recon-plan

recon-plan is a command for coding agents from HermeticOrmus/LibreSecOps-Claude-Code. It costs 0 tokens per session (1,329 once invoked), scanned A, original, MIT.

A command for planning reconnaissance, the process of learning what systems and entry points belong to an authorized bug bounty target. It organizes passive research, active checks, and attack-surface mapping within the program rules.

In plain words
What is it for?
Use it to plan testing of websites, APIs, mobile apps, cloud assets, domains, and IP ranges before looking for vulnerabilities.
Why use it?
It helps researchers test systematically and avoid missing assets or violating scope restrictions.

Command

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 commands/hermeticormus/libresecops-claude-code/recon-plan
Clone the repo
git clone --depth 1 https://github.com/HermeticOrmus/LibreSecOps-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 recon-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/recon-plan.svg)](https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/recon-plan)
Your own site
<a href="https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/recon-plan"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/recon-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,329 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.01329
Opus 5 $0.00000 $0.00665
Sonnet 5 $0.00000 $0.00266
Haiku 4.5 $0.00000 $0.00133

Measured 4d ago against content hash fc8b43cc4f14, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recon-plan scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "https://crt.sh/?q=%.example.com&output=json" | jq -r '.[].name_value' | sort -u
plugins/bug-bounty-methodology/commands/recon-plan.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/recon-plan

Generate a structured reconnaissance plan for an authorized bug bounty target, with passive and active recon phases, tool recommendations, and prioritized attack surface mapping.

Trigger

Use at the start of a bug bounty engagement after reviewing the program scope. Appropriate when:

  • Beginning testing on a new bug bounty program
  • Expanding recon on an existing target after initial testing
  • Planning recon for a specific asset type (API, mobile, cloud)
  • Refreshing recon on a target with updated scope

Input

  • Program name and platform: Where the program is hosted (HackerOne, Bugcrowd, etc.)
  • Scope: In-scope domains, applications, IP ranges, and mobile apps
  • Out of scope: Explicitly excluded targets and testing techniques
  • Program rules: Key rules affecting methodology (rate limits, no automated scanning, etc.)
  • Your skills and tools: What testing capabilities you have (Burp Pro, mobile testing setup, cloud experience)
  • Previous findings (optional): Known vulnerabilities or areas already tested

Process

  1. Scope analysis -- Parse the scope to identify all testable assets and explicit boundaries. Map wildcard scopes (*.example.com) vs specific assets (app.example.com).

  2. Passive reconnaissance (no direct target interaction):

    Subdomain enumeration:

    • Certificate Transparency logs: crt.sh, certspotter
    • DNS datasets: SecurityTrails, DNSDumpster, RapidDNS
    • Search engines: Google dorks (site:example.com), Bing, DuckDuckGo
    • GitHub/GitLab code search: Subdomains, API keys, internal URLs
    • Wayback Machine: Historical subdomains, removed pages, old API endpoints
    • Passive DNS: PassiveTotal, VirusTotal, AlienVault OTX

    Technology intelligence:

    • Shodan/Censys: Open ports, services, certificates, technologies
    • BuiltWith/Wappalyzer data: Technology stack information
    • Job postings: Technologies mentioned in hiring (reveals internal stack)

    Data exposure:

    • GitHub/GitLab: Code repositories, leaked credentials, configuration files
    • Pastebin/paste sites: Leaked data, credentials, configuration
    • Google dorking: Exposed files, admin panels, error messages
    • Cloud storage: S3 buckets, Azure Blobs, GCP Storage naming patterns

Read the full file on GitHub · 146 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. 4d ago First seen · 146 lines · 0 tokens per session scan A fc8b43cc4f14

Subscribe to this mod's changes

recon-plan is a command published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,329 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.