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.
git clone --depth 1 https://github.com/riemannulus/knowledge-baseWrote 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/riemannulus/knowledge-base/setup)<a href="https://agentmods.dev/commands/riemannulus/knowledge-base/setup"><img src="https://agentmods.dev/badge/commands/riemannulus/knowledge-base/setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/riemannulus/knowledge-base/setup"><img src="https://agentmods.dev/badge/commands/riemannulus/knowledge-base/setup.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00032 | $0.00582 |
| Opus 5.5 | $0.00013 | $0.00233 |
| Sonnet 5.5 | $0.00006 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade B, and why
setup scanned grade B with 2 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
다시 열거나, `~/.claude/settings.json`의 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`docker compose up -d` 후 `curl -s -o /dev/null -w "%{http_code}" -X POST What it actually says
kb MCP 서버 연결을 점검하고, 문제가 있으면 원인별로 안내하라.
절차
-
연결 확인: kb 서버의
list_sources도구를 호출한다.- 성공 → 인덱싱된 소스/문서 수를 요약해 보여주고 "연결 정상"으로 마친다.
- kb 도구 자체가 목록에 없거나 호출 실패 → 2번으로.
-
진단 (실패 시): 아래를 순서대로 확인해 해당되는 안내를 하라.
- 설정값 확인: 이 플러그인의 서버 URL/토큰은 설치 시 입력받은
userConfig 값이다 (
${user_config.kb_mcp_url}로 MCP 설정에 치환됨). 값 변경은/plugin메뉴에서 kb-workflow 플러그인의 설정(Configure)을 다시 열거나,~/.claude/settings.json의pluginConfigs["kb-workflow@knowledge-base"].options에서 직접 수정 (토큰은 sensitive라 보안 저장소에 있음 — 파일에는 안 보인다). 변경 후/mcp에서 kb 서버를 재연결하라고 안내. - 로컬(기본값 127.0.0.1:8000)인데 실패: KB 스택이 떠 있는지 —
docker compose up -d후curl -s -o /dev/null -w "%{http_code}" -X POST http://127.0.0.1:8000/mcp -d '{}'가 401/406이면 서버는 정상(인증 단계). - 원격인데 401: 토큰 문제 — 관리자에게
kb token create <이름>으로 발급받아 재설정. - URL 오타/미도달: URL이
/mcp로 끝나는지, VPN/터널 안인지 확인.
- 설정값 확인: 이 플러그인의 서버 URL/토큰은 설치 시 입력받은
userConfig 값이다 (
-
프로젝트 단위 오버라이드가 필요하면: 프로젝트
.mcp.json에 같은 이름kb서버를 정의하면 플러그인 정의보다 우선한다(Local > Project > User > Plugin). 예: stdio 직결{"mcpServers": {"kb": {"command": "kb", "args": ["mcp"]}}}.
$ARGUMENTS가 비어 있지 않으면 사용자가 새 서버 URL을 준 것일 수 있다 — 그 값으로 위 재설정 경로를 안내하라.
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.
- 1mo ago First seen · 35 lines · 32 tokens per session scan B a5cdf3b70310
setup is a command published in the GitHub repository riemannulus/knowledge-base (1 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 582 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
init
Scaffold a new MindBase project (v2 layout). Usage: /mb:init [template] [-- mission ...].
ask
Query the MindBase wiki — cited answer using hybrid search + graph expansion. Usage: /mb:ask [-p ] [--all-projects].
export
Export a project to a portable bundle. Usage: /mb:export [-p ] [target].
prompts
Work with MCP prompt templates for memory operations.
save-memory
You are saving what you learned this session into the megamemory knowledge graph. This is YOUR memory — record anything valuable for future sessions: what you understood about the project, what you built, decisions that were made, patterns you noticed, or intent the user shared.
bootstrap-memory
RUN { git ls-files; git ls-files --others --exclude-standard; } 2>/dev/null | sort -u | xargs wc -l 2>/dev/null | sort -rn | head -150 READ README.md.