profile

name	profile
description	Inspect the operator profile. Auto-run when: conversation reveals a behavioral pattern or preference not yet in the profile, after extended interaction generating new observations, or user asks about their profile or dimensions. Invoke proactively without asking.

Show the operator profile summary and dimension breakdown.

Default (no args): Read the distilled manifest and show a summary:

cd ~/projects/hapax-council && jq '{
  name: .operator.name,
  goals: [.goals.primary[] | {name, status}],
  patterns: (.patterns | keys),
  constraints: (.constraints | length),
  neurocognitive: (.neurocognitive | length)
}' profiles/operator.json

Then read the full profile and show per-dimension fact counts:

cd ~/projects/hapax-council && uv run python -c "
import json
p = json.load(open('profiles/operator-profile.json'))
for dim, facts in sorted(p.get('dimensions', {}).items()):
    count = len(facts) if isinstance(facts, list) else len(facts) if isinstance(facts, dict) else 0
    print(f'  {dim}: {count} facts')
"

With dimension arg (e.g., /profile neurocognitive): Show the facts for that specific dimension from profiles/operator-profile.json.

With --refresh flag: Run the profiler to update:

cd ~/projects/hapax-council && LITELLM_API_KEY=$(pass show litellm/master-key) uv run python -m agents.profiler --auto