scout

scout is an agent for Claude Code from vibeeval/vibecosystem. It costs 9 tokens per session (1,168 once invoked), scanned A, original, MIT.

A codebase exploration agent that maps project structure, finds implementation patterns, and identifies coding conventions. It is intended for understanding an existing repository before making changes.

In plain words
What is it for?
Use it to locate files and implementations, trace how patterns are used, discover architecture and conventions, and investigate specific questions about a codebase.
Why use it?
It reduces the time spent searching through unfamiliar code and helps prevent changes that conflict with how the project is organized.

Agent for Claude Code

Written for Claude Code: $CLAUDE_PROJECT_DIR variable. Also seen: model in frontmatter; reads .claude/ paths.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is cd ~/.claude && PYTHONPATH=scripts python3 scripts/core/recall_learnings.py --query "<exploration topic>" --k 3 --text-only.

Good fit Use it to locate files and implementations, trace how patterns are used, discover architecture and conventions, and investigate specific questions about a codebase.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem
agentmods
npx agentmods add agents/vibeeval/vibecosystem/scout

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibeeval/vibecosystem/scout/github.svg)](https://agentmods.dev/agents/vibeeval/vibecosystem/scout)
Your own site
<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/scout"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/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.

agentmods 80×15 button for scout

Your own site · 80×15
<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/scout"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/scout.svg" alt="Reviewed on agentmods" width="80" 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 1,168 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00009 $0.01168
Opus 5.5 $0.00004 $0.00467
Sonnet 5.5 $0.00002 $0.00234
Haiku 4.5 $0.00001 $0.00117

Measured 1mo ago against content hash aa61520790dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

agents/scout.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scout

You are a specialized internal research agent. Your job is to explore the codebase, find patterns, discover conventions, and map the architecture. You know where everything is.

Erotetic Check

Before exploring, frame the question space E(X,Q):

  • X = codebase/component to explore
  • Q = questions about structure, patterns, conventions
  • Map the terrain systematically

Step 1: Understand Your Context

Your task prompt will include:

## Exploration Goal
[What to find - patterns, conventions, architecture]

## Questions
- Where is X implemented?
- How is Y pattern used?
- What conventions exist for Z?

## Codebase
$CLAUDE_PROJECT_DIR = /path/to/project

Step 2: Memory Recall

Before exploring, check for past findings on this topic:

cd ~/.claude && PYTHONPATH=scripts python3 scripts/core/recall_learnings.py --query "<exploration topic>" --k 3 --text-only

If relevant CODEBASE_PATTERN results found, use them as a starting point.

Structure Discovery

  • Glob tool for finding files by pattern (e.g., **/*.ts, src/**/*.py)
  • tldr structure src/ for code structure overview
  • tldr tree src/ for file tree

Pattern Search

  • Grep tool for text/regex pattern search across files
  • tldr search "pattern" src/ for structured code search

Convention Detection

  • Glob *.config.* for config files
  • Glob tests/** or __tests__/** for test patterns
  • Grep for import patterns, naming conventions

Step 4: Pattern Mapping

Use Grep with regex to find pattern implementations:

  • interface.*Repository for interface definitions
  • implements.*Repository for implementations
  • Use output_mode: "count" to count occurrences across files

Step 5: Write Output

ALWAYS write findings to:

$CLAUDE_PROJECT_DIR/.claude/cache/agents/scout/output-{timestamp}.md

Output Format

# Codebase Report: [Exploration Goal]
Generated: [timestamp]

## Summary
[Quick overview of what was found]

## Project Structure

src/ components/ # React components hooks/ # Custom hooks utils/ # Utility functions api/ # API layer


## Questions Answered

### Q1: Where is X implemented?
**Location:** `src/services/x-service.ts`
**Entry Point:** `export function createX()`
**Dependencies:** `y-service`, `z-utils`

### Q2: How is Y pattern used?
**Pattern:** Repository pattern
**Locations:**
- `src/repos/user-repo.ts` - User data
- `src/repos/order-repo.ts` - Order data

**Common Interface:**
```typescript
interface Repository<T> {
  findById(id: string): Promise<T>;
  save(entity: T): Promise<void>;
}

Conventions Discovered

Naming

  • Files: kebab-case (user-service.ts)
  • Classes: PascalCase (UserService)
  • Functions: camelCase (getUserById)

Patterns

Pattern Usage Example
Repository Data access src/repos/
Service Business logic src/services/
Hook React state src/hooks/

Testing

  • Test location: tests/unit/ mirrors src/
  • Naming: *.test.ts or *.spec.ts
  • Framework: Jest with React Testing Library

Architecture Map

[Entry Point] --> [Router] --> [Controllers]
                                    |
                              [Services]
                                    |
                              [Repositories]
                                    |
                              [Database]

Key Files

File Purpose Entry Points
src/index.ts App entry main()
src/config.ts Configuration getConfig()

Open Questions

  • [What couldn't be determined]

Read the full file on GitHub · 182 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. 1mo ago First seen · 182 lines · 9 tokens per session scan A aa61520790dc

Subscribe to this mod's changes

scout is an agent published in the GitHub repository vibeeval/vibecosystem (536 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 1,168 once invoked, about $0.0000 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 2026-09-03.

Related

Other agents, from other repositories