A team knowledge-base workflow plugin that connects coding agents to an MCP knowledge-base server. It provides skills for starting a work brief, recording events, and saving the finished record.

Use it to brief work at the start, log important events as they happen, and flush the completed notes to the team knowledge base. It can connect to a local or remote server with an optional access token.

It helps teams keep development decisions and progress from being lost during or between coding sessions.

kb-workflow — Plugin for Claude Code by 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.

Clone the repo

git clone --depth 1 https://github.com/riemannulus/knowledge-base

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/riemannulus/knowledge-base/kb-workflow/github.svg)](https://agentmods.dev/plugins/riemannulus/knowledge-base/kb-workflow)

Your own site

<a href="https://agentmods.dev/plugins/riemannulus/knowledge-base/kb-workflow"><img src="https://agentmods.dev/badge/plugins/riemannulus/knowledge-base/kb-workflow/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/riemannulus/knowledge-base/kb-workflow"><img src="https://agentmods.dev/badge/plugins/riemannulus/knowledge-base/kb-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 3 skills, 1 command, 3 hooks, 1 MCP server cost 358 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

kb-workflow 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 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.

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.

plugins/kb-workflow/.claude-plugin/plugin.json · 28 lines

What it actually says

{
  "name": "kb-workflow",
  "version": "0.2.1",
  "description": "팀 지식베이스(kb MCP) 개발 워크플로 — 착수 브리핑(kb-brief) · 발생 즉시 기록(kb-log) · 원장 flush(kb-wrap) 스킬 + 기록 유실 방지 훅(Stop/SessionStart/PreCompact) + kb MCP 서버 연결. 설치 시 서버 URL/토큰을 물어본다 (로컬 compose는 기본값 엔터).",
  "author": {
    "name": "riemannulus",
    "url": "https://github.com/riemannulus/knowledge-base"
  },
  "homepage": "https://github.com/riemannulus/knowledge-base",
  "mcpServers": "./.mcp.json",
  "userConfig": {
    "kb_mcp_url": {
      "type": "string",
      "title": "KB MCP 서버 URL",
      "description": "로컬 docker compose는 기본값 그대로 엔터. 팀 원격 서버는 https://kb.example.com/mcp 형태로 입력",
      "default": "http://127.0.0.1:8000/mcp",
      "required": false
    },
    "kb_auth_token": {
      "type": "string",
      "title": "KB 접근 토큰",
      "description": "원격 서버의 베어러 토큰 (kb token create로 발급, kbt_ 접두). 로컬 무인증 모드면 비워두기",
      "sensitive": true,
      "required": false
    }
  }
}

Contents

What it installs

The manifest is a name and a version. 3 skills, 1 command, 3 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 358 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

1mo ago First seen · 28 lines scan A 0d47d7c6590a

Subscribe to this mod's changes

kb-workflow is a plugin published in the GitHub repository riemannulus/knowledge-base (1 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Building agents LLM Memory and context claude embeddings full-text-search hybrid-search knowledge-base

mb

Karpathy's LLM-Wiki pattern as a Claude Code plugin. Build and maintain a persistent, AI-tended research wiki from sources, capture daily thoughts, query what you know, lint for orphans and contradictions. Operations: /mb:init, /mb:contribute, /mb:build, /mb:ask, /mb:lint, /mb:status, /mb:research, /mb:daily-brief…

frankchu91/mindbase-llm-wiki · not measured

kb-workflow

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Nothing flagged

What it actually says

What it installs

What this file has done since we first saw it

Other plugins, from other repositories

mb

markdown-vault-mcp

llm-wiki-manager

gnosis

agent-knowledge

subcog