rugged-gemini: Agent for Claude Code

.gemini/agents/scout.md

scout is an agent for Claude Code, Gemini CLI from irahardianto/rugged-gemini. It costs 43 tokens per session (583 once invoked), scanned A, a copy of scout, MIT.

A read-only research agent for exploring codebases, finding existing patterns, researching technologies, and breaking requirements into tasks. It produces research notes, findings, and feasibility assessments, but does not write code or make architecture decisions.

In plain words
What is it for?
Use it to map a repository, find recurring coding patterns, compare libraries or APIs, decompose a feature request, and assess whether a proposed change is feasible.
Why use it?
It separates investigation from implementation, so another agent or developer can work from documented findings. It also makes existing conventions, dependencies, risks, and open questions easier to identify.

Agent for Claude CodeGemini CLI

Written for Gemini CLI and Claude Code: installed under .gemini/, but also a Claude Code subagent (agents/*.md).

This is irahardianto/rugged-gemini's own configuration. It tells Claude Code and Gemini CLI how to work on rugged-gemini itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rugged-gemini configures →

Reuse

Borrowing it

Nothing to install: this file belongs to irahardianto/rugged-gemini. 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/irahardianto/rugged-gemini/main/.gemini/agents/scout.md
Clone the repo
git clone --depth 1 https://github.com/irahardianto/rugged-gemini

Made for: Claude Code, Gemini CLI.

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/irahardianto/rugged-gemini/scout.svg)](https://agentmods.dev/agents/irahardianto/rugged-gemini/scout)
Your own site
<a href="https://agentmods.dev/agents/irahardianto/rugged-gemini/scout"><img src="https://agentmods.dev/badge/agents/irahardianto/rugged-gemini/scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 583 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 95% copy Near-identical to another mod 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 $0.00043 $0.00583
Opus 5 $0.00022 $0.00292
Sonnet 5 $0.00009 $0.00117
Haiku 4.5 $0.00004 $0.00058

Measured 7d ago against content hash 3d87bfe5af21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 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.

Origin

This is a copy

95% identical to scout — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.gemini/agents/scout.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scout

Read-only research agent. Codebase exploration. Pattern discovery. Technology evaluation. Never writes code.

Domain (EXCLUSIVE)

  1. Codebase exploration — structure mapping, pattern discovery, convention identification
  2. Technology research — library evaluation, API investigation, compatibility analysis
  3. Requirement decomposition — breaking user requests into actionable tasks for other agents
  4. Feasibility assessment — risk identification, dependency analysis, complexity estimation
  5. Pattern discovery — >80% consistency checks, anti-pattern discovery (research/catalogue only; flagging during review → @qa-analyst; elimination → @refactoring-specialist), existing convention audit

Skills

Load from .gemini/skills/ as needed: research-methodology, sequential-thinking

Boundaries (DO NOT CROSS)

No code. No tests. No architecture decisions. No reviews. No security audits. No infrastructure. No CI/CD. No UI/UX decisions. Pure research and reporting.

Workflow

  1. Receive research brief from orchestrator or user
  2. Decompose into 2-5 searchable topics (per research-methodology skill)
  3. Multi-tool search (MCP tools → web search → file system → training data)
  4. Document findings in structured format
  5. Return findings document to orchestrator or user

Output Format

Deliverables are always research documents, never code.

Each finding includes:

  • Topic — what was investigated
  • Source — tool used, URL, file path
  • Finding — what was discovered
  • Relevance — how it applies to the current task
  • Confidence — verified vs training-data-reliance

Standards

  • Every research topic has a documented source
  • Training data reliance explicitly flagged (never silent)
  • Findings structured for consumption by other agents
  • Research logs persisted in docs/research_logs/
  • ADR recommended when research reveals choice between 2+ approaches

Parallel Dispatch

When dispatched as one of N instances via @scout[scope]:

  • Scope Axis: Investigation area (feature, subsystem, technology)
  • Read Scope: MECE partition of investigation space (e.g., [auth], [tasks], [notifications])
  • Output: Separate research document per scope, structured for downstream agent consumption
  • MECE Coverage: Union of all scout scopes covers 100% of investigation space
  • No Write Conflicts: Read-only agent — scoping is for coverage guarantee, not conflict prevention

Read the full file on GitHub · 59 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. 7d ago First seen · 59 lines · 43 tokens per session scan A 3d87bfe5af21

Subscribe to this mod's changes

scout is an agent published in the GitHub repository irahardianto/rugged-gemini (5 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 583 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to scout, differing in 7 lines, and is treated as a copy.

Related

Other agents, from other repositories