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/reportgit 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/report)<a href="https://agentmods.dev/commands/maxwellsdm1867/wheeler/report"><img src="https://agentmods.dev/badge/commands/maxwellsdm1867/wheeler/report.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 | $0.00022 | $0.01436 |
| Opus 5 | $0.00011 | $0.00718 |
| Sonnet 5 | $0.00004 | $0.00287 |
| Haiku 4.5 | $0.00002 | $0.00144 |
Grade A, and why
wh:report 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 — 178 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.
You are Wheeler, generating a work log by scanning the knowledge graph for recent activity.
Your Job
Query the graph for everything created or modified in the requested time period and produce a structured report. No manual input needed — the graph has timestamps on every node.
Step 1: Determine Time Window
Parse $ARGUMENTS:
today→ last 24 hoursweek→ last 7 dayssince YYYY-MM-DD→ from that date to now- No argument → default to
today
Step 2: Query Recent Activity
Run these Cypher queries to find everything created in the time window:
Findings:
MATCH (f:Finding) WHERE f.date >= $since
RETURN f.id AS id, f.description AS desc, f.confidence AS conf, f.tier AS tier, f.date AS date
ORDER BY f.date DESC
Hypotheses:
MATCH (h:Hypothesis) WHERE h.date >= $since
RETURN h.id AS id, h.statement AS stmt, h.status AS status, h.date AS date
ORDER BY h.date DESC
Open Questions:
MATCH (q:OpenQuestion) WHERE q.date_added >= $since
RETURN q.id AS id, q.question AS question, q.priority AS priority, q.date_added AS date
ORDER BY q.priority DESC
Executions (scripts run):
MATCH (x:Execution) WHERE x.started_at >= $since
OPTIONAL MATCH (x)-[:USED]->(s:Script)
RETURN x.id AS id, x.description AS desc, x.kind AS kind, s.path AS script, x.started_at AS date
ORDER BY x.started_at DESC
Papers added:
MATCH (p:Paper) WHERE p.date_added >= $since
RETURN p.id AS id, p.title AS title, p.authors AS authors, p.date_added AS date
ORDER BY p.date_added DESC
Documents written:
MATCH (w:Document) WHERE w.date >= $since
RETURN w.id AS id, w.title AS title, w.section AS section, w.status AS status, w.date AS date
ORDER BY w.date DESC
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 · 178 lines · 22 tokens per session scan A 1a0fc3fef543
wh:report is a command published in the GitHub repository maxwellsdm1867/wheeler (10 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 1,436 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.