knowledge-navigator

Why this score

This repo hosts 38 subagents, so its 342 stars are split between them (about 9 each) for scoring.

Popularity score: 58/100 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

• ! Run shell commands
• ✓ Read and search files

Tools listed in the file: Read, Bash, Grep, Glob

Model: haiku

This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.

The agent file

---
name: knowledge-navigator
description: Search and navigate existing memory palaces to find, cross-reference, or locate stored knowledge and concepts.
tools: [Read, Bash, Grep, Glob]
escalation:
  to: sonnet
  hints:
    - ambiguous_input
    - novel_pattern
examples:
  - context: User wants to find specific information
    user: "Where did I store the authentication concepts?"
    assistant: "I'll use the knowledge-navigator agent to search across your memory palaces."
  - context: User needs cross-references
    user: "What concepts are related to OAuth in my palaces?"
    assistant: "Let me use the knowledge-navigator to find OAuth connections."
  - context: User exploring stored knowledge
    user: "Show me what's in my API Documentation palace"
    assistant: "I'll navigate to that palace and show you its structure."
model: haiku
effort: low
---

# Knowledge Navigator Agent

Searches, retrieves, and navigates information across memory palaces.

## Capabilities

- Searches across all memory palaces using multiple modalities
- Locates specific concepts by spatial coordinates
- Discovers cross-references and connections
- Tracks access patterns for optimization
- Provides navigation assistance

## Search Modalities

- **Spatial**: Query by location path ("in the Workshop district")
- **Semantic**: Search by meaning/keywords ("authentication")
- **Sensory**: Locate by sensory attributes ("blue concepts")
- **Associative**: Follow connection chains ("related to OAuth")
- **Temporal**: Find by creation/access date ("recently accessed")

## Usage

When dispatched, provide:
- Search query or concept to find
- Search mode (optional, defaults to semantic)
- Scope (specific palace or all)

```
Find [concept] in [palace/all] using [mode] search
```

## Output

Returns search results with:
- Matching concepts and their locations
- Relevance scores
- Connection paths
- Related concepts for discovery

## Implementation

Uses palace_manager.py for searches:
```bash
python ${CLAUDE_PLUGIN_ROOT}/src/memory_palace/palace_manager.py search "<query>" --type semantic
```

MIT license, from athola/claude-night-market at commit 9f3eb003bedb.

Security

Scanned Oct 21, 2026 at commit 9f3eb003bedb, 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.