if command -v npx &>/dev/null; then
        echo "$query" | npx arxiv-mcp-server 2>/dev/null
    else
        # Direct API fallback
        curl -s "http://export.arxiv.org/api/query?search_query=all:$(echo "$query" | tr ' ' '+')" \
            | python3 -c "
import sys, xml.etree.ElementTree as ET
root = ET.parse(sys.stdin).getroot()
ns = {'a': 'http://www.w3.org/2005/Atom'}
for entry in root.findall('a:entry', ns)[:5]:
    title = entry.find('a:title', ns).text.strip().replace('\n',' ')
    summary = entry.find('a:summary', ns).text.strip()[:200]
    link = entry.find('a:id', ns).text.strip()
    print(f'PAPER: {title}')
    print(f'  URL: {link}')
    print(f'  {summary}...')
    print()
" 2>/dev/null
    fi
}

# Search smithery.ai for relevant MCP tools
smithery_search() {
    local query="$1"
    curl -s "https://registry.smithery.ai/servers?q=$(echo "$query" | tr ' ' '+')" 2>/dev/null \
        | python3 -c  2>/dev/null
}