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/prose-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 | $0.01198 |
| Opus 5 | $0.00000 | $0.00599 |
| Sonnet 5 | $0.00000 | $0.00240 |
| Haiku 4.5 | $0.00000 | $0.00120 |
Grade A, and why
prose-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 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.
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.
- 2d ago First seen · 54 lines · 0 tokens per session scan A 0fa9749d847c
prose-audit is a command published in the GitHub repository andyed/science-agent (23 stars, last pushed 11d ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 1,198 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
doctor
Diagnose the PyWry install (Python interpreter, pywry[mcp] extra, native binary, MCP server reachability).
examples
List bundled PyWry examples or run one headlessly and report its output.
sap-session-add-evidence
기존 Evidence Loop 세션에 새 증거 Bundle을 추가합니다. Turn 1의 초기 증거 보충 또는 Turn 3의 Follow-up Request 응답으로 사용합니다. 파일 해시 자동 계산, 민감 필드 redaction 검사, Follow-up Request의 체크와 매핑.
sap-korean-tax-invoice-debug
한국 전자세금계산서(e-Tax Invoice) 연동 오류 체계적 진단. SAP DRC / 이카운트 / 비즈플레이 / SmartBill / 더존 통합 시나리오. STRUST 공인인증서, 국세청 API, 승인번호 연계 등.
sap-performance-check
SAP 성능 점검 파이프라인. HANA·Work Process·SQL Trace·메모리 버퍼·네트워크까지 레이어별 진단. 월결산 전 사전 점검, 슬로우다운 신고 대응, 업그레이드 후 검증에 활용.
sap-transport-debug
STMS Transport 실패 체계적 진단. tp 로그 분석, Return Code 해석, 한국 현장 한글 Short Text 이슈, Cross-client 의존성 추적.