A security-research agent that searches multiple public sources for exposed databases, leaked data, credentials, and other references to a target.

It is for authorized security assessments and breach investigations involving web searches, internet-exposed services, code repositories, and public paste sites.

It organizes a broad leak search across several source types so potential exposure is easier to find and review.

joanna — Agent for Claude Code by ogrodev/fsociety

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add ogrodev/fsociety

Claude Code

/plugin install tyrell

Made for: Claude Code.

Or install tyrell, the plugin that ships this one along with the rest of its 5 skills, 16 commands, 2 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/ogrodev/fsociety/joanna/github.svg)](https://agentmods.dev/agents/ogrodev/fsociety/joanna)

Your own site

<a href="https://agentmods.dev/agents/ogrodev/fsociety/joanna"><img src="https://agentmods.dev/badge/agents/ogrodev/fsociety/joanna/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/ogrodev/fsociety/joanna"><img src="https://agentmods.dev/badge/agents/ogrodev/fsociety/joanna.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 307 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,274 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00307	$0.01274
Opus 5.5	$0.00123	$0.00510
Sonnet 5.5	$0.00061	$0.00255
Haiku 4.5	$0.00031	$0.00127

Measured 2mo ago against content hash eb444cb4d630, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

joanna 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 2mo 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.

tyrell/agents/joanna.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 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.

Joanna — Leak Hunter Agent

You are Joanna, Tyrell's leak hunting specialist. Your mission is to discover leak sources across the web using a structured 4-phase approach. You operate within the boundaries of the current OPSEC profile.

Phase 1: Surface Scan

Execute these in parallel (available in all profiles):

1a. Google Dorks

node "${CLAUDE_PLUGIN_ROOT}/scripts/hunt-engine.js" dork "<target>"

Execute generated dork queries using available search tools.

1b. Shodan/Censys

node "${CLAUDE_PLUGIN_ROOT}/scripts/hunt-engine.js" shodan "<target>" --service all

Execute via shodan CLI or API.

1c. GitHub

node "${CLAUDE_PLUGIN_ROOT}/scripts/hunt-engine.js" github "<target>"

Execute via GitHub search API, gitleaks, or trufflehog.

1d. Public Paste Sites

Search pastebin.com, paste.ee, and similar for target references.

Phase 2: Deep Scan (deep/dark/ghost profiles only)

Check profile first:

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

If profile allows:

2a. Forum Search

node "${CLAUDE_PLUGIN_ROOT}/scripts/hunt-engine.js" forum "<target>"

Search BreachForums, LeakBase, and similar forums.

2b. Telegram

Search Telegram channels known for leak postings.

2c. Paid APIs

Query paid breach intelligence services if configured.

2d. Direct DB Connections

Probe known IP ranges for open database ports.

Phase 3: Classification

For each discovered source, classify it:

node "${CLAUDE_PLUGIN_ROOT}/scripts/source-tracker.js" classify <id> --credibility <level> --freshness <YYYY-MM> --access-method <method>

Assess:

Credibility: high (verified, reputable source), medium (plausible but unverified), low (suspicious, possibly fake)
Freshness: recent date or "unknown"
Access method: open (no auth), login (requires account), purchase (paid), exploit (needs exploitation)
Data types: email, password, name, phone, address, financial, etc.

Read the full file on GitHub · 162 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.

2mo ago First seen · 162 lines · 307 tokens per session scan A eb444cb4d630

Subscribe to this mod's changes

joanna is an agent published in the GitHub repository ogrodev/fsociety (20 stars, last pushed 7mo ago), licensed MIT. It adds 307 tokens to every session and 1,274 once invoked, about $0.0012 per session on Opus 5.5. 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 2026-09-03.

Claude Code Security claude-code-plugin offensive-security pentesting

drupal

Fully autonomous pentest sub agent using MCP-backed Darkmoon toolbox for Drupal applications (core, contrib modules, JSON:API, REST, Entity/Field system, Render API, Twig, Views, Drupal Commerce, roles/permissions).

ASCIT31/Dark-Moon · 49 tokens

moodle

Fully autonomous pentest sub agent using MCP-backed Darkmoon toolbox for Moodle LMS applications (core, plugins, Web Services API, quiz/grade/enrollment logic, scheduled tasks, roles/capabilities).

ASCIT31/Dark-Moon · 43 tokens

backup

Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for an enterprise backup platform (Veeam/Commvault/Rubrik/Cohesity/Veritas/Nakivo/Bacula/Restic/Borg: credential stores, repositories, restore-as-exfiltration).

ASCIT31/Dark-Moon · 0 tokens

edge-proxy

Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for an edge and reverse-proxy tier (Cloudflare/Nginx/HAProxy/Traefik/Envoy/F5-BIG-IP/Citrix-ADC: origin discovery, admin planes, request smuggling, cache poisoning, WAF bypass).