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/graph-linkgit 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/graph-link)<a href="https://agentmods.dev/commands/maxwellsdm1867/wheeler/graph-link"><img src="https://agentmods.dev/badge/commands/maxwellsdm1867/wheeler/graph-link.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 | $0.00030 | $0.02047 |
| Opus 5 | $0.00015 | $0.01024 |
| Sonnet 5 | $0.00006 | $0.00409 |
| Haiku 4.5 | $0.00003 | $0.00205 |
Grade A, and why
wh:graph-link 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 — 163 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, running a session-scoped provenance grouping pass. Your job: find orphan nodes (no WAS_GENERATED_BY link) created in the current session, group them by inferred provenance, propose Execution nodes that capture the work, and apply the links only after the scientist approves the whole batch.
This is a complement to /wh:close, not a replacement. /wh:close finds orphans and walks the scientist through one-by-one fixes; this command groups them upfront so the scientist makes one decision per logical Execution instead of N decisions per node.
Safety Rules: READ THESE FIRST
- NEVER auto-create links. Always present the full grouped proposal and wait for approval.
- NEVER fabricate provenance. If you cannot infer a sensible Execution from the orphan cluster, propose adding it to a "needs scientist review" group.
- NEVER delete nodes or modify existing relationships. This command only adds.
- Papers are never orphans. They are reference entities, not produced by Wheeler.
- Executions are never orphans. They ARE the provenance.
Phase 1: Scope the Sweep
Determine the orphan set:
-
Parse
$ARGUMENTS:--session <id>: scope to nodes withn.session_id = <id>--last <hours>: scope to nodes withcoalesce(n.updated, n.date) >= datetime() - duration({hours: <N>})- Default (no args): use
--last 4(matches/wh:closewindow) AND scope to current MCP session_id when known
-
Find orphans with the corresponding Cypher (substitute parameters from args):
MATCH (n) WHERE coalesce(n.updated, n.date) IS NOT NULL AND datetime(coalesce(n.updated, n.date)) >= datetime() - duration({hours: $hours}) AND NOT n:Execution AND NOT n:Paper AND NOT (n)-[:WAS_GENERATED_BY]->(:Execution) RETURN n.id AS id, labels(n)[0] AS type, n.title AS title, n.path AS path, n.session_id AS session, coalesce(n.updated, n.date) AS timestamp ORDER BY type, timestamp
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 · 163 lines · 30 tokens per session scan A d9792b8c7638
wh:graph-link is a command published in the GitHub repository maxwellsdm1867/wheeler (10 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 2,047 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
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.