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.
curl -O https://raw.githubusercontent.com/maxwellsdm1867/wheeler/main/.claude/commands/wh/llmsr-transfer.mdgit clone --depth 1 https://github.com/maxwellsdm1867/wheelerWrote 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.
[](https://agentmods.dev/commands/maxwellsdm1867/wheeler/llmsr-transfer)<a href="https://agentmods.dev/commands/maxwellsdm1867/wheeler/llmsr-transfer"><img src="https://agentmods.dev/badge/commands/maxwellsdm1867/wheeler/llmsr-transfer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/maxwellsdm1867/wheeler/llmsr-transfer"><img src="https://agentmods.dev/badge/commands/maxwellsdm1867/wheeler/llmsr-transfer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.02523 |
| Opus 5 | $0.00022 | $0.01262 |
| Sonnet 5 | $0.00009 | $0.00505 |
| Haiku 4.5 | $0.00004 | $0.00252 |
Grade A, and why
wh:llmsr-transfer 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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Wheeler, running an LLM-SR generalization test and marshalling BOTH of its numbers into the knowledge graph. The wheeler llmsr transfer verb refits a discovered equation's constants from scratch on a table the search never scored; one deterministic wheeler integrate verb writes the graph. No model is called anywhere in this act: there is no search here, no generator, no sub-agent.
The whole point of this act is that "does it generalize" is TWO questions, and they must never collapse into one number.
- Does the FORM transfer? Refit the constants on the new data under the same functional form. A law that governs a new cell with different constants is the SAME law. This is what symbolic regression is looking for.
- Do the CONSTANTS transfer? Apply the source run's own fitted constants unchanged. This is a different and strictly weaker question.
The verb reports both, labelled. You must too. Never present the refit number as plain generalization, and never let either stand in for the other.
Preflight
- Run
wheeler llmsr --help. Treat the tool as unavailable if the command exits non-zero or its output containsUNAVAILABLE:(a zero exit alone is not enough: when the engine fails to import, Wheeler still registers the command group as a stub so the cause stays visible). Report the cause the output actually shows, quoting it verbatim, and stop./wh:llmsr-discover's preflight section has the full diagnosis tree if the message is ambiguous; do not guess a cause the output does not support. - Confirm the RUN exists and is finished:
wheeler llmsr status --run <run id or dir>. Reportphaseverbatim. A run still infittingcan be transferred (the verb only reads), but say so rather than implying the search is complete. - Read context so the test is shaped by the graph. Use
mcp__wheeler_core__search_contexton the request andmcp__wheeler_query__query_datasets/query_open_questions/query_hypothesesto find the held-out recording, the motivating question, and any hypothesis about the functional form this bears on. Post a one-line preamble naming what you found.
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.
- 8d ago First seen · 109 lines · 44 tokens per session scan A 2c2a4f65fed6
wh:llmsr-transfer is a command published in the GitHub repository maxwellsdm1867/wheeler (11 stars, last pushed 7d ago), licensed MIT. It adds 44 tokens to every session and 2,523 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.
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.
analysis
You are the Analysis Agent for NanoResearch. Your job is to analyze experiment results and produce structured findings.
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.
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.
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…
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.