/ty-hunt
Unified multi-source leak hunt — runs applicable sources based on current profile
$ npx -y skills add ogrodev/fsociety --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/ty-hunt
Context preview
What this command does when you run it.
Unified multi-source leak hunt — runs applicable sources based on current profile
Command definition
ty-hunt.mddescription: Unified multi-source leak hunt — runs applicable sources based on current profile
allowed-tools: Bash, Read, Write, Glob, Grep, Task
argument-hint: <query>
> **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 "${CLAUDE_PLUGIN_ROOT}/scripts/session-state.js" showCheck if this target was already hunted:
node "${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
Present results as:
===========================================
HUNT RESULTS: $ARGUMENTS
Profile: <current profile>
===========================================
Sources discovered: N
[SOURCE-ID] TYPE/SERVICE — Description
URL: ...
Access: open|login|purchase|exploit
Data types: email, password, ...
Estimated records: N
→ Recommended: /ty-acquire or /ty-handoff
===========================================
Next steps:
- /ty-classify <id> — Classify sources
- /ty-acquire <id> — Dump accessible sources
- /ty-handoff <id> — Hand off to elliot
===========================================Update metrics:
node "${CLAUDE_PLUGIN_ROOT}/scripts/session-state.js" metric total_hunts +1
node "${CLAUDE_PLUGIN_ROOT}/scripts/session-state.js" metric sources_discovered +1Read more
description: Unified multi-source leak hunt — runs applicable sources based on current profile allowed-tools: Bash, Read, Write, Glob, Grep, Task argument-hint: <query>
> **Storage Policy**: ALL output files MUST be saved in the project directory. NEVER write to `/tmp/` or any system temporary directory.
Unified Leak Hunt
You are a Tyrell leak hunter. Execute a multi-source search across all sources allowed by the current OPSEC profile.
**Query:** `$ARGUMENTS`
---
Phase 1: Check Profile & State
node "${CLAUDE_PLUGIN_ROOT}/scripts/hunt-profile.js" get
node "${CLAUDE_PLUGIN_ROOT}/scripts/session-state.js" showCheck 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
Present results as:
===========================================
HUNT RESULTS: $ARGUMENTS
Profile: <current profile>
===========================================
Sources discovered: N
[SOURCE-ID] TYPE/SERVICE — Description
URL: ...
Access: open|login|purchase|exploit
Data types: email, password, ...
Estimated records: N
→ Recommended: /ty-acquire or /ty-handoff
===========================================
Next steps:
- /ty-classify <id> — Classify sources
- /ty-acquire <id> — Dump accessible sources
- /ty-handoff <id> — Hand off to elliot
===========================================Update metrics:
node "${CLAUDE_PLUGIN_ROOT}/scripts/session-state.js" metric total_hunts +1
node "${CLAUDE_PLUGIN_ROOT}/scripts/session-state.js" metric sources_discovered +1Multi-plugin marketplace for Claude Code offensive security plugins
Repo: ogrodev/fsociety
Other commands on fsociety.
- /apiscan
API security audit — REST, GraphQL, JWT analysis, parameter discovery
Open command - /archives
Archive or list previous engagement snapshots
Open command - /bruteforce
Password brute force and hash cracking against target services
Open command - /campaign
Resume or execute an attack campaign with progress tracking
Open command - /dashboard
Show running scans, system health, and engagement status
Open command - /debrief
Post-engagement lessons learned analysis and debrief report
Open command

