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/statusgit 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/status)<a href="https://agentmods.dev/commands/maxwellsdm1867/wheeler/status"><img src="https://agentmods.dev/badge/commands/maxwellsdm1867/wheeler/status.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 | $0.00024 | $0.01182 |
| Opus 5 | $0.00012 | $0.00591 |
| Sonnet 5 | $0.00005 | $0.00236 |
| Haiku 4.5 | $0.00002 | $0.00118 |
Grade A, and why
wh:status 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 4d 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.
Connectivity Check
Before proceeding: call graph_health. If it returns "status": "offline",
STOP. Tell the user Neo4j is not running and provide the remediation steps
from the error response. Offer to retry after they start it. Do not continue
with other work.
Show the current state of everything and suggest what to do next.
Step 0a: Check for updates
Read ~/.cache/wheeler/version-check.json if it exists. If update_available is true, show a banner at the top of the output:
⬆ Wheeler X.Y.Z available (you have A.B.C) — run /wh:update
Step 0b: Query graph for all plans (graph-first)
Call query_plans() (all statuses) and group results by status. This is the authoritative plan index. Also read .plans/STATE.md if it exists as a supplementary narrative. If STATE.md and graph disagree on any plan's status, the graph wins; flag the drift.
Step 1: Investigation Status
From the graph query results, show:
- Plans by status: in-progress, approved (ready to execute), draft (needs review), completed
.continue-here.md— paused work from a previous session (auxiliary narrative)*-CONTEXT.md— discussions that haven't been planned yet
Step 2: Task Status
Team tasks (check first)
Use TaskList to check for active agent team tasks. If a team exists, show:
- Completed tasks (with brief results)
- In-progress tasks
- Flagged checkpoints needing judgment
- Pending/blocked tasks
Headless logs (fallback)
If no team tasks found, check .logs/:
- Run
python -m wheeler.log_summaryvia Bash - Unreviewed completed tasks
- Flagged checkpoints needing judgment
- Failed tasks
Step 3: Graph Status
Use wheeler MCP tools:
graph_status— node counts by typequery_findings— 5 most recent findings with confidence scoresquery_open_questions— top 5 open questions by prioritygraph_gaps— unsupported hypotheses, unlinked questionsdetect_stale— analyses with changed scriptsquery_review_queue— results a service harvest landed that nobody has read yet. This one is easy to lose track of: the work is paid for and sitting in the graph, unjudged. Report it per batch (<N> undiscussed from <batch>) whenever it is non-empty.
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.
- 4d ago First seen · 109 lines · 24 tokens per session scan A 6cd23223712e
wh:status is a command published in the GitHub repository maxwellsdm1867/wheeler (10 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 1,182 once invoked, about $0.0001 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.