introspect

/introspect — Framework Deep Self-Analysis

When to use

When the user says "introspect", "self-analysis", "framework health check", "what needs improvement", "audit the framework", "what's missing", "framework inventory", or wants a structured assessment of the Torus framework's current state.

Hard Limits (read before executing anything)

• Read-only — never modify any files during introspection
• Always search memory for previous introspect results before starting
• Always save results to memory after completing the report
• Show raw numbers in all tables (no rounding percentages to hide detail)
• If any scan step fails, record the failure and continue — partial data is better than none

---

Phase 1: SCAN — Enumerate All Framework Components

Collect a complete inventory. Run ALL of the following:

Gates:

ls ~/.claude/hooks/gates/gate_*.py 2>/dev/null | sort
ls ~/.claude/hooks/gates/gate_*.py 2>/dev/null | wc -l

For each gate file, extract its gate number and name:

python3 -c "
import os, re
gate_dir = os.path.expanduser('~/.claude/hooks/gates')
gates = sorted(f for f in os.listdir(gate_dir) if f.startswith('gate_') and f.endswith('.py'))
for g in gates:
    path = os.path.join(gate_dir, g)
    with open(path) as f:
        content = f.read()
    # Extract gate name from GATE_NAME constant or first docstring
    name_match = re.search(r'GATE_NAME\s*=\s*[\"\'](.*?)[\"\']', content)
    num_match = re.search(r'gate_(\d+)', g)
    lines = content.count('\n')
    name = name_match.group(1) if name_match else '(unnamed)'
    num = num_match.group(1) if num_match else '?'
    print(f'  Gate {num:>2}: {g:<30} {lines:>4} lines  name={name}')
"

Skills:

ls ~/.claude/skill-library/*/SKILL.md 2>/dev/null
ls ~/.claude/skill-library/*/SKILL.md 2>/dev/null | wc -l

For each skill, extract name and description:

python3 -c "
import os, re
skills_dir = os.path.expanduser('~/.claude/skill-library')
for skill in sorted(os.listdir(skills_dir)):
    skill_path = os.path.join(skills_dir, skill, 'SKILL.md')
    if os.path.exists(skill_path):
        with open(skill_path) as f:
            content = f.read()
        desc_match = re.search(r'^description:\s*>?\s*\n\s+(.*)', content, re.MULTILINE)
        inline_match = re.search(r'^description:\s+(.+)$', content, re.MULTILINE)
        desc = (desc_match or inline_match)
        desc_text = desc.group(1)[:60] if desc else '(no description)'
        lines = content.count('\n')
        print(f'  {skill:<20} {lines:>4} lines  {desc_text}')
"