wheeler: Command for Claude Code

.claude/commands/wh/asta-theorize.md

wh:asta-theorize is a command for Claude Code from maxwellsdm1867/wheeler. It costs 30 tokens per session (1,640 once invoked), scanned A, original, MIT.

A Wheeler command that asks Asta Theorizer to propose candidate explanations for a research question and records them in Wheeler's knowledge graph.

In plain words
What is it for?
Use it to shape a question, check existing findings, generate possible theories through Asta, and link the results to the research graph.
Why use it?
It helps turn an investigation question and the existing research context into theories that can be tracked with their sources and relationships.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is maxwellsdm1867/wheeler's own configuration. It tells Claude Code how to work on wheeler itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything wheeler configures →

Part of the wh plugin — 41 skills, 40 commands, 2 agents, 3 hooks, 5 MCP servers shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to maxwellsdm1867/wheeler. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/maxwellsdm1867/wheeler/main/.claude/commands/wh/asta-theorize.md
Clone the repo
git clone --depth 1 https://github.com/maxwellsdm1867/wheeler

Made for: Claude Code.

Or install wh, the plugin that ships this one along with the rest of its 41 skills, 40 commands, 2 agents, 3 hooks, 5 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for wh:asta-theorize

README.md
[![agentmods](https://agentmods.dev/badge/commands/maxwellsdm1867/wheeler/asta-theorize.svg)](https://agentmods.dev/commands/maxwellsdm1867/wheeler/asta-theorize)
Your own site
<a href="https://agentmods.dev/commands/maxwellsdm1867/wheeler/asta-theorize"><img src="https://agentmods.dev/badge/commands/maxwellsdm1867/wheeler/asta-theorize.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,640 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.01640
Opus 5 $0.00015 $0.00820
Sonnet 5 $0.00006 $0.00328
Haiku 4.5 $0.00003 $0.00164

Measured 8d ago against content hash 6f54ec12c4fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

wh:asta-theorize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/wh/asta-theorize.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Wheeler, running an Asta Theorizer pass over a research question and marshalling the candidate theories into the knowledge graph. You orchestrate; the asta CLI generates the theories and owns its own auth and timeouts; one deterministic wheeler integrate verb writes the graph.

Preflight

  1. Confirm Asta is installed: asta --version. If that fails, say Asta is not available and stop. Do not attempt generation.
  2. Read context so the question is shaped by the graph. Use mcp__wheeler_core__search_context with the user's question (or the active question) to see what is already known: existing findings, hypotheses, and gaps. Use mcp__wheeler_query__query_findings to see what results already exist. Use this only to sharpen the intervention, outcome, and scope of the question and to choose a link target. Do not invent theories.
  • The question is $ARGUMENTS when provided. If empty, ask the user for a question or derive one from the active investigation.
  • Sharpen it from the graph context: name the intervention or mechanism, the outcome, and the scope (system, population, regime). A crisp question yields crisper theories.
  • Pick at most one link target: the Question (Q-...) or Plan (PL-...) this generation supports. Each theory's parent node will be linked AROSE_FROM that node. If there is no clear target, run without one.

Run the generation

Run the CLI, capturing the artifact to a temp file. This requires an Asta login. The subcommand takes no positional argument: the question goes in --theory-query (required), and any scoping constraint you sharpened above (system, population, regime) goes in --mission-statement (optional). There is no output flag, so redirect stdout to the artifact path:

asta generate-theories literature-theory-generation --theory-query "$QUESTION" --mission-statement "$SCOPE" > /tmp/asta-theorizer.json

Drop --mission-statement when there is no scoping constraint. Because the artifact arrives on stdout, the redirect creates the file whether or not the run succeeded: check the exit status, never the file's existence.

Read the full file on GitHub · 72 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 72 lines · 30 tokens per session scan A 6f54ec12c4fa

Subscribe to this mod's changes

wh:asta-theorize is a command published in the GitHub repository maxwellsdm1867/wheeler (11 stars, last pushed 6d ago), licensed MIT. It adds 30 tokens to every session and 1,640 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other commands, from other repositories

planning

You are the Planning Agent for NanoResearch. Your job is to design a detailed experiment blueprint from the ideation output.

OpenRaiser/NanoResearch · 0 tokens

analysis

You are the Analysis Agent for NanoResearch. Your job is to analyze experiment results and produce structured findings.

OpenRaiser/NanoResearch · 0 tokens

cite-check

Verify that citations actually exist and that the claims they support are faithful to the cited source. Runs deterministic existence checks (Crossref / OpenAlex / Semantic Scholar / arXiv) plus a claim-faithfulness pass via the alterlab-citation-verifier skill.

AlterLab-IEU/AlterLab-Academic-Skills · 56 tokens

replication-package

Scaffold or audit a social-science replication package at a target directory, and audit the manuscript and its archived research objects against FAIR principles.

scdenney/open-science-skills · 0 tokens

paper-review-lite

Run a Critical-Reviewer-style pre-submission audit of the current paper using parallel sub-agents inside Claude Code. Adversarial and quote-grounded, with a verification cross-check to filter hallucinations. Covers content and argument, numerical consistency, references and DOIs, writing quality, figures and…

scdenney/open-science-skills · 0 tokens

literature-review

Build or audit a literature review for the task below. Produce an evidence map, closest-prior-work assessment, gap verdict, source-cluster structure, and synthesis plan that can feed into narrative-building, hypothesis-building, or pre-registration-writing.

scdenney/open-science-skills · 0 tokens