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/wikiwebgit 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/wikiweb)<a href="https://agentmods.dev/commands/kimsanguine/llm-brain/wikiweb"><img src="https://agentmods.dev/badge/commands/kimsanguine/llm-brain/wikiweb.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 | $0.00033 | $0.00510 |
| Opus 5 | $0.00016 | $0.00255 |
| Sonnet 5 | $0.00007 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
wikiweb scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
llm-brain의 wiki-web UI(로컬 HTML 검색·페이지뷰)를 띄웁니다. CLI query의 시각화 버전입니다.
실행
cd "$(git rev-parse --show-toplevel)" # llm-brain 레포 루트
uv run python -m wiki_app
(uv 미설치 시: .venv/bin/python -m wiki_app)
서버가 뜨면 브라우저에서 http://localhost:8000 을 엽니다. 종료는 Ctrl+C.
제공 기능
- 검색: 제목·description·tags 점수 매칭, 결과 < 3개일 때 본문 grep(본문 검색) 자동 확장. 한국어/영문 모두.
- 페이지뷰: 마크다운 렌더 +
[[wikilink]](페이지끼리 연결) 클릭 SPA(새로고침 없이 이동) 네비게이션. - AI 답변 토글:
claude -p라이브 연결(미설치 시 graceful 비활성). citation 검증 전 토큰은 표시하지 않으며, 제한된 buffer에서 검증한 뒤 한 번에 보내는verified-buffered방식임을 UI에 표시합니다. usable claim이 없으면 출처 페이지를 표시하지 않고 제외 사유 count와 다음 행동 하나를 보여줍니다.
검색·페이지 보기·AI query는 읽기 경로이며 raw/·wiki/·wiki_stats.json·접근
lock을 변경하지 않습니다. 접근 통계가 필요하면 별도로
uv run python scripts/curate.py --record-access PAGE_SLUG를 실행합니다.
데이터가 없다면 (선택)
wiki/가 비어 있으면 검색 결과가 안 나옵니다. 데모 데이터로 먼저 체험:
cd "$(git rev-parse --show-toplevel)"
cp -r examples/seed-wiki/wiki ./wiki # 데모 wiki 복사
cp examples/seed-wiki/index.md ./index.md # 데모 목차
uv run python -m wiki_app # → http://localhost:8000
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 · 41 lines · 33 tokens per session scan A d31da4dfce90
wikiweb is a command published in the GitHub repository kimsanguine/llm-brain (10 stars, last pushed 20d ago), licensed MIT. It adds 33 tokens to every session and 510 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 2026-08-31.
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).
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
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"…