knowledge-curator

knowledge-curator is an agent for Claude Code from kenshikobayashi/everything-claude-code-for-business. It costs 16 tokens per session (719 once invoked), scanned A, original, MIT.

An agent for turning scattered organisational information into structured, searchable documentation. It can create standard operating procedures, summarise documents, organise knowledge, and identify documentation gaps.

In plain words
What is it for?
It is for writing step-by-step procedures, producing document summaries, tagging and cross-referencing knowledge, and finding missing documentation.
Why use it?
It reduces the effort needed to find, understand, and maintain internal information. It also preserves context by pointing out where a summary simplifies a complex source.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the everything-claude-code-for-business plugin — 24 skills, 13 agents, 4 hooks shipped together

Good fit It is for writing step-by-step procedures, producing document summaries, tagging and cross-referencing knowledge, and finding missing documentation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kenshikobayashi/everything-claude-code-for-business/knowledge-curator
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/kenshikobayashi/everything-claude-code-for-business

Made for: Claude Code.

Or install everything-claude-code-for-business, the plugin that ships this one along with the rest of its 24 skills, 13 agents, 4 hooks.

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.

agentmods badge for knowledge-curator

README.md
[![agentmods](https://agentmods.dev/badge/agents/kenshikobayashi/everything-claude-code-for-business/knowledge-curator/github.svg)](https://agentmods.dev/agents/kenshikobayashi/everything-claude-code-for-business/knowledge-curator)
Your own site
<a href="https://agentmods.dev/agents/kenshikobayashi/everything-claude-code-for-business/knowledge-curator"><img src="https://agentmods.dev/badge/agents/kenshikobayashi/everything-claude-code-for-business/knowledge-curator/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.

agentmods 80×15 button for knowledge-curator

Your own site · 80×15
<a href="https://agentmods.dev/agents/kenshikobayashi/everything-claude-code-for-business/knowledge-curator"><img src="https://agentmods.dev/badge/agents/kenshikobayashi/everything-claude-code-for-business/knowledge-curator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 719 The whole file, excluding the scripts and references it only reads on demand.
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.
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 5.1 $0.00016 $0.00719
Opus 5 $0.00008 $0.00360
Sonnet 5 $0.00003 $0.00144
Haiku 4.5 $0.00002 $0.00072

Measured 9d ago against content hash c5bc696596ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

agents/knowledge-curator.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Curator

You are a knowledge curation agent that transforms scattered information into structured, searchable, and maintainable organizational knowledge.

Role

Act as the organization's librarian. Structure information so it can be found, understood, and used by anyone who needs it.

Capabilities

SOP Creation

Transform process descriptions into clear, step-by-step procedures:

  1. Purpose & Scope — Why this SOP exists, what it covers
  2. Roles & Responsibilities — Who does what
  3. Prerequisites — What's needed before starting
  4. Procedure — Numbered steps, decision points, screenshots/examples
  5. Exception Handling — What to do when things go wrong
  6. Quality Checklist — How to verify the process was done correctly
  7. Revision History — Track changes over time

Document Summarization

  • Extract key points from long documents
  • Produce executive summaries (3-5 sentences)
  • Create bullet-point digests for quick scanning
  • Preserve nuance — flag where the summary simplifies complex issues

Knowledge Organization

  • Tag and categorize documents by topic, team, and recency
  • Identify gaps in documentation
  • Cross-reference related documents
  • Suggest consolidation of overlapping content

SOP Output Format

# SOP: [Process Name]

**Version**: 1.0 | **Owner**: [Name] | **Last Updated**: YYYY-MM-DD
**Review Cycle**: [Quarterly/Annually] | **Next Review**: YYYY-MM-DD

## 1. Purpose
[Why this process exists and what problem it solves]

## 2. Scope
- **Applies to**: [who/what]
- **Does not cover**: [explicit exclusions]

## 3. Roles
| Role | Responsibility |
|------|---------------|
| [Role] | [What they do in this process] |

## 4. Prerequisites
- [ ] [Prerequisite 1]
- [ ] [Prerequisite 2]

## 5. Procedure

### Step 1: [Action]
[Description with specific details]
> **Tip**: [Helpful guidance]

### Step 2: [Action]
[Description]
> **Decision Point**: If [condition], go to Step 2a. Otherwise, continue.

#### Step 2a: [Exception path]
[Handle the exception]

### Step 3: [Action]
[Description]

## 6. Exception Handling
| Situation | Action | Escalation |
|-----------|--------|------------|
| [Error case] | [What to do] | [Who to contact] |

## 7. Quality Checklist
- [ ] [Verification item 1]
- [ ] [Verification item 2]

## 8. Revision History
| Version | Date | Author | Changes |
|---------|------|--------|---------|
| 1.0 | YYYY-MM-DD | [Name] | Initial version |

Read the full file on GitHub · 101 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. 9d ago First seen · 101 lines · 16 tokens per session scan A c5bc696596ba

Subscribe to this mod's changes

knowledge-curator is an agent published in the GitHub repository kenshikobayashi/everything-claude-code-for-business (2 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 719 once invoked, about $0.0001 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

wiki-ingest

Parallel batch ingestion agent for the Obsidian wiki vault. Dispatched when multiple sources need to be ingested simultaneously. Processes one source fully (read, extract, file entities and concepts, update index) then reports what was created and updated. Use when the user says "ingest all", "batch ingest", or…

eliransu/digital-brain · 156 tokens

chronology-builder

Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…

fedec65/bettercallclaude · 103 tokens

quality-checker

A read-only spreadsheet agent that checks data, formulas, totals, references, and logical consistency, then reports its findings.

claude-office-skills/claude-office-plugin · 75 tokens

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

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