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/fivetaku/llm-wiki/ingestgit clone --depth 1 https://github.com/fivetaku/llm-wikiWrote 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/fivetaku/llm-wiki/ingest)<a href="https://agentmods.dev/commands/fivetaku/llm-wiki/ingest"><img src="https://agentmods.dev/badge/commands/fivetaku/llm-wiki/ingest.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 | $0.00097 | $0.00950 |
| Opus 5 | $0.00048 | $0.00475 |
| Sonnet 5 | $0.00019 | $0.00190 |
| Haiku 4.5 | $0.00010 | $0.00095 |
Grade A, and why
ingest 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
/ingest — 수집 (저장만)
자료를 10-inbox/에 새 파일로 저장만 합니다. 위키 페이지는 만들지 않습니다 — 그건 /compile의 일(저장과 정제를 분리). 저장된 소스는 inbox에 "미컴파일" 상태로 쌓이고, /compile이 위키로 정제한 뒤 20-raw/로 옮깁니다.
사용법
/ingest [URL | 파일경로 | 붙여넣은 텍스트]
/ingest https://example.com/article
/ingest ~/Downloads/paper.pdf
사용자가 직접
10-inbox/에 파일을 떨궈도 됩니다 (그 경우/ingest없이 바로/compile).
실행 흐름
Step 1: 가져오기
- URL → 본문을 fetch해 마크다운으로 변환. (WebFetch가 SPA·봇차단으로 실패하면 사용자에게 본문 붙여넣기를 요청하거나 보유한 스크래핑 도구 사용.)
- 파일 경로 → 읽어서 가져옴. 이미지·PDF 첨부는
20-raw/assets/에 저장(영구 자산). - 텍스트 → 그대로.
Step 1.5: 포맷 변환 (바이너리 → 마크다운)
docx·pptx·xlsx·복잡 PDF는 Claude가 직접 못 읽으므로 마크다운으로 변환해 inbox에 넣는다 (원본 바이너리는 20-raw/assets/에 보관). 확장자별 라우팅 — 정본: conventions.md §12:
.md/.txt/.html→ 그대로..docx/.pptx/.xlsx→markitdown <파일> > 10-inbox/{slug}.md(1순위, 로컬·무료). 없으면pip install 'markitdown[all]'안내..pdf→ 텍스트형은 Claude가 직접 Read, 스캔/복잡 표는 markitdown.- 표·레이아웃 복잡 +
LLAMA_CLOUD_API_KEY있음 → LlamaParse로 고품질 변환(폴백). 키 없으면 markitdown으로. - 어떤 도구도 없으면 막지 말고 설치 안내 또는 "텍스트로 붙여달라".
Step 2: inbox에 저장
10-inbox/{YYYY-MM-DD}-{slug}.md에 새 파일명으로 저장한다.- 같은 자료의 갱신이면
-v2처럼 새 이름으로 (덮어쓰기 금지). - 파일 맨 위 frontmatter에 출처(원본 URL/경로)·수집일을 남긴다.
Step 3: 알림 (위키화 안 함)
- 위키 페이지는 만들지 않는다 — 저장만.
30-wiki/log.md에## [YYYY-MM-DD] ingest | {제목}한 줄.- "inbox에 미컴파일 소스 N개 대기 →
/compile로 위키화하세요" 안내.
트리거 경계
should-trigger: "이 자료 넣어줘", "수집해줘", "이 URL 가져와", "이 PDF 넣어" NOT-trigger:
- "위키로 정리해줘" / "정제해줘" / "컴파일" →
/compile - "X에 대해 뭐 알아?" →
/query - "위키 점검해줘" →
/lint - "원본 고쳐줘" → 금지 (raw 불변)
참조
/compile— inbox 소스를 위키 페이지로 정제 + raw 이동00-system/conventions.md— 페이지·인덱스·라우팅 규약
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 · 55 lines · 97 tokens per session scan A b8bd19a2f667
ingest is a command published in the GitHub repository fivetaku/llm-wiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 97 tokens to every session and 950 once invoked, about $0.0005 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.