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/kimsanguine/llm-brain/expressgit clone --depth 1 https://github.com/kimsanguine/llm-brainWrote 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/kimsanguine/llm-brain/express)<a href="https://agentmods.dev/commands/kimsanguine/llm-brain/express"><img src="https://agentmods.dev/badge/commands/kimsanguine/llm-brain/express.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.00502 |
| Opus 5 | $0.00009 | $0.00251 |
| Sonnet 5 | $0.00003 | $0.00100 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
express 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 4d 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
llm-brain의 express 커맨드입니다. 아래 절차를 실행하세요.
인자 파싱
$ARGUMENTS 형식:
blog '<주제>'→ 블로그 포스트lecture '<주제>' [--slides N]→ 강의 슬라이드 (기본 5장)summary --week→ 주간 요약 (최근 7일)summary --month→ 월간 요약 (최근 30일)report '<주제>'→ 심층 리포트
Step 1: express 스크립트 실행
cd "$(git rev-parse --show-toplevel)" # llm-brain 레포 루트
uv run python scripts/express.py $ARGUMENTS
스크립트가 관련 wiki 페이지를 수집하고 express/{type}/YYYY-MM-DD-{slug}.md 초안 파일을 생성합니다.
Step 2: 콘텐츠 합성
생성된 초안 파일을 읽습니다.
<!-- CONTEXT_START --> ~ <!-- CONTEXT_END --> 사이의 wiki 컨텍스트를 바탕으로 실제 콘텐츠를 작성해 초안 파일에 덮어씁니다.
타입별 작성 기준:
blog
- 독자: AI/기술 관심 한국어 독자
- 길이: 800-1200자 내외
- 구조: 도입 → 핵심 인사이트 2-3개 → 실천 제안 → 마무리
lecture
- 슬라이드 수:
--slides인자값 (기본 5) - 각 슬라이드:
## 슬라이드 N: 제목+ 핵심 포인트 3개 이내 - 마지막 슬라이드: Q&A 또는 실습 과제
summary
- 섹션: 핵심 인사이트 / 반복 패턴 / 다음 액션
- wiki에 없는 기간이면 "해당 기간 wiki 업데이트 없음" 안내
report
- 섹션: 현황 / 주요 발견 / 시사점 / 권고사항
- 길이: 1500자 이상
Step 3: 파일 경로 안내
작성 완료 후 저장된 파일 경로를 사용자에게 알립니다.
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.
- 4d ago First seen · 53 lines · 17 tokens per session scan A fd0cd702c3e3
express is a command published in the GitHub repository kimsanguine/llm-brain (10 stars, last pushed 20d ago), licensed MIT. It adds 17 tokens to every session and 502 once invoked, about $0.0001 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 commands, from other repositories
ingest
Ingest a source (URL/file/text) into Raw Sources + compile 1015 Wiki pages, with mandatory user-purpose gate and mothership cross-linking.
audit
Audit the whole Wiki vault against 3 knowledge-integrity criteria — eligibility coverage, MOC-cluster consistency, confidence calibration. Produces a vault health report and queues high-priority pages for /verify.
verify
Verify a single Wiki page against 3 knowledge-integrity criteria — eligibility, consistency, confirmability. Writes verificationStatus back to the page; flags conflicts as disputed rather than deleting them.
lint
Run comprehensive wiki health check — orphans, broken links, contradictions, stale pages, index sync, MOC coverage, v2/v4/v5 frontmatter coverage, Core Context freshness, and cross-vault link integrity (mainVaultRelated/mainVaultCmds).
onboard
Interview-based first-run setup for this LLM Wiki kit. Asks the essential questions (vault location/name, Mode A/B, mothership path, Core Context identity + reuse axes), then fills every placeholder and writes Core Context so the wiki knows you from day one. Activate when the user says "온보딩해줘", "처음 시작할게", "처음 시작"…
capture-tabs
Capture a Chrome research tab group or AI-chat research session into LLM Wiki Inbox markdown, then optionally route it through /inbox or /ingest.