curator

curator is an agent for Claude Code from frankchu91/mindbase-llm-wiki. It costs 49 tokens per session (421 once invoked), scanned A, original, MIT.

A read-only wiki quality checker that reviews a project’s structure and documentation for missing links, contradictions, outdated pages, and gaps.

In plain words
What is it for?
It helps find orphaned pages, conflicting information, stale claims, missing topics, and useful cross-links.
Why use it?
It shows where project knowledge is incomplete or unreliable without changing the files itself.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the mb plugin — 1 skill, 12 commands, 5 agents, 1 hook, 1 MCP server shipped together

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/frankchu91/mindbase-llm-wiki/curator
Clone the repo
git clone --depth 1 https://github.com/frankchu91/mindbase-llm-wiki

Made for: Claude Code.

Or install mb, the plugin that ships this one along with the rest of its 1 skill, 12 commands, 5 agents, 1 hook, 1 MCP server.

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 curator

README.md
[![agentmods](https://agentmods.dev/badge/agents/frankchu91/mindbase-llm-wiki/curator.svg)](https://agentmods.dev/agents/frankchu91/mindbase-llm-wiki/curator)
Your own site
<a href="https://agentmods.dev/agents/frankchu91/mindbase-llm-wiki/curator"><img src="https://agentmods.dev/badge/agents/frankchu91/mindbase-llm-wiki/curator.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 421 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 5.1 $0.00049 $0.00421
Opus 5 $0.00024 $0.00211
Sonnet 5 $0.00010 $0.00084
Haiku 4.5 $0.00005 $0.00042

Measured 6d ago against content hash 6e71bc0d16c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 6d 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.

apps/plugin/agents/curator.md · 37 lines

What it actually says

You are the MindBase curator sub-agent.

Your job: run a health check on the current project and surface findings clearly.

Process

  1. Validate structure via mindbase_validate_structure({ projectId }).
  2. Run wiki health via mindbase_run_wiki_health({ projectId }). This calls find_orphans + find_contradictions + find_gaps + suggest_links and returns a composite report.
  3. Format findings as a Markdown card list:
    ### Orphans (N)
    - <slug> — <one-line reason>
    
    ### Contradictions (N)
    - <topic> — pages A vs B
    
    ### Stale (N)
    - <slug> — not touched since <date>
    
    ### Suggested cross-links (N)
    - <source> → <target> — <reason>
    
  4. Log via mindbase_append_log({ projectId, operation: "lint", topic: "wiki health", details: "<counts>" }).
  5. Return the formatted findings to the dispatching agent.

Anti-patterns

  • ❌ Don't fix things — just report. /mb:build is the only writer for context.md.
  • ❌ Don't dedupe findings across categories — they're often interrelated.
  • ❌ Don't suggest > 10 actions per category (too noisy).
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. 6d ago First seen · 37 lines · 49 tokens per session scan A 6e71bc0d16c4

Subscribe to this mod's changes

curator is an agent published in the GitHub repository frankchu91/mindbase-llm-wiki (95 stars, last pushed 12d ago), licensed MIT. It adds 49 tokens to every session and 421 once invoked, about $0.0002 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 2026-08-30.