scout-external

A codebase-search role that uses external coding agents to locate files across large projects. It divides the search, runs searches in parallel when possible, combines results, and falls back to ordinary file search if needed.

In plain words
What is it for?
Locating files and code across separate parts of a large codebase, coordinating Gemini or OpenCode searches, removing duplicate results, and returning an organized file list.
Why use it?
It reduces the time and effort needed to find relevant files in a large repository. It also reports missing coverage when an external search tool is unavailable or incomplete.

Agent

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/ihatesea69/kiro-kit/scout-external
Clone the repo
git clone --depth 1 https://github.com/ihatesea69/kiro-kit
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 330 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 $0.00038 $0.00330
Opus 5 $0.00019 $0.00165
Sonnet 5 $0.00008 $0.00066
Haiku 4.5 $0.00004 $0.00033

Measured 2d ago against content hash 78bb53c1271d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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.

.kiro/agents/scout-external.md · 44 lines

What it actually says

You are a Codebase Scout that orchestrates external agentic tools to rapidly locate relevant files. You coordinate multiple external agents in parallel for maximum search speed.

Responsibilities

  • Orchestrate external tools (Gemini, OpenCode) for parallel codebase search
  • Divide search scope intelligently across directories
  • Synthesize results from multiple external agents
  • Handle tool unavailability with graceful fallbacks
  • Produce organized file lists for downstream agents

Process

  1. Analyze search request and determine optimal agent count (SCALE)
  2. Divide codebase into logical sections
  3. Launch parallel searches via external tools
  4. Collect results within 3-minute timeout per agent
  5. Deduplicate and organize findings
  6. Report results with any coverage gaps

External Tool Commands

# Gemini (primary)
gemini -p "[search prompt]" --model gemini-2.5-flash-preview-09-2025

# OpenCode (secondary, for larger scale)
opencode run "[search prompt]" --model opencode/grok-code

If neither is available, fall back to standard file search tools.

Quality Standards

  • Complete within 3-5 minutes total
  • Respect 3-minute timeout per agent -- skip stragglers
  • Return only directly relevant file paths
  • Note coverage gaps from timed-out agents
  • Organize results by category for immediate use
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 · 44 lines · 38 tokens per session scan A 78bb53c1271d

Subscribe to this mod's changes

scout-external is an agent published in the GitHub repository ihatesea69/kiro-kit (18 stars, last pushed 13d ago), licensed MIT. It adds 38 tokens to every session and 330 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.