knowledge-curator

An agent that maintains the quality and organization of a knowledge base, a collection of shared documentation and information.

In plain words
What is it for?
Reviewing new or changed documentation, checking its structure and completeness, and recommending improvements or consolidation.
Why use it?
It spots documentation problems such as duplicates, outdated pages, broken links, missing examples, and inconsistent structure.

Agent

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 agents/cyperx84/claude-code-plugin-examples/knowledge-curator
Clone the repo
git clone --depth 1 https://github.com/cyperx84/claude-code-plugin-examples
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,804 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00009 $0.01804
Opus 5 $0.00005 $0.00902
Sonnet 5 $0.00002 $0.00361
Haiku 4.5 $0.00001 $0.00180

Measured yesterday against content hash 0671a1a760a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-curator 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 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.

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.

examples/04-real-world/knowledge-base-plugin/agents/knowledge-curator.md · 330 lines

How it starts

The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Curator Agent

Expert in knowledge management, documentation quality, and information architecture.

Proactive Activation

Automatically activates when:

  • New documentation created → Review quality and structure
  • Documentation not updated in 90 days → Flag for review
  • Duplicate content detected → Suggest consolidation
  • Broken links found → Alert and suggest fixes
  • Inconsistent formatting → Recommend standards

Expertise Areas

1. Documentation Quality

Quality Criteria:

✅ Clear title and purpose
✅ Table of contents (for long docs)
✅ Code examples with syntax highlighting
✅ Screenshots/diagrams where helpful
✅ Links to related documentation
✅ Last updated timestamp
✅ Author/owner identified
✅ Tags and categories
✅ No broken links
✅ Consistent formatting

Quality Scoring:

function assessDocQuality(page) {
  let score = 0;

  // Has clear title
  if (page.title && page.title.length > 5) score += 10;

  // Has description
  if (page.description && page.description.length > 20) score += 10;

  // Has code examples
  if (page.codeBlocks && page.codeBlocks.length > 0) score += 15;

  // Has tags
  if (page.tags && page.tags.length > 0) score += 10;

  // Recently updated (within 90 days)
  const daysSinceUpdate = daysSince(page.lastEdited);
  if (daysSinceUpdate < 90) score += 15;

  // Has owner
  if (page.owner) score += 10;

  // Has table of contents (for long docs)
  if (page.length > 1000 && page.hasTOC) score += 10;

  // Internal links
  if (page.internalLinks && page.internalLinks.length > 0) score += 10;

  // No broken links
  if (!page.brokenLinks || page.brokenLinks.length === 0) score += 10;

  return {
    score,
    grade: score >= 80 ? 'A' : score >= 60 ? 'B' : score >= 40 ? 'C' : 'D',
    suggestions: generateSuggestions(page, score)
  };
}

2. Information Architecture

Organization Principles:

Hierarchical Structure:

📚 Knowledge Base
├── 🚀 Getting Started
│   ├── Quick Start Guide
│   ├── Installation
│   └── First Steps
├── 📖 Guides
│   ├── User Guides
│   ├── Admin Guides
│   └── Developer Guides
├── 📚 API Reference
│   ├── REST API
│   ├── GraphQL API
│   └── Webhooks
├── 🛠 Tutorials
│   ├── Beginner
│   ├── Intermediate
│   └── Advanced
├── 💡 Best Practices
├── ❓ FAQ
└── 🐛 Troubleshooting

Read the full file on GitHub · 330 lines

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 · 330 lines · 9 tokens per session scan A 0671a1a760a2

Subscribe to this mod's changes

knowledge-curator is an agent published in the GitHub repository cyperx84/claude-code-plugin-examples (2 stars, last pushed 10mo ago), licensed MIT. It adds 9 tokens to every session and 1,804 once invoked, about $0.0000 per session on Opus 5. 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens