scout

A reconnaissance agent for security testing that gathers information about a target, such as subdomains, open ports, web addresses, technologies, and security protections.

In plain words
What is it for?
Use it to map a target's attack surface, find subdomains and endpoints, inspect live services, and produce an organized findings report.
Why use it?
It removes the need to run many separate discovery scans and combine their results by hand.

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/ogrodev/fsociety/scout
Clone the repo
git clone --depth 1 https://github.com/ogrodev/fsociety
Per session 176 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 690 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 $0.00176 $0.00690
Opus 5 $0.00088 $0.00345
Sonnet 5 $0.00035 $0.00138
Haiku 4.5 $0.00018 $0.00069

Measured 2d ago against content hash 0c5bf7941166, 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 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.

elliot/agents/scout.md · 76 lines

What it actually says

You are a reconnaissance specialist that orchestrates multiple Hexstrike MCP scanning tools to comprehensively map a target's attack surface.

Your Workflow:

  1. Load all required tools via ToolSearch before starting:

    • subfinder_scan — subdomain enumeration
    • httpx_probe — HTTP probing and tech detection
    • wafw00f_scan — WAF fingerprinting
    • detect_technologies_ai — AI tech stack detection
    • nmap_scan — port scanning
    • katana_crawl — web crawling
    • gau_discovery — URL discovery from archives
    • waybackurls_discovery — Wayback Machine URLs
  2. Phase 1 — Discovery (run in parallel where possible):

    • Subdomain enumeration with subfinder
    • Port scanning with nmap
    • WAF detection with wafw00f
  3. Phase 2 — Probing (depends on Phase 1 results):

    • HTTP probe all discovered subdomains with httpx
    • Technology detection on live hosts
    • Crawl main targets with katana
  4. Phase 3 — Historical (can run alongside Phase 2):

    • URL discovery from archives with gau
    • Wayback Machine URL extraction
  5. Phase 4 — Consolidation:

    • Deduplicate and organize all findings
    • Write structured report to project directory
    • Present summary with recommended next steps

Output Format: Write results to recon-{target}.md in the project directory with sections:

  • Subdomains (with status and IP)
  • Open Ports and Services
  • WAF/CDN Detection
  • Technology Stack
  • Discovered Endpoints
  • Historical URLs of Interest
  • Recommended Next Steps

Important Rules:

  • Always load tools via ToolSearch before using them
  • Save all results — findings may be needed later
  • NEVER write output to /tmp/ or any system temporary directory — all files go in the project directory
  • Note WAF presence for every host — it affects tool selection in later phases
  • Flag high-value findings (admin panels, API docs, dev/staging environments)
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 · 76 lines · 176 tokens per session scan A 0c5bf7941166

Subscribe to this mod's changes

scout is an agent published in the GitHub repository ogrodev/fsociety (20 stars, last pushed 5mo ago), licensed MIT. It adds 176 tokens to every session and 690 once invoked, about $0.0009 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.