Agent skill

Directory Fuzzing

by NeoTheCapt in NeoTheCapt/RedteamAgent

Discover hidden directories, files, and endpoints on a web server

No licenceAuto-check: notesSecurity

Install Directory Fuzzing

skills CLI
$ npx skills add NeoTheCapt/RedteamAgent --skill directory-fuzzing -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NeoTheCapt/RedteamAgent directory-fuzzing --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NeoTheCapt/RedteamAgent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent/skills/directory-fuzzing .claude/skills/directory-fuzzing && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
directory-fuzzing
GitHub stars
142
Token cost
~737 tokens
SKILL.md length
68 words
Files
1
Skills in repo
25
Repo updated
First seen
Licence
None found

At a glance

Discover hidden directories, files, and endpoints on a web server

  • Works in 9 steps: Baseline Response → Common Path Discovery → Extension Fuzzing → …
  • Tasks that involve Fuzzing
  • SKILL.md covers When to Activate, Tools and Methodology
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Directory Fuzzing is an agent skill from NeoTheCapt/RedteamAgent. Discover hidden directories, files, and endpoints on a web server

Its SKILL.md is about 740 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Security, covering Fuzzing and Penetration testing. The repository describes itself as: An AI red-team agent for authorized labs and web app pentesting workflows. Turns Claude Code / OpenCode / Codex into a structured recon → test → exploit → report workflow, with…

When your agent uses it

  • Tasks that involve Fuzzing
  • Tasks that involve Penetration testing

Example prompts

  • “/directory-fuzzing”

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. Baseline Response
  2. Common Path Discovery
  3. Extension Fuzzing
  4. Filter Tuning
  5. Recursive Discovery
  6. Wordlist Escalation
  7. Backup and Sensitive Files
  8. Virtual Host / Subdomain
  9. Output

What it can do on your machine

Read from SKILL.md and the folder at commit 2e60476. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Directory Fuzzing loads about 737 tokens when it runs. Until then it costs about 21 tokens; SKILL.md has 68 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~21
When it runs · the whole SKILL.md, loaded when a task matches
~737

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:67
    for f in .env .git/config .htaccess web.config wp-config.php .DS_Store; do

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 68 words (~737 tokens).

“run_tool ffuf (primary), run_tool gobuster (fallback), run_tool curl (verification)”

— opening of SKILL.md by NeoTheCapt
name
directory-fuzzing
origin
RedteamOpencode

Read the full SKILL.md on GitHub

Files

Just SKILL.md in agent/skills/directory-fuzzing of NeoTheCapt/RedteamAgent.

Open the folder on GitHubat commit 2e60476

Compare with similar skills

Directory Fuzzing next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Directory Fuzzing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Directory Fuzzing this skillNeoTheCapt/RedteamAgent142—~737Automated safety check: NotesNone
Adaptive Web FuzzingEncod3d-Sec/TORCH329—~1.3kAutomated safety check: PassMIT
Audit Native Memory Safetycyberful/cyberful135—~829Automated safety check: PassAGPL-3.0
Fizzpashov/skills1.2k2 repos~11kAutomated safety check: PassMIT
Strix Code Vulnerability Scanusestrix/strix67k—~1.1kAutomated safety check: PassApache-2.0
Code Audit3stoneBrother/code-audit8921 repos~2.7kAutomated safety check: PassNone

Similar skills

  • Adaptive Web Fuzzing

    Encod3d-Sec/TORCH

    Adaptive web fuzzing for pentests, bug bounty and CTF work: picks the smallest suitable SecLists wordlist per target surface and calibrates filters against soft-404 responses.

    329 GitHub stars~1.3k tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Audit C, C++, unsafe Rust, native extensions, parsers, codecs, FFI boundaries, and systems code for memory corruption and low-level exploitation risk.

    135 GitHub stars~829 tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Fizz

    pashov/skills

    Generate Echidna/Medusa-compatible Solidity fuzz suites from Foundry or Hardhat projects.

    1.2k GitHub starsUsed in 2 repos~11k tokens
    SecurityAuto-check passed
  • Runs a Strix white-box security review that reads the source, then exploits what it finds in a sandbox so each reported issue has a proof-of-concept.

