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/andyed/science-agent/auditgit clone --depth 1 https://github.com/andyed/science-agentWhat 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 | $0.00000 | $0.00118 |
| Opus 5 | $0.00000 | $0.00059 |
| Sonnet 5 | $0.00000 | $0.00024 |
| Haiku 4.5 | $0.00000 | $0.00012 |
Grade A, and why
audit 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 yesterday.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- yesterday First seen · 12 lines · 0 tokens per session scan A e755c1c98789
audit is a command published in the GitHub repository andyed/science-agent (23 stars, last pushed 10d ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 118 tokens. 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 2026-08-30.
Other commands, from other repositories
wh:ingest
Bootstrap knowledge graph from existing data files.
wh:asta-scholar
Use when the user wants to query Semantic Scholar via Asta (paper lookup, search, citations, snippet search, or an author's papers) and ingest the results into the Wheeler knowledge graph.
wh:asta-lit
Use when the user wants to find literature with Asta Paper Finder and ingest the results into the Wheeler knowledge graph.
wh:write
Use when the user wants to draft scientific text with Wheeler citation enforcement from knowledge-graph findings.
wh:chat
Use for casual discussion with Wheeler that reads the knowledge graph and writes only on explicit scientist approval.
OPSX: Fast Forward
Create a change and generate all artifacts needed for implementation in one go.