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 skills add dandacompany/vibe-finance-kit --skill backtest-auditgit clone --depth 1 https://github.com/dandacompany/vibe-finance-kitWrote 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/skills/dandacompany/vibe-finance-kit/backtest-audit)<a href="https://agentmods.dev/skills/dandacompany/vibe-finance-kit/backtest-audit"><img src="https://agentmods.dev/badge/skills/dandacompany/vibe-finance-kit/backtest-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dandacompany/vibe-finance-kit/backtest-audit"><img src="https://agentmods.dev/badge/skills/dandacompany/vibe-finance-kit/backtest-audit.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00050 | $0.00499 |
| Opus 5.5 | $0.00020 | $0.00200 |
| Sonnet 5.5 | $0.00010 | $0.00100 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
backtest-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 2mo 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.
What it actually says
Backtest Audit
백테스트가 실행됐다는 사실과 의사결정 근거로 쓸 수 있다는 판단을 분리한다. 먼저 산출물을 읽고, 코드 수정은 사용자가 요청한 경우에만 한다.
Audit order
StrategySpec, 데이터 스냅샷,BacktestReport의 ID와 해시 연결을 확인한다.t일 종가 판단이t+1일 시가 또는 명시된 다음 봉에서 체결됐는지 확인한다.- 전략과 벤치마크의 초기자금, 기간, 비용, 단위를 맞춘다.
- 파라미터 선택 구간과 최종 평가 구간이 시간순으로 분리됐는지 확인한다.
- 거래비용·슬리피지·미체결 가정을 확인한다.
- 한 사이클을 손으로 검산하고 코드 결과와 맞춘다.
- 수익률뿐 아니라 MDD, 회전율, 자금 묶임, 거래 수, 미해결 포지션, 경고를 보고한다.
- MCP
audit_backtest_report로 필수 계약을 검사한다.
Fail-closed conditions
- 평가 구간으로 파라미터를 선택했다.
- 미래 가격을 신호 시점에 참조했다.
- 정정주가와 원시주가를 설명 없이 섞었다.
- 거래비용이 빠졌거나 벤치마크 조건이 다르다.
- 데이터 기준일·가용 시점을 재현할 수 없다.
하나라도 해당하면 결과를 “실패” 또는 “검증 대기”로 표시한다. 좋은 수익률이 이 게이트를 무효화하지 않는다.
Output
verdict: pass|revise|fail
errors: string[]
warnings: string[]
verified_assumptions: string[]
unresolved_questions: string[]
decision_eligible: boolean
체크리스트 전문은 audit-checklist.md를 읽는다.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 43 lines · 50 tokens per session scan A fa9203322881
backtest-audit is a skill published in the GitHub repository dandacompany/vibe-finance-kit (1 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 499 once invoked, about $0.0002 per session on Opus 5.5. 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.
backtest-audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| backtest-auditdandacompany/vibe-finance-kit | Skill | 1 | 2mo ago | MIT | A | 50 | Codex |
| joinquant-skillgaaiyun/joinquant-skill | Skill | 91 | 4d ago | none | A | 144 | Claude Code, Codex |
| dcf-valuationnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 55 | Claude Code, Codex |
| tushareHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 79 | Claude Code, Codex |
| social-media-intelligenceHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 28 | Claude Code, Codex |
| vibe-tradingHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 172 | Claude Code, Codex |
| geopolitical-riskHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 34 | Claude Code, Codex |