    67k GitHub stars~1.1k tokensUpdated today
    SecurityAuto-check passed
  • Code Audit

    3stoneBrother/code-audit

    Professional code security audit skill covering 55+ vulnerability types.

    892 GitHub starsUsed in 1 repo~2.7k tokens
    SecurityAuto-check passed
  • Triages findings from a Strix pentest by severity, fixes each root cause with a minimal change, and re-runs Strix to confirm the exploit no longer works.

    67k GitHub stars~1.5k tokensUpdated today
    SecurityAuto-check passed

More from NeoTheCapt/RedteamAgent

All 25 skills in this repo
  • Auth Bypass

    NeoTheCapt/RedteamAgent

    Test for authentication and authorization flaws including credential attacks, session issues, and access control bypasses

    142 GitHub stars~1.3k tokensUpdated 2 mo ago
    Auto-check passed
  • Business Logic Testing

    NeoTheCapt/RedteamAgent

    Business logic vulnerability detection — workflow bypass, price manipulation, state abuse, and application-specific flaws

    142 GitHub stars~2.8k tokensUpdated 2 mo ago
    Auto-check passed
  • Cors Testing

    NeoTheCapt/RedteamAgent

    CORS misconfiguration testing for data theft and access control bypass

    142 GitHub stars~904 tokensUpdated 2 mo ago
    Auto-check passed
  • Csrf Testing

    NeoTheCapt/RedteamAgent

    Cross-site request forgery testing for state-changing operations

    142 GitHub stars~791 tokensUpdated 2 mo ago
    Auto-check passed
  • Deserialization Testing

    NeoTheCapt/RedteamAgent

    Insecure deserialization detection and gadget chain exploitation

    142 GitHub stars~836 tokensUpdated 2 mo ago
    Auto-check passed
  • Open Redirect Testing

    NeoTheCapt/RedteamAgent

    Test for unvalidated redirects — URL parameters, login flows, OAuth callbacks that redirect to attacker-controlled domains

    142 GitHub stars~608 tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Directory Fuzzing

What does Directory Fuzzing do?

Discover hidden directories, files, and endpoints on a web server. Directory Fuzzing is an agent skill from NeoTheCapt/RedteamAgent.

When should I use Directory Fuzzing?

Directory Fuzzing fits situations like: tasks that involve Fuzzing; tasks that involve Penetration testing.

How do I install Directory Fuzzing in Claude Code?

Run `npx skills add NeoTheCapt/RedteamAgent --skill directory-fuzzing -a claude-code`. Or copy the skill folder (agent/skills/directory-fuzzing in NeoTheCapt/RedteamAgent) into .claude/skills/directory-fuzzing in your project. Claude Code loads it when a task matches its description.

How do I install Directory Fuzzing in Codex?

Run `npx skills add NeoTheCapt/RedteamAgent --skill directory-fuzzing -a codex`. Or copy the skill folder (agent/skills/directory-fuzzing in NeoTheCapt/RedteamAgent) into .agents/skills/directory-fuzzing in your project. Codex loads it when a task matches its description.

Can I use Directory Fuzzing in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NeoTheCapt/RedteamAgent --skill directory-fuzzing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/directory-fuzzing, .gemini/skills/directory-fuzzing, .github/skills/directory-fuzzing and .opencode/skills/directory-fuzzing in your project.

What does Directory Fuzzing need to run?

SKILL.md names no scripts, command-line tools or credentials: Directory Fuzzing is instructions for the agent only.

Does Directory Fuzzing access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Directory Fuzzing safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Directory Fuzzing use?

No licence was found for Directory Fuzzing or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Directory Fuzzing use?

About 737 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Directory Fuzzing?

Skills that share tags, products or a category with Directory Fuzzing: Adaptive Web Fuzzing (Encod3d-Sec/TORCH, 329 stars), Audit Native Memory Safety (cyberful/cyberful, 135 stars), Fizz (pashov/skills, 1.2k stars) and Strix Code Vulnerability Scan (usestrix/strix, 67k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Directory Fuzzing?

NeoTheCapt (a GitHub user) maintains it in NeoTheCapt/RedteamAgent, which has 142 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on August 2, 2026.

Source: NeoTheCapt/RedteamAgent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.