BugHunter

BugHunter is a skill for Claude Code from CarbeneAI/Forge. It costs 107 tokens per session (2,537 once invoked), scanned A, original, MIT.

A source-code security review process that looks for vulnerabilities, proves whether they can be exploited, fixes them, and checks the fixes. A proof of vulnerability is a reproducible demonstration that a security flaw is real.

In plain words
What is it for?
Use it to audit a repository, investigate bug-bounty targets, generate exploit demonstrations, validate security patches, and produce vulnerability reports.
Why use it?
It reduces false alarms by requiring evidence for each finding. It also connects discovery to patching and verification instead of stopping at a list of possible problems.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents; mentions Claude Code.

Good fit Use it to audit a repository, investigate bug-bounty targets, generate exploit demonstrations, validate security patches, and produce vulnerability reports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/carbeneai/forge/bughunter
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.

Any agent
npx skills add CarbeneAI/Forge --skill bughunter
Clone the repo
git clone --depth 1 https://github.com/CarbeneAI/Forge

Made for: Claude Code.

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 BugHunter

README.md
[![agentmods](https://agentmods.dev/badge/skills/carbeneai/forge/bughunter/github.svg)](https://agentmods.dev/skills/carbeneai/forge/bughunter)
Your own site
<a href="https://agentmods.dev/skills/carbeneai/forge/bughunter"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/bughunter/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.

agentmods 80×15 button for BugHunter

Your own site · 80×15
<a href="https://agentmods.dev/skills/carbeneai/forge/bughunter"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/bughunter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,537 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00107 $0.02537
Opus 5 $0.00053 $0.01269
Sonnet 5 $0.00021 $0.00507
Haiku 4.5 $0.00011 $0.00254

Measured 8d ago against content hash 77edfd1a9748, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

BugHunter 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 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.

Runs shell commandslowCapability

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

| **JavaScript/TS** | eval, innerHTML, dangerouslySetInnerHTML, child_process, prototype pollution, regex DoS |
.claude/skills/BugHunter/SKILL.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BugHunter

AI-powered source code vulnerability discovery and patching pipeline. Inspired by Praetorian Constantine -- adapted for Claude Code's native capabilities.

Philosophy

"Never report a finding you can't prove, never propose a fix you haven't tested."

Three core principles (from DARPA AIxCC):

  1. Patching matters 3x more than discovery -- validation through re-exploitation is critical
  2. Accuracy multipliers punish speculation -- independent verification at every stage
  3. Prove it or drop it -- every finding needs a proof-of-vulnerability

Pipeline Overview

1. INGEST --> 2. DETECT --> 3. VERIFY --> 4. EXPLOIT --> 5. PATCH --> 6. REPORT
     |              |            |             |            |            |
  Clone/Map     Multi-pass    Agentic       Generate     Fix + Re-    CWE/CVSS
  + Score       LLM scan      code flow     PoV code     verify       Markdown
  files         (fast+deep)   analysis                                + JSON

Quick Start

Full Scan (recommended)

"Run a BugHunter full scan on <repo-url-or-path>"
"Bug bounty scan this repository"

Quick Triage

"BugHunter quick scan on src/"
"Triage this codebase for security issues"

Targeted Scan

"BugHunter scan the auth module for injection flaws"
"Hunt for deserialization bugs in the API routes"

Patch Validation

"BugHunter validate this patch fixes the vulnerability"
"Re-exploit after patch to confirm the fix"

Workflow Routing

Workflow Trigger File
Full Scan "full scan", "bug bounty scan", "comprehensive audit" workflows/FullScan.md
Quick Scan "quick scan", "triage", "fast audit" workflows/QuickScan.md
Patch Validate "validate patch", "verify fix", "re-exploit" workflows/PatchValidate.md

Stage Details

Stage 1: Ingest

Clone (or open) the target repository and build an attack surface map.

Read the full file on GitHub · 271 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 271 lines · 107 tokens per session scan A 77edfd1a9748

Subscribe to this mod's changes

BugHunter is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 2,537 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

cybersecurity

Ultimate AI-powered cybersecurity code review skill. Performs comprehensive security audit across 8 dimensions: vulnerability detection (OWASP Top 10:2021, CWE Top 25:2024), secret scanning, dependency/supply chain analysis, IaC security, threat intelligence (malware/backdoor/C2 detection, MITRE ATT&CK mapping)…

AgriciDaniel/claude-cybersecurity · 201 tokens

appsec-code-review

../../../appsec-devsecops/appsec-code-review/SKILL.md.

jaskaranhundal/usap-skills · 0 tokens

cn-check

Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.

continuedev/continue · 49 tokens

find-security-vulnerabilities-in-code

Find security vulnerabilities in a codebase or repository with Strix — a white-box AI security review that reads your source, reasons about the actual data flow and authorization model, then exploits what it finds in a live sandbox so every reported issue has a working proof-of-concept instead of a noisy…

usestrix/strix · 129 tokens

implementing-github-advanced-security-for-code-scanning

Configure GitHub Advanced Security with CodeQL to perform automated static analysis and vulnerability detection across repositories at enterprise scale.

xalgorix/xalgorix · 34 tokens

implementing-semgrep-for-custom-sast-rules

Write custom Semgrep SAST rules in YAML to detect application-specific vulnerabilities, enforce coding standards, and integrate into CI/CD pipelines.

xalgorix/xalgorix · 37 tokens