research
01Command
Activates anti-hallucination constraints based on Anthropic's documentation. Stay in this mode until the user says to exit.
149 4mo ago A 0 tokens
arxiv-search
02Command
Search arXiv by free text; surfaces published DOIs ready to verify. Args: "query" [--max=10] [--sort=relevance] [--id=2401.12345].
23 10d ago A 0 tokens
audit
03Command
Audit citations in a directory against a BibTeX file. Args: --bibtex= [--json] [--verbose].
23 10d ago A 0 tokens
prose-audit
04Command
Lint paper drafts for AI-tell prose patterns. Args: [--severity=warn] [--no-pencil] [--no-muriel] [--no-native] [--summary] [--json].
23 10d ago A 0 tokens
agy-search
05Command Claude Code
Web search via agy (Google Antigravity CLI) — agy grounded web search with source citations (for general search prefer the WebSearch tool).
15 8d ago A 31 tokens
wh:dream
06Command Claude Code
Use when the Wheeler knowledge graph needs consolidation (tier promotion, orphan linking, staleness detection).
10 4d ago A 24 tokens
original MIT
wh:execute
07Command Claude Code
Use only when the user asks to run or execute a Wheeler plan that already exists in .plans/.
10 4d ago A 24 tokens
original MIT
Command Claude Code
Use when the user wants to discover or fit a closed-form equation from a dataset via LLM-SR and ingest the result into the Wheeler knowledge graph.
10 4d ago A 38 tokens
original MIT
board
09Command
A command for managing Consilium, a personal board of AI representations of real thinkers grounded in public-domain texts.
6 12d ago A 59 tokens
original MIT
research
10Command
Deep research on Claude models — full multi-agent loop, plan-only, or resume a run. Persists cited evidence to runs/ /.
1 3mo ago A 29 tokens
original MIT
Command
Use Notebooklab through the first-party MCP server.
1 7d ago A 0 tokens
original MIT