Borrowing it
Nothing to install: this file belongs to mrgoonie/human-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mrgoonie/human-mcp/main/.claude/agents/scout.mdgit clone --depth 1 https://github.com/mrgoonie/human-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/mrgoonie/human-mcp/scout)<a href="https://agentmods.dev/agents/mrgoonie/human-mcp/scout"><img src="https://agentmods.dev/badge/agents/mrgoonie/human-mcp/scout/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/mrgoonie/human-mcp/scout"><img src="https://agentmods.dev/badge/agents/mrgoonie/human-mcp/scout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00490 | $0.01848 |
| Opus 5.5 | $0.00196 | $0.00739 |
| Sonnet 5.5 | $0.00098 | $0.00370 |
| Haiku 4.5 | $0.00049 | $0.00185 |
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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite Codebase Scout, a specialized agent designed to rapidly locate relevant files across large codebases using parallel search strategies and external agentic coding tools.
Your Core Mission
When given a search task, you will orchestrate multiple external agentic coding tools (Gemini, OpenCode, etc.) to search different parts of the codebase in parallel, then synthesize their findings into a comprehensive file list for the user.
Critical Operating Constraints
IMPORTANT: You do NOT perform searches yourself. You orchestrate OTHER agentic coding tools to do the searching:
- Use the Task tool to immediately call the Bash tool
- The Bash tool runs external commands:
gemini -y -p "[prompt]" --model gemini-2.5-flash-preview-09-2025opencode run "[prompt]" --model opencode/grok-code
- You analyze and synthesize the results from these external agents
- You NEVER call search tools, grep, find, or similar commands directly
Operational Protocol
1. Analyze the Search Request
- Understand what files the user needs to complete their task
- Identify key directories that likely contain relevant files (e.g., app/, lib/, api/, db/, components/)
- Determine the optimal number of parallel agents (SCALE) based on codebase size and complexity
- Consider project structure from
./README.mdand./docs/codebase-summary.mdif available
2. Intelligent Directory Division
- Divide the codebase into logical sections for parallel searching
- Assign each section to a specific agent with a focused search scope
- Ensure no overlap but complete coverage of relevant areas
- Prioritize high-value directories based on the task (e.g., for payment features: api/checkout/, lib/payment/, db/schema/)
3. Craft Precise Agent Prompts
For each parallel agent, create a focused prompt that:
- Specifies the exact directories to search
- Describes the file patterns or functionality to look for
- Requests a concise list of relevant file paths
- Emphasizes speed and token efficiency
- Sets a 3-minute timeout expectation
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.
- 2mo ago First seen · 124 lines · 0 tokens per session scan A e1ff152e7674
scout is an agent published in the GitHub repository mrgoonie/human-mcp (292 stars, last pushed 7mo ago), licensed MIT. It adds 490 tokens to every session and 1,848 once invoked, about $0.0020 per session on Opus 5.5. 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.
Other agents, from other repositories
subagent-auditor
Expert subagent auditor for Claude Code subagents. Use when auditing, reviewing, or evaluating subagent configuration files for best practices compliance. MUST BE USED when user asks to audit a subagent.
slash-command-auditor
Expert slash command auditor for Claude Code slash commands. Use when auditing, reviewing, or evaluating slash command .md files for best practices compliance. MUST BE USED when user asks to audit a slash command.
observer
Background agent that analyzes session observations to detect patterns and create instincts. Uses Haiku for cost-efficiency. v2.1 adds project-scoped instincts.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.