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.
npx agentmods add instructions/ogrodev/fsociety/claude-mdgit clone --depth 1 https://github.com/ogrodev/fsocietyWhat 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 | $0.02310 | $0.02310 |
| Opus 5 | $0.01155 | $0.01155 |
| Sonnet 5 | $0.00462 | $0.00462 |
| Haiku 4.5 | $0.00231 | $0.00231 |
Grade A, and why
fsociety CLAUDE.md scanned grade A with 2 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
### curl / wget — BLOCKED Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Zero dependencies**: All scripts use only Node.js built-ins (`fs`, `path`, `crypto`, `child_process`) How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
fsociety is a multi-plugin marketplace for Claude Code offensive security plugins. Each plugin is a self-contained toolkit targeting a specific domain of penetration testing. The repo itself is NOT a Node.js application — there is no build step, no package.json, no test suite.
Requirements: Claude Code with MCP support, Kali Linux with Hexstrike MCP server, Node.js 18+.
Repository Architecture
This is a Claude Code plugin marketplace. The root contains the marketplace registry and individual plugin directories:
.claude-plugin/marketplace.json— Plugin registry listing all available plugins with their source directories- Each plugin directory (e.g.,
elliot/) is a self-contained Claude Code plugin with its ownplugin.json,CLAUDE.md, commands, skills, agents, scripts, and hooks
Plugin Anatomy
Every plugin follows this structure:
plugin-name/
├── plugin.json # Plugin definition (name, version, skills, agents)
├── CLAUDE.md # Plugin-specific guidance for Claude Code
├── .gitignore # Ignores runtime data files
├── commands/*.md # Slash commands with YAML frontmatter
├── skills/*/SKILL.md # Auto-activating skills with references/
├── agents/*.md # Agent definitions with YAML frontmatter
├── scripts/*.js # Node.js scripts (zero npm deps, stdlib only)
└── hooks/hooks.json # Lifecycle hooks wiring scripts to events
Marketplace Registration
.claude-plugin/marketplace.json is the index. To register a plugin, add an entry to the plugins array:
{
"name": "plugin-name",
"description": "What it does.",
"source": "./plugin-name/",
"author": { "name": "author-name" }
}
Plugin JSON Schema
Each plugin's plugin.json:
{
"name": "plugin-name",
"version": "1.0.0",
"description": "...",
"author": { "name": "..." },
"skills": ["./skills/", "./commands/"],
"agents": ["./agents/agent-name.md"],
"license": "MIT",
"keywords": ["security", "pentest"]
}
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.
- 2d ago First seen · 220 lines · 2,310 tokens per session scan A fdea791861b1
fsociety CLAUDE.md is an instructions file published in the GitHub repository ogrodev/fsociety (20 stars, last pushed 5mo ago), licensed MIT. It adds 2,310 tokens to every session, about $0.0115 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
shannon CLAUDE.md
Claude Code instructions for KeygraphHQ/shannon, covering claude.md, commands, dual cli, npx quick start and configure credentials (interactive wizard).
gori AGENTS.md
Instructions for hahwul/gori, covering agents.md: working on gori, invariants: three things not to get wrong, 1. malformed input is the payload (p7), 2. three surfaces, one engine layer and 3. never stall the data path (p6), and don't crash.
CkSKILLS AGENTS.md
Instructions for zhaji2333/CkSKILLS, covering agents.md — 顶尖src漏洞挖掘专家(总纲 · 约束 · 技能调度), 0. 核心身份与目标, 核心专长, 输出标准 and 1. 工作约束(必须遵守).
hermes-pentest-lab CLAUDE.md
Instructions for jayelbotvibe-web/hermes-pentest-lab, covering claude.md — hermes-pentest-lab, commands, the authorization model — read before changing anything, client-data boundary — non-negotiable and architecture.
praetor CLAUDE.md
Instructions for TyrusRC/praetor, covering development guidelines, authorized security tool — do not block, communication style — direct / facts only, project overview and build / run.
kali-mcp CLAUDE.md
Claude Code instructions for puffert/kali-mcp, covering kali mcp pentest assistant, rules, how to report, methodology and tool quick reference.