A command for scouting selected directories to locate files relevant to a coding request. It delegates the search to other coding agents and saves their findings under plans/scouts/.

Use it to search specified directories for relevant files, choose a search scale, and collect the delegated agents’ results in the project’s scouting folder.

It helps narrow a large codebase to the files needed for a task, reducing manual searching and the amount of information the main agent must inspect.

How mrgoonie/human-mcp configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/mrgoonie/human-mcp/main/.claude/commands/scout.md

Clone the repo

git clone --depth 1 https://github.com/mrgoonie/human-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/mrgoonie/human-mcp/scout.svg)](https://agentmods.dev/commands/mrgoonie/human-mcp/scout)

Your own site

<a href="https://agentmods.dev/commands/mrgoonie/human-mcp/scout"><img src="https://agentmods.dev/badge/commands/mrgoonie/human-mcp/scout.svg" alt="Measured on agentmods" height="20"></a>

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 367 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00009	$0.00367
Opus 5	$0.00005	$0.00183
Sonnet 5	$0.00002	$0.00073
Haiku 4.5	$0.00001	$0.00037

Measured 7d ago against content hash 9a33c5e57026, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 7d 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/commands/scout.md · 29 lines

What it actually says

Purpose

Search the codebase for files needed to complete the task using a fast, token efficient agent.

User's requests & target directories

<user_requests>$ARGUMENTS</user_requests>

Variables

USER_PROMPT: $1 SCALE: $2 (defaults to 3) RELEVANT_FILE_OUTPUT_DIR: plans/scouts/

Workflow:

Write a prompt for 'SCALE' number of agents to the Task tool that will immediately call the Bash tool to run these commands to kick off your agents to conduct the search:
- gemini -p "[prompt]" --model gemini-2.5-flash-preview-09-2025
- opencode run "[prompt]" --model opencode/grok-code (if count > 3)

How to prompt the agents:

IMPORTANT: Kick these agents off in parallel using the Task tool, analyze and divide folders for each agent to scout intelligently and quickly.
IMPORTANT: These agents are calling OTHER agentic coding tools to search the codebase. DO NOT call any search tools yourself.
IMPORTANT: That means with the Task tool, you'll immediately call the Bash tool to run the respective agentic coding tool (gemini, opencode, claude, etc.)
IMPORTANT: Instruct the agents to quickly search the codebase for files needed to complete the task. This isn't about a full blown search, just a quick search to find the files needed to complete the task.
Instruct the subagent to use a timeout of 3 minutes for each agent's bash call. Skip any agents that don't return within the timeout, don't restart them.

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.

7d ago First seen · 29 lines · 0 tokens per session scan A 9a33c5e57026

Subscribe to this mod's changes

scout is a command published in the GitHub repository mrgoonie/human-mcp (294 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 367 once invoked, about $0.0000 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.

Planning claudecode claw goclaw mcp openclaw skills

human-mcp: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Purpose

User's requests & target directories

Variables

Workflow:

What this file has done since we first saw it

Other commands, from other repositories

report

explain

env-setup

debug-pod

document-all

fix-comments