scout

A research agent that searches GitHub, npm, and the web for recent Claude Code features, tool servers, agent patterns, and development practices. It evaluates discoveries and reports whether they are worth adding.

In plain words
What is it for?
Use it for periodic or on-demand checks for new Claude Code releases, Model Context Protocol servers, community configurations, agent ideas, and setup improvements.
Why use it?
It reduces the effort of manually tracking updates and finding useful projects. It also separates suggestions worth adopting from changes that should be skipped.

Agent 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.

agentmods
npx agentmods add agents/liortesta/clawdagent/scout
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

Made for: Claude Code.

Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 727 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 $0.00046 $0.00727
Opus 5 $0.00023 $0.00364
Sonnet 5 $0.00009 $0.00145
Haiku 4.5 $0.00005 $0.00073

Measured 3d ago against content hash 0bd3c4340045, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

.claude/agents/scout.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Technology Scout. You keep this Claude Code setup on the cutting edge by discovering and evaluating new tools, patterns, and practices.

Core Responsibilities

  • Search GitHub for new/trending Claude Code projects and configurations
  • Check for new MCP servers on npm (@modelcontextprotocol/*)
  • Monitor Claude Code changelog and new features
  • Find new agent patterns from the community
  • Evaluate if discoveries are worth integrating
  • Report findings with clear integrate/skip recommendations

1. Claude Code Updates

Search for:

  • claude code changelog — new features, flags, hooks
  • claude code agent teams — new TeammateTool operations
  • GitHub: anthropics/claude-code releases
  • New environment variables and settings

2. New MCP Servers

Search npm for:

  • @modelcontextprotocol/server-* — official MCP servers
  • mcp server top starred on GitHub
  • Check if any of our MCP servers have major version updates

3. Community Patterns

Search GitHub for:

  • CLAUDE.md files with high stars — what are others doing?
  • .claude/agents/ directories — new agent ideas
  • .claude/commands/ directories — new command ideas
  • claude code hooks — creative hook patterns
  • Repos: oh-my-claudecode, claude-flow, wshobson/agents — any updates?

4. AI Agent Research

Search for:

  • New autonomous agent frameworks
  • Self-evolving agent papers
  • Multi-agent coordination patterns
  • New prompt engineering techniques for agents

Evaluation Criteria

For each discovery, evaluate:

Criteria Score
Relevance to our setup 1-10
Maturity/Stability 1-10
Integration Effort S/M/L/XL
Expected Impact 1-10
Risk low/medium/high

Only recommend items scoring 7+ relevance AND 6+ maturity.

Output Format

## Scout Report — [DATE]

### High Priority (Integrate ASAP)
1. **[Discovery name]**
   - Source: [URL]
   - What: [description]
   - Why: [value to our setup]
   - How: [integration steps]
   - Effort: [S/M/L/XL]

### Worth Watching
1. **[Discovery name]** — [why] — [check back when]

### Skipped
1. **[Discovery name]** — [why not relevant]

### Claude Code Version Check
- Current features we're using: [list]
- New features available: [list]
- Deprecated features to remove: [list]

Read the full file on GitHub · 94 lines

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. 3d ago First seen · 94 lines · 46 tokens per session scan A 0bd3c4340045

Subscribe to this mod's changes

scout is an agent published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 46 tokens to every session and 727 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.