What is claude-skills-for-bug-bounty?

A guide to building custom skills for the Claude Code command-line tool, using reusable instructions, scripts, and fallback plans. It explains how these skills provide context and task guidance rather than retraining the model.

Use it to design, implement, and refine TypeScript-based CLI skills for authorised bug bounty work and repeatable security tasks.

It helps organise security-testing workflows and reduce inconsistent results when connecting Claude Code with tools such as Burp, Nuclei, or other scanners.

claude-skills-for-bug-bounty — Skill for Claude Code and Codex by Shul

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/ShulkwiSEC/bb-huge

agentmods

npx agentmods add skills/shulkwisec/bb-huge/claude-skills-for-bug-bounty

Made for: Claude Code, Codex.

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/skills/shulkwisec/bb-huge/claude-skills-for-bug-bounty/github.svg)](https://agentmods.dev/skills/shulkwisec/bb-huge/claude-skills-for-bug-bounty)

Your own site

<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/claude-skills-for-bug-bounty"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/claude-skills-for-bug-bounty/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/skills/shulkwisec/bb-huge/claude-skills-for-bug-bounty"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/claude-skills-for-bug-bounty.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,799 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 3 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	$0.00054	$0.02799
Opus 5	$0.00027	$0.01399
Sonnet 5	$0.00011	$0.00560
Haiku 4.5	$0.00005	$0.00280

Measured 8d ago against content hash 4867d7c1ebfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

claude-skills-for-bug-bounty scanned grade B with 3 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 8d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

const response = await fetch("http://127.0.0.1:8080/api/v1/intercept", { method: "POST",

Makes network callslowCapability

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

// Use curl with proxy settings

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

import { execSync } from "child_process";

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

claude-skills-for-bug-bounty — 100% identical, 0 lines differ

skills/curated/claude-skills-for-bug-bounty/SKILL.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Building Claude Skills for Bug Bounty Hunting

When to Use

When setting up Claude Code CLI for the first time in a bug bounty workflow.
When creating custom skills to integrate external tools (Kaido, Burp, Nuclei) with Claude.
When defining skill files that Claude will consume to perform autonomous security testing.
When optimizing existing skill definitions for better agent performance and fewer hallucinations.

Prerequisites

Claude Code CLI installed and authenticated (claude command available in terminal)
Node.js / TypeScript toolchain installed (Node 18+, npx tsx)
Basic familiarity with Claude's .claudemd file format and skill directory structure
Target scope defined by bug bounty program (HackerOne / Bugcrowd / Intigriti)

Core Concept: Skills ≠ Training

"You are not training Claude. You are giving Claude context, prompts, and skills." — Critical Thinking Podcast, Ep. 166 [09:40]

Term	Meaning
Context	Background information: target scope, program policy, authentication tokens
Prompts	Specific instructions for a task: "Find IDOR in `/api/v2/users`"
Skills	Reusable instruction sets + scripts that teach Claude how to use an external tool or execute a methodology

Skills give Claude "powers" it does not have natively — access to your VPS, private APIs, proxies, and custom tooling.

Workflow

Phase 1: Skill File Structure

Every skill lives in a directory with a SKILL.md file and optional support scripts:

skills/
└── kaido-proxy/
    ├── SKILL.md          # Instructions Claude reads
    ├── scripts/
    │   ├── intercept.ts  # TypeScript helper Claude can execute
    │   └── replay.ts     # Request replay utility
    └── references/
        └── kaido-api.md  # API documentation for Kaido endpoints

SKILL.md Anatomy:

---
name: kaido-proxy-interaction
description: >
  Intercept, modify, and replay HTTP requests through Kaido proxy.
  Use this skill when testing authenticated endpoints or fuzzing parameters.
tools: [kaido, burp-suite]
---

Read the full file on GitHub · 310 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.

8d ago First seen · 310 lines · 54 tokens per session scan B 4867d7c1ebfa

Subscribe to this mod's changes

claude-skills-for-bug-bounty is a skill published in the GitHub repository ShulkwiSEC/bb-huge (22 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 2,799 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 3 findings (sends data to an external url, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Building agents Claude Code Security agent-skills ai-agents ai-for-cybersecurity ai-hunting ai-orchestration automation bug-bounty-methodology claude-skills llm-tools methodology pair-hunting