Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/maxwellsdm1867/wheeler/servicegit 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/service)<a href="https://agentmods.dev/commands/maxwellsdm1867/wheeler/service"><img src="https://agentmods.dev/badge/commands/maxwellsdm1867/wheeler/service.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.01416 |
| Opus 5 | $0.00036 | $0.00708 |
| Sonnet 5 | $0.00015 | $0.00283 |
| Haiku 4.5 | $0.00007 | $0.00142 |
Grade A, and why
wh:service 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 3d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Wheeler's service router. You SELECT the right external service for a task, INTERVIEW the scientist for that service's inputs, SHOW the assembled request, and only then DISPATCH the service's own act. The service list is data from the registry, not prose in this file: never hardcode a service table, and never invent a service. No em dashes.
1. Load the available services
The registry knows every enabled service whose availability probe passes (across all providers: Asta, LLM-SR, local). Read it:
./.venv/bin/python -c "from wheeler.config import load_config; from wheeler.integrations.registry import available_services; import json; print(json.dumps([{'id': c.id, 'name': c.name, 'provider': c.provider, 'act': c.act, 'kind': c.kind, 'cost': c.cost, 'when': c.when, 'description': c.description} for c in available_services(load_config())], indent=2))"
If the list is empty, tell the scientist no services are available (none enabled, or none pass their probe, for example Asta not authenticated) and stop.
2. Select the service
- Direct name: if
$ARGUMENTSnames a serviceid/name(for example/wh:service llmsr-discoveror/wh:service paper-finder), select it directly. - Intent match: otherwise read graph context if useful (
search_context) and match the task against each service'swhen+description. If exactly one fits, select it. If several could fit, use AskUserQuestion to let the scientist pick (options drawn from the matching services, labeled withname+cost). If none fit, say so and suggest/wh:startfor general Wheeler routing, then stop. - Empty
$ARGUMENTS: AskUserQuestion first, offering the available services.
3. Cost gate
Before going further, if the chosen service's cost is not "free" or "cheap"
(for example Theorizer at about 7 dollars and 20 minutes, or llmsr-discover
"slow, minutes"), state the cost and time and confirm with the scientist. Stop if
they decline.
4. Interview for the service's inputs (the load-bearing step)
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.
- 3d ago First seen · 110 lines · 73 tokens per session scan A 92933937f093
wh:service is a command published in the GitHub repository maxwellsdm1867/wheeler (10 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 1,416 once invoked, about $0.0004 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
analysis
You are the Analysis Agent for NanoResearch. Your job is to analyze experiment results and produce structured findings.
status
Show the current status of a NanoResearch workspace.
search
Fuzzy-search CrossRef by title. Args: "title query.
migrate-server
迁移服务器端旧项目数据到 v5 结构.
rebuttal-init
交互式初始化 Rebuttal 项目.
git
Git operations with intelligent commit messages and workflow optimization.