Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add kimsanguine/llm-brain/plugin install 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/ingest)<a href="https://agentmods.dev/commands/kimsanguine/llm-brain/ingest"><img src="https://agentmods.dev/badge/commands/kimsanguine/llm-brain/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 | $0.00019 | $0.00916 |
| Opus 5 | $0.00010 | $0.00458 |
| Sonnet 5 | $0.00004 | $0.00183 |
| Haiku 4.5 | $0.00002 | $0.00092 |
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 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.
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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
llm-brain의 ingest 커맨드입니다. 아래 절차를 순서대로 실행하세요.
인자 파싱
$ARGUMENTS를 파싱해 모드를 결정합니다:
https://...또는http://...로 시작 → URL 모드--file <경로>포함 → 파일 모드--note "<텍스트>"포함 → 노트 모드--resonance high|medium|low옵션이 있으면 해당 레벨 사용--priority-only→ resonance: high 미처리 파일만 처리- 인자 없음 → 미처리 파일 목록만 확인
Step 1: 스크립트 실행
인자에 따라 아래 중 해당하는 명령 실행:
# URL 수집
cd "$(git rev-parse --show-toplevel)" # llm-brain 레포 루트
uv run python scripts/ingest.py --url <URL> [--resonance <level>]
# 파일 추가
uv run python scripts/ingest.py --file <경로> [--resonance <level>]
# 텍스트 노트
uv run python scripts/ingest.py --note "<텍스트>" [--resonance <level>]
# 미처리 목록 확인 (인자 없음)
uv run python scripts/ingest.py [--priority-only]
exit code 0 = 처리할 파일 없음, exit code 1 = 미처리 파일 있음.
Step 2: wiki 컴파일
스크립트 출력에서 미처리 파일 목록을 확인합니다.
미처리 파일이 있으면 schema/ingest.md 규칙에 따라 각 파일을 wiki 페이지로 컴파일합니다:
- 각 raw 파일 내용 읽기
schema/domains.yaml기준 도메인 분류index.md에서 관련 기존 페이지 확인- 기존 페이지 있음 → 갱신 (sources 추가, 내용 병합)
- 없음 → 신규 생성 (wiki frontmatter 포함)
- wikilink 교차 연결
index.md갱신
Step 3: 완료 표시
wiki 컴파일 완료 후:
cd "$(git rev-parse --show-toplevel)" # llm-brain 레포 루트
uv run python scripts/ingest.py --mark-done
Step 4: 그래프 delta 처리
wiki 페이지가 0개이거나 Step 2에서 변경 사항이 없으면 이 단계를 건너뜁니다.
4-0. 스냅샷 (export_graph.py 실행 전 반드시 먼저):
import sys
sys.path.insert(0, "scripts")
from ingest import snapshot_graph
snapshot_graph() # wiki/graph.json → wiki/.graph_prev.json 복사
4-1. export_graph.py 실행 (graph.json 갱신):
cd "$(git rev-parse --show-toplevel)" # llm-brain 레포 루트
uv run python scripts/export_graph.py
4-2. delta 계산 및 출력:
import sys
sys.path.insert(0, "scripts")
from ingest import run_delta_pipeline, print_delta
delta = run_delta_pipeline()
if delta:
print_delta(delta)
else:
print("[ingest] delta — 변경 없음")
Step 5: Canvas 생성
delta가 있으면 wiki/canvas/ingest-delta.canvas를 생성합니다:
import sys
sys.path.insert(0, "scripts")
from ingest import generate_ingest_delta_canvas
generated = generate_ingest_delta_canvas()
if not generated:
print("[ingest] canvas 생성 생략 (delta 없음)")
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 · 113 lines · 19 tokens per session scan A 8b1693502b36
ingest is a command published in the GitHub repository kimsanguine/llm-brain (10 stars, last pushed 22d ago), licensed MIT. It adds 19 tokens to every session and 916 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
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"…
refresh-context
Re-snapshot Core Context.md from (optional) mothership system files + key personal essays. Run when mothership files change, when new essays signal philosophy shift, or when snapshot is older than 30 days.
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).