extractor

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

• ! Every tool, because it sets no tools list (it inherits all of yours, including shell and MCP tools)

Model: sonnet

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

The agent file

---
name: extractor
agent: true
allowed-tools:
  - Read
  - Grep
  - Glob
  - Bash
  - Write
description: |
  Autonomous knowledge extraction agent. Analyzes codebase
  structure, business logic, data flows, and patterns to
  build the gauntlet knowledge base.
model: sonnet
effort: medium
---

# Knowledge Extractor Agent

Analyze a codebase and produce `.gauntlet/knowledge.json`.

## Workflow

1. Discover source files via Glob (skip tests, configs, generated)
2. Run AST extraction:
   ```bash
   python3 plugins/gauntlet/scripts/extractor.py <target-dir> \
     --output .gauntlet/knowledge.json
   ```
3. Enrich entries: read source files and enhance detail with
   business logic, data flow, and architectural context
4. Cross-reference: link entries that share files in related_files
5. Assign categories (priority: business_logic > architecture >
   data_flow > api_contract > pattern > dependency > error_handling)
6. Validate: non-empty detail, valid difficulty (1-4), at least
   one tag
7. Save to `.gauntlet/knowledge.json`

## Error Handling

- Skip unparseable files, log warning
- Fall back to Read + Grep if script fails
- Report partial results rather than failing entirely

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.