agentmods.dev

setup

A command that checks and explains the connection between the coding agent and the kb knowledge-base server.

In plain words
What is it for?
Use it after installation, when changing the server address or access token, or when the knowledge-base connection fails.
Why use it?
It helps identify whether the problem is a missing service, incorrect address, invalid token, VPN issue, or configuration mismatch.

Command

1 20d ago B scan 32 tokens original MIT
View the source file riemannulus/knowledge-base
Install

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.

agentmods
npx agentmods add commands/riemannulus/knowledge-base/setup
Clone the repo
git clone --depth 1 https://github.com/riemannulus/knowledge-base
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 582 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00032 $0.00582
Opus 5 $0.00016 $0.00291
Sonnet 5 $0.00006 $0.00116
Haiku 4.5 $0.00003 $0.00058

Measured yesterday against content hash a5cdf3b70310, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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
plugins/kb-workflow/commands/setup.md · 35 lines

What it actually says

kb MCP 서버 연결을 점검하고, 문제가 있으면 원인별로 안내하라.

절차

  1. 연결 확인: kb 서버의 list_sources 도구를 호출한다.

    • 성공 → 인덱싱된 소스/문서 수를 요약해 보여주고 "연결 정상"으로 마친다.
    • kb 도구 자체가 목록에 없거나 호출 실패 → 2번으로.

  2. 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 /plugin 메뉴에서 kb-workflow 플러그인의 설정(Configure)을 다시 열거나, ~/.claude/settings.json의 pluginConfigs["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 -d 후 curl -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.

  3. 프로젝트 단위 오버라이드가 필요하면: 프로젝트 .mcp.json에 같은 이름 kb 서버를 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.

Changes

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.

  1. yesterday First seen · 35 lines · 32 tokens per session scan B a5cdf3b70310

Subscribe to this mod's changes

setup is a command published in the GitHub repository riemannulus/knowledge-base (1 stars, last pushed 20d ago), licensed MIT. It adds 32 tokens to every session and 582 once invoked, about $0.0002 per session on Opus 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.

Data and AILLMMemory and contextResearchclaudeembeddingsfull-text-searchhybrid-searchknowledge-base
Related

Other commands, from other repositories

spec-orchestrator

Orchestrate implementation of a large specification using parallel agent teams. Reads specs via discovery subagents, synthesizes a task plan, spawns implementation teammates, and manages wave-based execution.

zircote/subcog · 42 tokens

integrate

Analyze and enhance AI artifacts to leverage Subcog memory effectively.

zircote/subcog · 12 tokens

run-tests

Run automated functional tests for Subcog MCP tools. Execute the test suite to validate all MCP tool functionality including memory CRUD, search, knowledge graph, prompts, templates, and maintenance operations.

zircote/subcog · 41 tokens

namespaces

List and explain available memory namespaces.

zircote/subcog · 6 tokens

prompts

Work with MCP prompt templates for memory operations.

zircote/subcog · 8 tokens

recall

Search persistent memories using semantic, hybrid, or text search.

zircote/subcog · 11 tokens