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/johnfkoo951/cmds-llm-wiki/ingestgit clone --depth 1 https://github.com/johnfkoo951/cmds-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/johnfkoo951/cmds-llm-wiki/ingest)<a href="https://agentmods.dev/commands/johnfkoo951/cmds-llm-wiki/ingest"><img src="https://agentmods.dev/badge/commands/johnfkoo951/cmds-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 5.1 | $0.00033 | $0.08182 |
| Opus 5 | $0.00016 | $0.04091 |
| Sonnet 5 | $0.00007 | $0.01636 |
| Haiku 4.5 | $0.00003 | $0.00818 |
Grade A, and why
ingest scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
ENCODED=$(python3 -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1], safe=''))" "<exact path from qmd>") The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 6d ago First seen · 557 lines · 33 tokens per session scan A 7b129e029685
ingest is a command published in the GitHub repository johnfkoo951/cmds-llm-wiki (85 stars, last pushed 10d ago), with no licence file. It adds 33 tokens to every session and 8,182 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
okf
Command "okf" from kimsanguine/llm-brain, covering 인자 파싱, 기본 private export, 🔴 share-ready gate (외부 공유 전 one-way door), legacy step 1: private dry-run 검토 and legacy step 2: private export.
curate
Command "curate" from kimsanguine/llm-brain, covering 인자 파싱, step 1: curate 스크립트 실행, step 2: distill 실행 (--distill 또는 --all 일 때), step 3: reweave 실행 (--reweave 일 때) and step 3.5: 모순 후보 화해 (wiki/contradictionqueue.md 존재 시).
query
Command "query" from kimsanguine/llm-brain, covering step 1: index.md 검색, step 2: persisted claim ledger 로드, step 3: wiki 기반 답변 and step 4: 연결 요약 출력.
doctor
Command "doctor" from kimsanguine/llm-brain, covering 인자, guided 프로필, 실행, 점검 항목 and 결과 해석.
ingest
Command "ingest" from kimsanguine/llm-brain, covering 인자 파싱, step 1: 스크립트 실행, url 수집, 파일 추가 and 텍스트 노트.
express
Command "express" from kimsanguine/llm-brain, covering 인자 파싱, step 1: express 스크립트 실행, step 2: 콘텐츠 합성 and step 3: 파일 경로 안내.