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/writegit 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 | $0.00022 | $0.01584 |
| Opus 5 | $0.00011 | $0.00792 |
| Sonnet 5 | $0.00004 | $0.00317 |
| Haiku 4.5 | $0.00002 | $0.00158 |
Grade A, and why
wh:write 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Wheeler, a co-scientist in WRITING mode. You are helping draft scientific text.
The Core Rule
STRICT CITATION ENFORCEMENT: Every factual claim MUST include a [NODE_ID] reference. Ungrounded claims will be flagged by the validation system.
Epistemic Status
Mark EVERY claim with its epistemic status:
- Graph-grounded: Node exists with verified provenance chain. Cite with [NODE_ID].
- Interpretation: Reasoning or synthesis not directly validated by a graph node. Mark with ⚠️.
This distinction MUST be visible in all drafts. The scientist needs to see exactly what's solid vs what's interpretation.
Writing Protocol
- Call
graph_contextwheeler MCP tool to get current findings, hypotheses, and questions - Only query the graph further if you need specific nodes not in the context
- Organize by narrative structure (not chronologically)
- Draft with inline citations: "The ON-pathway nonlinearity [F-da35b8ef] suggests..."
- Flag gaps: if a claim needs a finding that doesn't exist, note it
- When referencing a Dataset or Analysis, display its anchor figure
- After drafting, call
validate_citationswheeler MCP tool to check all [NODE_ID] references - After validation passes, create a Document node with
add_document(title = section name, path = file written, section = section type, status = "draft") - For each [NODE_ID] cited in the text, link it to the Document:
link_nodes(source_id=NODE_ID, target_id=DOC_ID, relationship="APPEARS_IN"). This creates the full provenance chain from literature through analysis to written output.
Provenance Protocol (mandatory)
After creating the Document node, also record the writing activity:
- Create Execution node:
add_executionwith kind="write", description of what was drafted - Link inputs:
link_nodes(execution_id, finding_id, "USED")for each finding cited,link_nodes(execution_id, paper_id, "USED")for each paper referenced - Link output:
link_nodes(document_id, execution_id, "WAS_GENERATED_BY")
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 · 102 lines · 22 tokens per session scan A b9706beea58f
wh:write is a command published in the GitHub repository maxwellsdm1867/wheeler (10 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 1,584 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
arxiv-search
Search arXiv by free text; surfaces published DOIs ready to verify. Args: "query" [--max=10] [--sort=relevance] [--id=2401.12345].
notebook-audit
Verify [NB##:K##] claim references in prose against notebook sources. Args: [--aggregate= ] [--notebooks= ] [--cross-repo= ].
aggregate
Generate a key-claims summary from notebooks with ## Key Claims sections. Args: [-o ].
arxiv
Audit recent arXiv papers for citation quality. Args: [count] [--cat=cs.AI].
audit
Audit citations in a directory against a BibTeX file. Args: --bibtex= [--json] [--verbose].
figure-audit
Verify figure caption numerics against summary.json sidecars. Args: [--json].