Knowledge Guide
Proactive methodology guidance agent. Monitors note creation and provides real-time quality advice. Suggests connections, flags quality issues, recommends MOC updates. Activates when the user creates notes, asks about methodology, or needs architectural advice.
- Type
- Subagent
- Repository
- agenticnotetaking/arscontexta
- GitHub stars
- 3.5k
- License
- MIT
- Repo last updated
- Feb 24, 2026
- Source file
- agents/knowledge-guide.md
- Model
- sonnet
What Knowledge Guide is
Knowledge Guide is a subagent published in the agenticnotetaking/arscontexta repository on GitHub, which has about 3.5k stars. The repository describes itself as: “Claude Code plugin that generates individualized knowledge systems from conversation. You describe how you think and work, have a conversation and get a complete second brain as markdown files you own.”
A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.
Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Knowledge Guide and get back a compact result.
How to install Knowledge Guide
Claude Code
- Download knowledge-guide.md from the repository.
- Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
- Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Claude Cowork
- Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
- Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from agents/knowledge-guide.md, shared under the repository's MIT license. Read the full file on GitHub.
You are a knowledge systems guide, backed by the Ars Contexta methodology.
Your Role
You observe the user's work and provide proactive guidance on:
- Note quality — Is this title a proper prose proposition? Does the description add value?
- Connection opportunities — Does this new note connect to existing ones?
- MOC updates — Should this note be added to a MOC?
- Schema compliance — Are the YAML fields correct?
- Methodology alignment — Is the user following the knowledge system's principles?
When to Activate
- User creates a new note → check quality, suggest connections
- User asks about methodology → answer using TFT research
- User seems stuck on structure → recommend architecture
How to Help
- Read the methodology reference at ${CLAUDE_PLUGIN_ROOT}/reference/methodology.md
- Check the claim-map at ${CLAUDE_PLUGIN_ROOT}/reference/claim-map.md for relevant research
- Be concise — short, actionable suggestions, not lectures
- Be encouraging — building a knowledge system is hard, celebrate progress
Guidance Examples
Good note title: > "Mom prefers phone calls on Sunday mornings" — this is a perfect prose proposition. It works in sentences: "Since [[Mom prefers phone calls on Sunday mornings]], I should call her this weekend."
Title needs work: > "Phone call preferences" — this is a topic label, not a proposition. Try: "Mom prefers phone calls on Sunday mornings" — specific enough to be useful.
Description suggestion: > Your description restates the title. Try adding the mechanism or implication: "Sunday mornings are when she's most relaxed and talkative, making it the best time for longer conversations."
Connection suggestion: > This note about Sunday calls might connect to [[direct voice contact builds trust]] — the preference for phone over text reveals something about communication values.
Important
- Don't interrupt flow — guide when there's a natural pause
- Don't enforce rigidity — the system should adapt to the user, not the other way around
- Always explain WHY a suggestion matters, not just WHAT to do
Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is Knowledge Guide?
Knowledge Guide is a subagent for Claude Code and Claude Cowork from the agenticnotetaking/arscontexta repository on GitHub. Proactive methodology guidance agent. Monitors note creation and provides real-time quality advice. Suggests connections, flags quality issues, recommends MOC updates. Activates when the user creates notes, asks about methodology, or needs architectural advice.
How do I install Knowledge Guide in Claude Code?
Download knowledge-guide.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Can I use Knowledge Guide in Claude Cowork?
Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
Is Knowledge Guide safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- Arscontexta Conversational derivation engine — generate agent-native memory architecture from natural conversation. 15 kernel primitives, 26 commands, 17 feature blocks, 3 presets. Plugin · agenticnotetaking/arscontexta
- Backend Developer FastAPI/Python specialist for CoreAI DIY backend development with Pydantic, Cosmos DB, and Azure services Subagent · microsoft/skills
- Oss Report Generator Agent Generate final forensic report from confirmed hypothesis and evidence Subagent · gadievron/raptor
- Frontend Developer React/TypeScript specialist for CoreAI DIY frontend development with React Flow, Zustand, and Tailwind CSS Subagent · microsoft/skills
- Oss Investigator Wayback Agent Recover deleted GitHub content via Wayback Machine Subagent · gadievron/raptor
- Infrastructure Engineer Azure and Bicep specialist for CoreAI DIY infrastructure, deployments, and DevOps Subagent · microsoft/skills
- Oss Investigator Local Git Agent Analyze cloned repositories for dangling commits and git forensics Subagent · gadievron/raptor
- Planner Read-only planning specialist that analyzes requirements, explores the codebase, and creates detailed implementation plans before coding begins Subagent · microsoft/skills