scout

A read-only repository scout that answers one narrowly defined question using file, symbol, or command evidence.

In plain words
What is it for?
Use it to locate files, check established coding patterns, or gather evidence before planning or implementing a change.
Why use it?
It helps agents find reliable facts without changing code or getting distracted by unrelated parts of the repository.

Agent

Part of the genie plugin — 22 skills, 11 commands, 7 agents, 1 hook shipped together

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/automagik-dev/genie/scout
Clone the repo
git clone --depth 1 https://github.com/automagik-dev/genie

Or install genie, the plugin that ships this one along with the rest of its 22 skills, 11 commands, 7 agents, 1 hook.

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 187 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 $0.00032 $0.00187
Opus 5 $0.00016 $0.00093
Sonnet 5 $0.00006 $0.00037
Haiku 4.5 $0.00003 $0.00019

Measured 3d ago against content hash e48a678bdd9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

plugins/genie/agents/scout.md · 23 lines

What it actually says

Scout

Role charter

Answer one bounded repository question with direct file, symbol, or command evidence. Search narrowly, distinguish observed facts from inference, and return a concise map for the requesting agent. Remain read-only: do not implement, fix, review, stage, commit, or mark tasks done.

Context diet

The brief must contain the exact question, search boundary, relevant repository or subsystem, desired evidence format, and a stop condition for insufficient evidence.

The brief must not contain implementation permission, a full WISH when one section suffices, unrelated history, broad "understand everything" requests, secrets, or raw transcripts from other agents.

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. 3d ago First seen · 23 lines · 32 tokens per session scan A e48a678bdd9d

Subscribe to this mod's changes

scout is an agent published in the GitHub repository automagik-dev/genie (334 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 187 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.

Related

Other agents, from other repositories

ralph-loop-runner

Use this agent when you need to execute a Ralph orchestration loop end-to-end and verify its completion. This includes testing prompts against the Ralph system, validating that orchestration completes successfully, and capturing both results and any runtime issues. Examples:\n\n \nContext: User wants to test if a…

mikeyobrien/ralph-orchestrator · 286 tokens

mdm

Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for mobile device management platforms (Microsoft Intune, Jamf Pro, VMware/Omnissa Workspace ONE, Ivanti EPMM/MobileIron).

ASCIT31/Dark-Moon · 46 tokens

context-isolator

Runs data-heavy read-and-summarize operations in an isolated context window to prevent bloating the main conversation. Use when a task requires reading potentially large inputs (long commit logs, deep filesystem scans, aggregated logs, many-file searches) but only a small structured summary needs to flow back to main…

dork-labs/dorkos · 76 tokens

adr-critic

Lightweight ADR reviewer that checks decision rationale, alternatives fairness, consequences completeness, and clarity. Reads Author's Notes as prioritized attack vectors. Use when the ADR review operation needs a quick quality check.

joaquimscosta/arkhe-claude-plugins · 43 tokens

foundation_architecture

Status: Draft Purpose: Define the minimal viable system architecture and cross‑reference OpenHands SDK capabilities with Tier 0 questions to guide incremental development. Related: ./openhandsinsightsandprioritization.md, ./implementationquestions.md, ./design/multiagentorchestration.md.

kivo360/OmoiOS · 0 tokens

firmware

Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for embedded / IoT firmware and devices (firmware image extraction, hardcoded credentials & secrets, backdoors, embedded web/CGI/LuCI interfaces, insecure network services, outdated components — OpenWrt/BusyBox/Dropbear/uhttpd class devices).

ASCIT31/Dark-Moon · 70 tokens