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/asta-assistantgit 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/asta-assistant)<a href="https://agentmods.dev/commands/maxwellsdm1867/wheeler/asta-assistant"><img src="https://agentmods.dev/badge/commands/maxwellsdm1867/wheeler/asta-assistant.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 5.1 | $0.00079 | $0.02874 |
| Opus 5 | $0.00039 | $0.01437 |
| Sonnet 5 | $0.00016 | $0.00575 |
| Haiku 4.5 | $0.00008 | $0.00287 |
Grade A, and why
wh:asta-assistant 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 6d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Wheeler, bridging the Asta Research Assistant (Ai2's asta-assistant plugin: a long-range autonomous research loop) with the knowledge graph. This is NOT a one-shot tool call, and you never run the loop yourself. It has two moves: SEED a self-contained mission folder from the graph, and HARVEST the completed work back into the graph. The scientist drives the loop in between.
Because the loop is long-horizon and goal-driven, a harvest is a BATCH: it can land a dozen outcomes the scientist has not read. Saving that work and judging it are two different jobs at two different times. This act does the saving and hands over a page to read; /wh:discuss <slug> does the judging.
How this routes through plan mode
The loop is human-driven, so it fits a plan as a hand-off step:
/wh:plannames a mission ("run an asta-assistant mission on ") as a step and passes its Plan id.- At execute time (
/wh:executecalls this act, or you call it directly), the SEED move builds the mission folder and hands you a copy-paste run block. The plan step is now "in progress, awaiting the external loop." - You
cdinto the folder in a separate terminal and drive the loop. The folder is self-contained: a fresh session reads it and keeps going. - When the loop is done, you return here (that is the ping) and the HARVEST move indexes the work, renders the brief, and leaves the outcomes queued. The plan step completes when
/wh:discuss <slug>endorses which of them are results.
Preflight
- Confirm Asta is installed:
asta --version. If not, say the Asta Research Assistant is unavailable (needs theastaCLI plus theasta-assistantplugin) and stop. ls .wheeler/asta-assistant/to see existing missions (ignore the error if absent).
Decide the move
$ARGUMENTSstarts withharvest(or names an existing mission slug) -> Harvest.- Otherwise -> Seed (treat
$ARGUMENTSas the mission request; if empty, ask for it or offer to harvest an existing mission).
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.
- 6d ago First seen · 153 lines · 79 tokens per session scan A 08d3c50669b6
wh:asta-assistant is a command published in the GitHub repository maxwellsdm1867/wheeler (10 stars, last pushed 4d ago), licensed MIT. It adds 79 tokens to every session and 2,874 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.
rebuttal-init
交互式初始化 Rebuttal 项目.
migrate-server
迁移服务器端旧项目数据到 v5 结构.
checklist
Generate a custom checklist for the current feature based on user requirements.