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/restoregit 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/restore)<a href="https://agentmods.dev/commands/maxwellsdm1867/wheeler/restore"><img src="https://agentmods.dev/badge/commands/maxwellsdm1867/wheeler/restore.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 | $0.00032 | $0.01076 |
| Opus 5 | $0.00016 | $0.00538 |
| Sonnet 5 | $0.00006 | $0.00215 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
wh:restore 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Restore from a Wheeler backup archive. Three modes are supported:
--verify(or--dry-run): replay into a scratch namespace, compare against the manifest, then clean up. Live data is never touched.--fresh --target DIR: extract the full project tree and replay all graph nodes and relationships into a fresh (empty or clean) directory.--merge: merge archive nodes into the current (possibly populated) project using a configurable conflict policy.
--fresh and --merge require manifest_version >= 2 (archives created
by Wheeler v0.8+). v1 archives still pass --verify.
Step 1: Validate input
Parse $ARGUMENTS. The first non-flag argument is the archive path.
If no archive path is given, ask the user for one. Do not guess.
If the path does not exist on disk, tell the user. Do not invoke the CLI.
Determine which mode the user wants: verify (default), fresh, or merge.
Step 2: Run the appropriate restore command
Verify mode (default / --dry-run)
wheeler restore <archive_path> --verify [--keep-scratch]
Fresh mode
wheeler restore <archive_path> --fresh --target <dir> [--force]
[--accept-signature-mismatch]
[--neo4j-uri URI] [--neo4j-password PW]
[--neo4j-database DB] [--project-tag TAG]
--target DIR is required. The target must be empty or contain only a
clean project shell (just .git/, .gitignore, or a pristine
wheeler init output) unless --force is passed.
Merge mode
wheeler restore <archive_path> --merge
[--conflict skip|replace|prefix] [--prefix STR]
[--accept-signature-mismatch]
[--neo4j-uri URI] [--neo4j-password PW]
[--neo4j-database DB] [--project-tag TAG]
--conflict governs what happens when an incoming node ID already exists
in the recipient graph: skip (default), replace (overwrite via
update_node), or prefix (rewrite incoming IDs to <prefix>__<id>).
--prefix STR is required when --conflict=prefix.
If wheeler is not on PATH, fall back to:
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 · 118 lines · 32 tokens per session scan A 09b19da958a8
wh:restore is a command published in the GitHub repository maxwellsdm1867/wheeler (10 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 1,076 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.