agentmods.dev

ty-hunt

ty-hunt is a command for coding agents from ogrodev/fsociety. It costs 13 tokens per session (774 once invoked), scanned A, original, MIT.

Unified multi-source leak hunt — runs applicable sources based on current profile.

Command

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

not rated 20 5mo ago A scan 13 tokens MIT
View the source file ogrodev/fsociety
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/ogrodev/fsociety/ty-hunt
Clone the repo
git clone --depth 1 https://github.com/ogrodev/fsociety

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 ty-hunt

README.md
[![agentmods](https://agentmods.dev/badge/commands/ogrodev/fsociety/ty-hunt.svg)](https://agentmods.dev/commands/ogrodev/fsociety/ty-hunt)
Your own site
<a href="https://agentmods.dev/commands/ogrodev/fsociety/ty-hunt"><img src="https://agentmods.dev/badge/commands/ogrodev/fsociety/ty-hunt.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 774 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin unknown 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 $0.00013 $0.00774
Opus 5 $0.00006 $0.00387
Sonnet 5 $0.00003 $0.00155
Haiku 4.5 $0.00001 $0.00077

Measured today against content hash e04e505fae25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ty-hunt 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 today.

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.

2. **Shodan** — Use `shodan` CLI or Shodan API via curl
tyrell/commands/ty-hunt.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Storage Policy: ALL output files MUST be saved in the project directory. NEVER write to /tmp/ or any system temporary directory.

Unified Leak Hunt

You are a Tyrell leak hunter. Execute a multi-source search across all sources allowed by the current OPSEC profile.

Query: $ARGUMENTS

Phase 1: Check Profile & State

node "${CLAUDE_PLUGIN_ROOT}/scripts/hunt-profile.js" get
node "${CLAUDE_PLUGIN_ROOT}/scripts/session-state.js" show

Check if this target was already hunted:

node "${CLAUDE_PLUGIN_ROOT}/scripts/source-tracker.js" search "$ARGUMENTS"

Phase 2: Generate Queries

Run these in parallel based on the profile:

Surface sources (all profiles)

node "${CLAUDE_PLUGIN_ROOT}/scripts/hunt-engine.js" dork "$ARGUMENTS"
node "${CLAUDE_PLUGIN_ROOT}/scripts/hunt-engine.js" shodan "$ARGUMENTS" --service all
node "${CLAUDE_PLUGIN_ROOT}/scripts/hunt-engine.js" github "$ARGUMENTS"

Deep sources (deep/dark/ghost profiles only)

node "${CLAUDE_PLUGIN_ROOT}/scripts/hunt-engine.js" forum "$ARGUMENTS"

Phase 3: Execute Searches

For each generated query set, execute the searches using available MCP tools or CLI:

  1. Google Dorks — Use web search tools with the generated dork queries
  2. Shodan — Use shodan CLI or Shodan API via curl
  3. GitHub — Use gitleaks/trufflehog or GitHub search API
  4. Forums — Use web search or direct forum access (deep+ profile)

Apply timing delays based on profile:

  • surface: immediate
  • deep: 1-5s between requests
  • dark: 3-10s between requests
  • ghost: 10-60s random delays

Phase 4: Log Discovered Sources

For each discovered leak source:

node "${CLAUDE_PLUGIN_ROOT}/scripts/source-tracker.js" add <source_type> "<url>" "<description>" --service <svc> --access-method <method> --data-types <types> --records <n>

Source types: exposed-db, forum, paste, darkweb, telegram, github

Phase 5: Triage & Report

Read the full file on GitHub · 110 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. today First seen · 110 lines · 13 tokens per session scan A e04e505fae25

Subscribe to this mod's changes

ty-hunt is a command published in the GitHub repository ogrodev/fsociety (20 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 774 once invoked, about $0.0001 per session on Opus 5. 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 2026-09-03.

Securityclaude-codeclaude-code-pluginoffensive-securitypentesting
Related

Other commands, from other repositories

pentest

Activate pentest mode — displays ASCII art, configures session isolation, collects engagement scope, then OWNS the engagement: pre-flight, recon, planning (via the pentester-orchestrator planner), executor dispatch, a time-budget quota loop, aggregation, and report generation.

Stickman230/claude-pentest · 58 tokens

pentest-attacks

Define the attack profile for an engagement — select which attack categories and skills to use. Saves to .pentest-attacks.json. If run before /pentest:pentest, the orchestrator will respect the selection. If run standalone, does not launch a pentest.

Stickman230/claude-pentest · 60 tokens

pentest-kali

Connect to a Metasploit-Kali Server (MKS) REST API — verifies connectivity, discovers available Kali tools, and configures agents to prefer MKS endpoints over local Bash equivalents.

Stickman230/claude-pentest · 43 tokens

pentest-scope

Define or update engagement scope — saves scope to disk without launching a pentest. Can be run before or during an engagement. If a pentest is active and the target changes drastically, warns the operator and suggests a new engagement.

Stickman230/claude-pentest · 51 tokens

pentest-exit

Close pentest session — summarizes findings, ensures outputs are saved, lifts isolation, and prompts for /clear.

Stickman230/claude-pentest · 26 tokens

bb-ad

Active Directory enumeration and attack techniques. Includes LDAP enumeration, Kerberos attacks (Kerberoasting, AS-REP Roasting), SMB attacks, and domain privilege escalation. Use this when targeting Windows domain environments.

allsmog/blackbox-claude-plugin · 44 tokens