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 skills add Stickman230/claude-pentest --skill authenticatinggit clone --depth 1 https://github.com/Stickman230/claude-pentestWrote 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.
[](https://agentmods.dev/skills/stickman230/claude-pentest/authenticating)<a href="https://agentmods.dev/skills/stickman230/claude-pentest/authenticating"><img src="https://agentmods.dev/badge/skills/stickman230/claude-pentest/authenticating.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01053 |
| Opus 5 | $0.00027 | $0.00526 |
| Sonnet 5 | $0.00011 | $0.00211 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
authenticating 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authentication Testing
Automated authentication security testing: signup, login, 2FA/OTP bypass, CAPTCHA, bot detection using Playwright.
Quick Start
1. Initialize Playwright
2. Test: signup → login → 2FA → CAPTCHA → bot detection
3. Document findings with evidence
Core Workflows
Account Registration: Navigate → analyze form → generate password (PasswordGenerator) → create account → store credentials (CredentialManager)
Login Security: Test bypasses → credential validation → session tokens → fixation/hijacking
2FA/OTP Bypass: Enable 2FA → test vectors (response manipulation, direct access, parameter removal, code reuse, brute force) → extract OTP from email
CAPTCHA Assessment: Identify type → test server-side validation, token expiration, reusability → bypass vectors
Bot Detection: Stealth mode → human-like behavior (natural mouse, variable typing, random pauses) → test detection
Credential Tools
PasswordGenerator (tools/password_generator.py):
from tools.password_generator import generate_password
password = generate_password(hint_text="8-16 chars, uppercase, lowercase, numbers")
CredentialManager (tools/credential_manager.py):
from tools.credential_manager import CredentialManager
mgr = CredentialManager()
cred_id = mgr.store_credential(target="example.com", username="test", password="pass")
cred = mgr.get_credential("example.com")
See reference/PASSWORD_CREDENTIAL_MANAGEMENT.md.
Playwright Automation
REQUIRED: All browser automation via Playwright MCP.
Human-like: Natural mouse, realistic typing (80-200ms delays), random pauses (500-2000ms), smooth scrolling Evidence: Screenshots before/after, network logs, console output Stealth: Hide webdriver, add chrome object, randomize fingerprints
Testing Techniques
CAPTCHA Bypass (11 techniques - reference/CAPTCHA_BYPASS.md):
Missing server validation, empty field, reusable tokens, HTTP header manipulation, content-type conversion, request method, parameter manipulation, OCR, response interception, token expiration, session persistence
What ships with it
9 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.
- outputs/.gitkeep 0 B
- README.md 10 KB
- reference/2FA_BYPASS.md 15 KB
- reference/BOT_DETECTION.md 19 KB
- reference/CAPTCHA_BYPASS.md 12 KB
- reference/PASSWORD_CREDENTIAL_MANAGEMENT.md 17 KB
- tools/__init__.py 245 B runs code
- tools/credential_manager.py 11 KB runs code
- tools/password_generator.py 11 KB runs code
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 · 110 lines · 54 tokens per session scan A 06b27cd77377
authenticating is a skill published in the GitHub repository Stickman230/claude-pentest (99 stars, last pushed 3mo ago), licensed MIT. It adds 54 tokens to every session and 1,053 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
discovery
Web app discovery — directory/file fuzzing, vhost discovery, JavaScript endpoint extraction.
web-recon
Web application enumeration hub — directory/file fuzzing, vhost discovery, API enumeration, CMS scanning, WAF detection, auth surface mapping, cookie audit.
cookie-audit
Cookie-conditional sink discovery — bisect required cookies per sink, session-write timeline for race-condition challenges.
Web Application Enumeration
This skill should be used when the user asks about "gobuster", "directory fuzzing", "web enumeration", "nikto", "web vulnerabilities", "feroxbuster", "ffuf", "subdomain enumeration", or needs guidance on web application testing.
open-redirect
Open redirect + tabnabbing — URL filter bypass, OAuth chain extension, phishing infrastructure-free, SSRF chain.