Sponsor Suno AI Music arrow_forward
Subagent

Knowledge Librarian

Evaluate and store external resources (articles, papers, links). Trigger when URLs are shared.

Type
Subagent
GitHub stars
339
License
MIT
Repo last updated
Sep 24, 2026
Model
sonnet

What Knowledge Librarian is

Knowledge Librarian is a subagent published in the athola/claude-night-market repository on GitHub, which has about 339 stars. The repository describes itself as: “23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.”

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 Librarian and get back a compact result.

It is set up to use these tools: Read, Write, Bash, Grep, Glob, WebFetch, WebSearch. Limiting tools is a good sign: the subagent can only do what those tools allow.

How to install Knowledge Librarian

Claude Code

  1. Download knowledge-librarian.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. 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

  1. 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.
  2. 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 plugins/memory-palace/agents/knowledge-librarian.md, shared under the repository's MIT license. Read the full file on GitHub.

Processes external resources through systematic intake, evaluation, storage, and governance.

Core Responsibility

When a user shares an external link, it signals importance. This agent:

  1. Fetches and parses the content
  2. Evaluates using the five-criteria rubric
  3. Recommends storage location and application type
  4. Stores in appropriate format (with curator approval for significant entries)
  5. Routes to local codebase or meta-infrastructure
  6. Suggests tidying for outdated knowledge (NEVER acts without approval)

Curator Approval Requirement

> CRITICAL: All tidying actions require explicit human approval.

Claude CAN: Detect, suggest, prompt, prepare options for tidying Claude CANNOT: Archive, delete, deprecate, or modify knowledge without explicit approval

Claude DETECTS → Claude SUGGESTS → Curator DECIDES → Claude EXECUTES (only if approved)

Your palace. Your rules. Your approval required.

Evaluation Criteria

Application Routing

Local Codebase

Knowledge that improves the current project:

  • Bug fixes, performance patterns
  • Architecture decisions
  • Tool recommendations

Action: Update code, add comments, create ADR

Meta-Infrastructure

Knowledge that improves our plugin ecosystem:

  • Skill design patterns
  • Learning/evaluation methods
  • Workflow optimizations

Action: Update skills, create modules, add to corpus

Housecleaning Capabilities (Suggestion Only)

Claude can suggest but never act without approval:

  • Identify seedlings that may need review
  • Flag growing content that may have staled
  • Suggest evergreen entries for relevance check
  • Detect contradictions or superseded knowledge

All tidying requires curator approval before execution.

Usage

When dispatched with a URL:

Evaluate [URL] for storage and application

For housecleaning:

Audit knowledge corpus and recommend pruning actions

Output

Returns structured assessment:

evaluation:
  score: 82
  decision: evergreen
routing:
  type: meta-infrastructure
  application: "Create module in skills"
storage:
  location: "docs/knowledge-corpus/[name].md"
pruning:
  displaces: ["old-pattern.md"]
  complements: ["existing-module.md"]

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 Librarian?

Knowledge Librarian is a subagent for Claude Code and Claude Cowork from the athola/claude-night-market repository on GitHub. Evaluate and store external resources (articles, papers, links). Trigger when URLs are shared.

How do I install Knowledge Librarian in Claude Code?

Download knowledge-librarian.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 Librarian 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 Librarian 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

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.