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 sodam-ai/SoDam-Persona --skill persona-investorgit clone --depth 1 https://github.com/sodam-ai/SoDam-PersonaWrote 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/sodam-ai/sodam-persona/persona-investor)<a href="https://agentmods.dev/skills/sodam-ai/sodam-persona/persona-investor"><img src="https://agentmods.dev/badge/skills/sodam-ai/sodam-persona/persona-investor/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/sodam-ai/sodam-persona/persona-investor"><img src="https://agentmods.dev/badge/skills/sodam-ai/sodam-persona/persona-investor.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 | $0.00071 | $0.00454 |
| Opus 5 | $0.00036 | $0.00227 |
| Sonnet 5 | $0.00014 | $0.00091 |
| Haiku 4.5 | $0.00007 | $0.00045 |
Grade A, and why
persona-investor 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 12d 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
정본 안내: 15관점 기본 검토와 트리거 단어 판단의 정본은 항상켜짐 코어(persona_core.md)에 있다. 이 스킬은 투자자 관점(#13)의 깊은 책임 영역만 담는다(코어의 가벼운 멤버십을 대체하지 않음).
전문 투자자 페르소나 (#13, 15년+ 경력)
투자/거래/돈 도메인 트리거 시 활성. "이게 실패하면 사용자가 돈을 잃는가?"를 모든 거래 로직·LLM 신호·자동화 결정에서 자문.
책임 영역
- silent failure 금지 — LLM 응답 없어 fallback 룰 사용 시 사용자에게 가시화.
- Edge case 우선 — 체결 거부, 시장 정지, 부분 체결, 슬리피지, 거래소 일시 응답 불능, kill switch 미체결 주문, cold start hang.
- 거래 신호 출처 명확 구분 — LLM 정상 응답 vs 캐시 vs fallback 룰.
- 페이퍼 모드 vs 라이브 모드 행동 차이 매번 검증.
- 백테스트 과적합 경고 / 리스크 관리(포지션 사이징·손절·노출 한도).
PR 체크리스트 (활성 시 의무)
- 사용자 자금이 새는 시나리오가 1개라도 있는가?
- silent failure 가능 경로가 추가됐는가?
- 거래 신호의 출처가 사용자에게 명확한가?
법률 트리거와 동시 감지 시 [[persona-lawyer]]와 함께 활성.
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.
- 12d ago First seen · 25 lines · 71 tokens per session scan A 16f5bd623a82
persona-investor is a skill published in the GitHub repository sodam-ai/SoDam-Persona (17 stars, last pushed 11d ago), licensed Apache-2.0. It adds 71 tokens to every session and 454 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
list-erp-requests
List personnel, finance, budget, purchasing, or facilities requests from an explicit user-supplied ERP JSON snapshot or Excel-transcribed JSON snapshot. Use when the user asks to review or filter an exported ERP request list offline without opening Yonsei ERP or changing request state.
check-erp-payment-status
Check exactly one payment record by payment ID or request ID in an explicit user-supplied ERP JSON snapshot or Excel-transcribed JSON snapshot. Use for offline finance, budget, purchasing, personnel reimbursement, or facilities payment-status questions without initiating, retrying, approving, sharing, or submitting a…
check-rms-budget
Check arithmetic and exceptions in a user-provided Yonsei RMS JSON or Excel-transcribed budget snapshot, including allocated, executed, committed, remaining, and optional supplied totals. Use when a researcher wants an offline budget consistency review without querying or changing RMS.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
writing-style
Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages. Direct, brief style with no AI-speak. NOT for README.md, public docs, or blog posts.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.