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/initgit clone --depth 1 https://github.com/maxwellsdm1867/wheelerWhat 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 | $0.00017 | $0.03228 |
| Opus 5 | $0.00009 | $0.01614 |
| Sonnet 5 | $0.00003 | $0.00646 |
| Haiku 4.5 | $0.00002 | $0.00323 |
Grade A, and why
wh:init 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 2d 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Wheeler, running project initialization. Walk the scientist through setting up their project step by step. Two flows are supported: start a brand-new project, or restore from a Wheeler backup archive that was created on another machine. Pick the mode first, then follow the matching steps. Always confirm the high-level facts with the scientist before doing irreversible work (creating files, writing the config, running restore).
Step 0: Pick a mode
If $ARGUMENTS looks like a path to a .tar.gz file (substring .tar.gz, or the file exists on disk), skip ahead to Path B: Restore from archive and treat that path as the archive.
Otherwise, ask the scientist:
"Are you starting a brand-new project, or restoring from a Wheeler backup archive (
.tar.gz)?"
Use AskUserQuestion with two options:
- New project: fresh project setup, configure paths and seed the first question.
- Restore from archive: I have a
wheeler-backup-*.tar.gzfrom another machine and want to unpack it here.
Branch on the answer. If "New project", continue with Path A below. If "Restore from archive", jump to Path B.
Path A: New project
Step A1: Check existing state
- If
wheeler.yamlexists in the current directory, warn the scientist and offer to reconfigure or abort. - Note the current working directory — this is the project root.
Step A2: Project description
Ask the scientist:
"What's this project about? One sentence is fine."
Store as project.name (short label, extracted from the description) and project.description (their full answer) in config.
Step A3: Path discovery
Use wheeler/scaffold.py's detect_project_dirs() logic — scan the project root for common directory names (scripts/, src/, data/, figures/, docs/, results/, analysis/, etc.).
For each of the 5 path categories (code, data, results, figures, docs):
- If matching directories were found, suggest them as options using AskUserQuestion
- Always include "Create .//" and "Skip" as options
- Let the scientist pick, modify, or provide custom paths
- Paths can be anywhere — local, external drive, network mount, shared NAS. Wheeler doesn't care where files physically live. Examples:
data/(local, relative)/Volumes/LabNAS/recordings/(network mount)/shared/lab/analysis-tools/(shared code)~/datasets/project-x/(home directory)
- Wheeler never copies or moves files — it just tracks where they are. The graph stores the path as-is and validates with hashes.
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.
- 2d ago First seen · 306 lines · 17 tokens per session scan A 802d5d3f65b4
wh:init is a command published in the GitHub repository maxwellsdm1867/wheeler (10 stars, last pushed 5d ago), licensed MIT. It adds 17 tokens to every session and 3,228 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
export
Export a knowledge abstract to an Obsidian vault — a folder of Markdown notes linked by [[wikilinks]].
bootstrap-memory
RUN { git ls-files; git ls-files --others --exclude-standard; } 2>/dev/null | sort -u | xargs wc -l 2>/dev/null | sort -rn | head -150 READ README.md.
maestro-issue
Intent-driven issue lifecycle management — describe what you want in natural language (报告一个 bug / 列出开放 issue / 关掉 ISS-xxx / 关联到 task / 扫描发现问题) and the workflow routes to the right operation. Operates on .workflow/issues/. 知识管理走 /maestro-knowledge；knowhow 沉淀走 /maestro-knowhow；约束规则走 /maestro-spec。Triggers on "issue 管理"…
twining:export
Export Twining state as markdown for context handoff or archival.
formula-f10
../../../core/thinkingos/agents/observer.md.
formula-f8
../../../core/thinkingos/agents/securityauditor.md.