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.
git clone --depth 1 https://github.com/sodam-ai/SoDam-WikiMateWrote 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/commands/sodam-ai/sodam-wikimate/wikimate-link)<a href="https://agentmods.dev/commands/sodam-ai/sodam-wikimate/wikimate-link"><img src="https://agentmods.dev/badge/commands/sodam-ai/sodam-wikimate/wikimate-link/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/commands/sodam-ai/sodam-wikimate/wikimate-link"><img src="https://agentmods.dev/badge/commands/sodam-ai/sodam-wikimate/wikimate-link.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 | $0.00042 | $0.00616 |
| Opus 5 | $0.00021 | $0.00308 |
| Sonnet 5 | $0.00008 | $0.00123 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
wikimate-link 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 7d 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
"Wikimate Link" 스킬의 워크플로우를 따른다. 사용자 의도가 "연결"이면 A, "목차/MOC"면 B를 따른다.
A. 노트끼리 연결 (add_links)
- 볼트 확정(이름 또는 경로). 모르면
wikimate_vaults로 후보를 묻는다. wikimate_link를action:"suggest"로 호출해 후보(title·summary·tags)를 읽기전용으로 본다.- 유사도 엔진 없이 직접 관련도를 판단한다 — 확실한 것만, 노트당 최대 5개. 왜 관련 있는지 한 줄 이유도 정리해 둔다. 확실하면 관계 종류(
kind:related/reference)도 판단(애매하면 생략). - 계획을 보고하고
AskUserQuestion으로 [연결하기/건너뛰기/수정] 개별 승인을 받는다(비가역 편집이라 사전승인 무관). - 승인된 것만
wikimate_link를action:"add_links", dry_run:false, reason:<3번 이유>, kind:<3번 종류(선택)>로 호출한다(둘 다 노트 본문 "## 왜 연결했는지" 섹션의 같은 불릿 줄에 기록됨 — kind는 괄호로). - 결과(반영된 related·백업 경로)를 재확인 후 보고하고, 그래프뷰 확인은 사용자에게 안내한다.
B. 목차(MOC) 만들기·갱신 (build_moc)
- 주제(topic)와 묶을 노트들을 확인한다(지어낸 노트 이름 금지). 볼트 확정은 A와 동일.
wikimate_link를action:"build_moc", topic:<주제>, targets:<노트 제목 배열>, dry_run:true로 호출해 신규/갱신 여부와 멤버를 확인한다(5개 상한 없음).AskUserQuestion으로 [만들기(갱신)/건너뛰기/대상 수정] 개별 승인을 받는다.- 승인된 것만
dry_run:false로 실제 호출한다. 기존 MOC가 있었다면 사용자가 직접 쓴 다른 섹션이 보존됐는지 확인한다. - 생성/갱신된 경로와 최종 멤버를 확인 후 보고하고, 그래프뷰 확인은 사용자에게 안내한다.
인자가 있으면 그 노트(또는 주제)를 대상으로 시작한다: $ARGUMENTS
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.
- 7d ago Changed 97f8b747c875
- 11d ago First seen · 24 lines · 42 tokens per session scan A c2910e7d887b
wikimate-link is a command published in the GitHub repository sodam-ai/SoDam-WikiMate (53 stars, last pushed 9d ago), licensed Apache-2.0. It adds 42 tokens to every session and 616 once invoked, about $0.0002 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 commands, from other repositories
pipi_setup
You are helping an operator personalize Open PiPi after installation.
daily-okr
Run a daily knowledge compound loop (7 KR). Invoke with /daily-okr or "start my daily review".
continue
Resume incomplete work from continuation tasks, or find the highest-impact next action.
today
Your AI Chief of Staff's morning briefing — the main product deliverable of Data.
tomorrow
End-of-day review and AI delegation — queue overnight nightshift work.
open
Open the memex vault in Finder or Obsidian.