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/backupgit 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/backup)<a href="https://agentmods.dev/commands/maxwellsdm1867/wheeler/backup"><img src="https://agentmods.dev/badge/commands/maxwellsdm1867/wheeler/backup.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 | $0.00034 | $0.00972 |
| Opus 5 | $0.00017 | $0.00486 |
| Sonnet 5 | $0.00007 | $0.00194 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
wh:backup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Snapshot the Wheeler knowledge graph plus all canonical files into a single
tar.gz archive. This shells out to the wheeler backup CLI subcommand on
purpose: the MCP transport caps tool results at ~235k chars and a real
graph dump saturates that immediately. The CLI runs in-process and is not
affected.
What gets included
By default (--scope project) the full project_root tree is packed:
knowledge/(all per-node JSON metadata)synthesis/(Obsidian-compatible markdown).plans/,.notes/,.logs/,docs/,scripts/, and all other project directories.wheeler/(embeddings, request log, repair queue; excludes.wheeler/backups/to prevent recursion)wheeler.yaml(config; the Neo4j password is stripped to${NEO4J_PASSWORD})graph_nodes.jsonl(one JSON object per node, full properties; paths rewritten to${PROJECT}/...)graph_relationships.jsonl(one per relationship, source + type + target + props)manifest.json(timestamp, version, counts, SHA-256 hashes, embedder info, manifest_version, archive_uuid, external_references, excluded_paths, manifest_signature)
Use --scope graph-only for the smaller v1-style metadata-only archive
(knowledge/, synthesis/, .wheeler/, wheeler.yaml plus graph JSONL, no full
project tree).
Artifact safety
A secret scan runs over all packed files by default. If any file contains
patterns that look like Anthropic API keys, the backup is aborted and the
offending files and patterns are listed. The scanned pattern set lives in
wheeler/portability.py. Pass --allow-secrets to override (not recommended).
The wheeler.yaml password field is always stripped to ${NEO4J_PASSWORD}
regardless.
Path portability
Paths stored in graph nodes (Finding.path, Dataset.path, Script.path, etc.)
are rewritten from absolute to ${PROJECT}/... inside the archive. Live
files on disk are never modified. On restore, ${PROJECT}/... is expanded
back to the absolute path of the recipient's project root.
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 · 107 lines · 34 tokens per session scan A c539516d7c4d
wh:backup is a command published in the GitHub repository maxwellsdm1867/wheeler (10 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 972 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.