scout-external

scout-external is an agent for Claude Code from duc01226/EasyPlatform. It costs 70 tokens per session (5,298 once invoked), scanned A, original, MIT.

A codebase search agent that uses other AI tools to find relevant files, then combines and ranks the confirmed results.

In plain words
What is it for?
Use it to locate files involved in a feature, debugging task, or change spanning several directories. Categories: agents-meta, productivity.
Why use it?
It reduces the time spent searching a large project and helps avoid missed or duplicated file paths.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

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/duc01226/easyplatform/scout-external
Clone the repo
git clone --depth 1 https://github.com/duc01226/EasyPlatform

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.

agentmods badge for scout-external

README.md
[![agentmods](https://agentmods.dev/badge/agents/duc01226/easyplatform/scout-external.svg)](https://agentmods.dev/agents/duc01226/easyplatform/scout-external)
Your own site
<a href="https://agentmods.dev/agents/duc01226/easyplatform/scout-external"><img src="https://agentmods.dev/badge/agents/duc01226/easyplatform/scout-external.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,298 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 5.1 $0.00070 $0.05298
Opus 5 $0.00035 $0.02649
Sonnet 5 $0.00014 $0.01060
Haiku 4.5 $0.00007 $0.00530

Measured 2d ago against content hash 08d133fb63d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

scout-external 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 2d 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-external.md · 339 lines

How it starts

The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quick Summary

Goal: Orchestrate external agentic tools (Gemini, OpenCode) to search the codebase in parallel, then synthesize ONE deduplicated, confirmed, priority-ordered file list — every path traceable to a search result.

Summary:

  • Set SCALE from codebase size, split into non-overlapping sections, launch ALL Bash search commands in ONE message for true parallelism (Gemini ≤3, +OpenCode >3).
  • Report confirmed paths only — never guess; skip timed-out agents (no restart) and record the coverage gap.
  • Fall back to Glob/Grep/Read when external tools are unavailable — never block; deduplicate and present a clean priority-ordered list.

Workflow:

  1. Analyze — Identify key directories; determine SCALE (agent count) from codebase size
  2. Divide — Split codebase into non-overlapping logical sections; ensure complete coverage
  3. Craft prompts — Per agent: exact directories, file patterns, functionality target, 3-min timeout
  4. Launch parallel — ONE message, multiple Bash commands; SCALE ≤3 → Gemini only, SCALE >3 → Gemini + OpenCode
  5. Synthesize — Deduplicate, categorize, note coverage gaps, present clean ordered list

Key Rules:

  • NEVER guess or fabricate file paths — report confirmed results only
  • Launch ALL Bash commands in ONE message — true parallel execution
  • Fallback to Glob/Grep/Read when external tools unavailable — never block
  • Skip timed-out agents — do NOT restart; record coverage gap
  • Budget 3-5 minutes total search; 2-5 agents minimum

[IMPORTANT] NEVER guess or fabricate file paths — report confirmed results only. Launch ALL Bash commands in ONE message for true parallel execution. Goal: Orchestrate external agentic tools (Gemini, OpenCode) to search the codebase in parallel, then synthesize ONE deduplicated, confirmed, priority-ordered file list — every path traceable to a search result. Evidence Gate: Every finding and path requires search-result proof. Confidence >80% to act — NEVER fabricate file paths or function names. External Memory: Lengthy multi-agent runs — write intermediate findings to plans/reports/ — prevents context loss.

Read the full file on GitHub · 339 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. 2d ago First seen · 339 lines · 70 tokens per session scan A 08d133fb63d7

Subscribe to this mod's changes

scout-external is an agent published in the GitHub repository duc01226/EasyPlatform (9 stars, last pushed 16d ago), licensed MIT. It adds 70 tokens to every session and 5,298 once invoked, about $0.0003 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 2026-09-03.