Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/kimsanguine/llm-brainnpx agentmods add commands/kimsanguine/llm-brain/doctorWrote 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/doctor)<a href="https://agentmods.dev/commands/kimsanguine/llm-brain/doctor"><img src="https://agentmods.dev/badge/commands/kimsanguine/llm-brain/doctor.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 5.1 | $0.00020 | $0.00901 |
| Opus 5 | $0.00010 | $0.00451 |
| Sonnet 5 | $0.00004 | $0.00180 |
| Haiku 4.5 | $0.00002 | $0.00090 |
Grade A, and why
doctor 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 8d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
llm-brain의 doctor 커맨드입니다. 설치를 진단·복구하거나, --guided로 쓰기 전
운영 프로필을 선택합니다.
$ARGUMENTS에 따라 아래를 실행하세요.
인자
- 인자 없음 → 진단만 (llm-brain 제품/개인 데이터 변경 없음)
--fix→ 안전 복구: 누락 디렉토리 생성 +schema/sources.yaml이 없으면sources.example.yaml에서 복사. 기존 파일은 절대 덮어쓰지 않음.--guided→ 읽기 전용 프로필 3개(Demo,Personal-private,Share-ready)만 표시--guided --profile demo|personal-private|share-ready→ 선택한 프로필의 명시적 다음 행동 1개만 표시
--guided는 --fix와 함께 쓸 수 없고, 진단·디렉터리 생성·config 복사·개인
콘텐츠 스캔을 실행하지 않습니다.
doctor.py 자체는 제품/개인 데이터를 변경하지 않지만, 실행기인 uv run은 Python
환경이나 패키지 캐시를 생성·갱신할 수 있습니다.
Guided 프로필
- Demo — 기존
examples/seed-wiki/wiki를 읽는 일회성 설치 검증 안내(브라우저 UI 체험은wikiweb의 데모 절차 사용) - Personal-private —
schema/sources.yaml이 있으면 사용자 설정을 preview하고, fresh clone처럼 없으면 존재하는schema/sources.example.yaml템플릿 preview 안내 - Share-ready — canonical
schema/okf_export.yaml, localschema/okf_export.local.yaml, 모든 후보의 명시적scope: shared|private확인 후 정확한scripts/okf_export.py --share --approve-share I_ACKNOWLEDGE_SHARE_READY_EXPORT다음 행동 하나를 안내
실행
cd "$(git rev-parse --show-toplevel)" # llm-brain 레포 루트
uv run python scripts/doctor.py $ARGUMENTS
(uv 미설치 시: .venv/bin/python scripts/doctor.py $ARGUMENTS)
점검 항목
- 필수 디렉토리:
raw/(7 하위 채널)·wiki/·schema/·scripts/·commands/·procedures/·examples/ - 스크립트(메모리 OS 포함): ingest·curate·express·okf_export·export_graph·sync_raw + episode·brain_context·memory_health·procedures·lib/frontmatter_utils
- 커맨드: ingest·curate·express·query·okf·doctor·wikiweb
- 설정:
schema/config.yaml(LLM 엔진)·schema/sources.yaml(소스 — gitignored, 없으면 WARN) - 의존성: pyyaml·fastapi·uvicorn·httpx·python-frontmatter (
uv sync로 설치) - claude CLI: cli 엔진(기본) 사용 시 필요 (없으면 WARN)
결과 해석
- ❌ FAIL = 설치 문제 → 해결 필요(디렉토리는
doctor --fix, 의존성은uv sync, 스크립트/커맨드 누락은 플러그인 재설치·git pull). - ⚠️ WARN = 선택/환경별(설정 파일·claude CLI 등) — 필요 시 안내대로.
- exit 0 = FAIL 없음(설치 정상) · exit 1 = FAIL 있음.
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.
- 8d ago First seen · 56 lines · 20 tokens per session scan A 1b1390d6ba09
doctor is a command published in the GitHub repository kimsanguine/llm-brain (10 stars, last pushed 24d ago), licensed MIT. It adds 20 tokens to every session and 901 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
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).
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.
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.
onboard
An interview-based setup command for an LLM Wiki, a notes system designed for use with language models. It asks about your wiki, files, working mode, and personal context, then fills in the setup details.