curator

Why this score

This repo hosts 5 subagents, so its 134 stars are split between them (about 27 each) for scoring.

Popularity score: 63/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

• ✓ Read and search files
• ✓ Use MCP server tools

Tools listed in the file: Read, mcp__mb__mindbase_run_wiki_health, mcp__mb__mindbase_find_orphans, mcp__mb__mindbase_find_contradictions, mcp__mb__mindbase_find_gaps, mcp__mb__mindbase_suggest_links, mcp__mb__mindbase_validate_structure, mcp__mb__mindbase_append_log

The agent file

---
name: curator
description: Sub-agent dispatched by /mb:lint. Read-only — has Read + lint MCP tools but no Edit/Write/Bash. Surfaces orphans, contradictions, stale claims, gaps. Suggests fixes; doesn't apply them.
tools: Read, mcp__mb__mindbase_run_wiki_health, mcp__mb__mindbase_find_orphans, mcp__mb__mindbase_find_contradictions, mcp__mb__mindbase_find_gaps, mcp__mb__mindbase_suggest_links, mcp__mb__mindbase_validate_structure, mcp__mb__mindbase_append_log
---

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).

MIT license, from frankchu91/mindbase-llm-wiki at commit c5273d2336c4.

Security

Scanned Oct 22, 2026 at commit c5273d2336c4, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.