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 SW-in-beta/simon-skills --skill simon-brain-updategit clone --depth 1 https://github.com/SW-in-beta/simon-skillsWrote 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/sw-in-beta/simon-skills/simon-brain-update)<a href="https://agentmods.dev/skills/sw-in-beta/simon-skills/simon-brain-update"><img src="https://agentmods.dev/badge/skills/sw-in-beta/simon-skills/simon-brain-update/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/sw-in-beta/simon-skills/simon-brain-update"><img src="https://agentmods.dev/badge/skills/sw-in-beta/simon-skills/simon-brain-update.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 | $0.00168 | $0.02817 |
| Opus 5 | $0.00084 | $0.01409 |
| Sonnet 5 | $0.00034 | $0.00563 |
| Haiku 4.5 | $0.00017 | $0.00282 |
Grade A, and why
simon-brain-update 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
simon-brain-update
simon* 스킬 결과물이나 웹 URL을 받아, 내용 기반으로 적합한 vault를 자동 판별하고 raw/에 원본을 저장한 뒤 wiki로 정제한다.
Trigger
/simon-brain-update {파일경로}— 로컬 MD 파일 처리/simon-brain-update {URL}— 단일 웹 URL 처리 (공식 문서, 블로그, 기술 아티클)/simon-brain-update— 최근 claude-reports/ 파일 목록 제시- 대화 중 여러 URL/파일 리스트가 주어지면 대량 처리(Bulk) 모드로 전환
입력 형태
| 타입 | 예시 | Step 1 처리 |
|---|---|---|
| A. 로컬 MD | ~/claude-reports/report.md |
Read |
| B. 단일 URL | https://claude.com/blog/... |
WebFetch → raw/에 저장 |
| C. URL 리스트 | 여러 URL (5+ 개) | 서브에이전트 분산 수집 |
Vault 감지
vault 목록은 하드코딩하지 않는다. 매번 동적으로 감지한다:
ls -d ~/Obsidian/*-wiki/ 2>/dev/null
각 vault의 CLAUDE.md를 읽어 도메인과 시그널 키워드를 파악한다. vault가 추가·삭제되어도 자동 반영.
Instructions
Step 0: 업로드 의사 확인
이 스킬은 사용자의 명시적 요청 없이 자동 실행하지 않는다.
다른 스킬(simon-md-reviewer 등) 완료 후에도 brain 업데이트는 제안만 한다:
리뷰가 완료되었습니다. 이 문서를 brain에 업데이트할까요? (/simon-brain-update)
사용자가 "yes", "업데이트해줘", "brain에 넣어줘" 등으로 동의하면 진행한다.
Step 1: 입력 수집
입력 타입에 따라 분기:
Type A (로컬 MD): Read 도구로 파일 내용을 읽는다.
Type B (웹 URL): WebFetch로 원본 markdown을 수집한다.
- prompt: "Return the full document verbatim as plain markdown. Do not summarize, translate, or truncate. Preserve all code blocks, tables, frontmatter exactly as-is."
- 리다이렉트 발생 시 대상 URL 재fetch. 메타에 "Redirected from: {original URL}" 표기.
- raw/ 저장 규칙은 Step 3 참조.
Type C (URL 리스트, 5+):
- 20~30개 단위로 묶어 병렬 서브에이전트에 분산 (Phase 1: 원본 수집만)
- 각 서브에이전트는 raw/에 원본 저장만 담당. 번역·요약 금지.
- 전부 수집된 후 Step 2~4 진행 (Phase 2: wiki 정제)
Step 2: Vault 판별 (중복 허용)
ls -d ~/Obsidian/*-wiki/로 활성 vault 목록을 감지한다- 각 vault의
CLAUDE.md를 읽어 도메인 태그와 카테고리를 파악한다 - 파일 내용 (또는 URL 도메인 + 제목)과 각 vault의 도메인을 대조하여 매칭 판별한다
판별 기준은 각 vault CLAUDE.md의 "Domain Tags" 섹션에서 동적으로 가져온다.
매칭 없음 (시그널 감지 실패 시):
어떤 vault에도 시그널이 감지되지 않으면:
- 문서 주제를 1줄로 요약
- 가장 근접한 vault + 해당 vault 내 새 카테고리 추가 제안
- 또는 새 vault 생성 제안
- 사용자가 선택 후 진행
[Dispatch] 기존 vault에 맞는 시그널을 찾지 못했습니다.
주제: "React Server Components와 서버 사이드 렌더링 패턴"
제안:
A) ai-wiki에 새 카테고리 "frontend-patterns/" 추가 후 저장
B) 새 vault "frontend-wiki" 생성
C) 직접 vault과 카테고리 지정
What ships with it
1 file 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.
- 9d ago First seen · 221 lines · 168 tokens per session scan A 91da372c9dd7
simon-brain-update is a skill published in the GitHub repository SW-in-beta/simon-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 168 tokens to every session and 2,817 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.