code-scout

A research toolkit for investigating software and machine-learning topics across GitHub, Hugging Face, websites, documentation, and research papers. It includes separate scouts and a tool for combining their findings.

In plain words
What is it for?
Use it for code or machine-learning research, including finding repositories, models, documentation, papers, and web information. It also supports deeper searches and selected Bright Data web-access tools.
Why use it?
Research spread across many sources is slow to coordinate and easy to miss. This toolkit organizes searches by source and provides fallback methods when a site is blocked or unavailable.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add YoungjaeDev/my-claude-plugins
agentmods
npx agentmods add plugins/youngjaedev/my-claude-plugins/code-scout
Clone the repo
git clone --depth 1 https://github.com/YoungjaeDev/my-claude-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

code-scout 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 yesterday.

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.

plugins/code-scout/.claude-plugin/plugin.json · 22 lines

What it actually says

{
  "name": "code-scout",
  "version": "3.0.0",
  "description": "Multi-axis code & ML research harness. 5-axis scout team (github/hf/web/docs/paper) + synthesis-scout + research-orchestrator skill + exa-web-search skill. exa MCP first, WebSearch fallback, brightdata tier-3, insane-search tier-4 (WAF/blocked URLs). paper-scout wraps paper-search-tools 8-source family. /deep-research is the sibling for non-code/ML topics (code-scout does not delegate). Also ships brightdata-guide for Bright Data web data access (Web Unlocker scraping, SERP, structured web_data_* extractors) via MCP tools and the bdata CLI.",
  "skills": [
    "./skills/research-orchestrator",
    "./skills/exa-web-search",
    "./skills/resource-finder",
    "./skills/brightdata-guide"
  ],
  "agents": [
    "./agents/github-scout.md",
    "./agents/hf-scout.md",
    "./agents/web-scout.md",
    "./agents/docs-scout.md",
    "./agents/paper-scout.md",
    "./agents/synthesis-scout.md",
    "./agents/scout.md",
    "./agents/deep-scout.md"
  ]
}
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. yesterday First seen · 22 lines scan A 66d5ea7d5bf4

Subscribe to this mod's changes

code-scout is a plugin published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed 6d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.