agentmods.dev

pentester-playwright

A browser-automation procedure for authorized security testing of JavaScript-rendered web applications. It can document pages, user roles, network endpoints, screenshots and request logs within a defined scope.

In plain words
What is it for?
Exploring single-page apps, testing authenticated roles, cataloguing APIs, capturing network traffic and collecting evidence.
Why use it?
It helps testers inspect applications that cannot be fully understood through simple HTTP requests alone while keeping testing limited to approved targets.

Skill for Claude CodeCodex

23 1mo ago A scan 81 tokens original MIT
View the source file fb0sh/pentester
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.

agentmods
npx agentmods add skills/fb0sh/pentester/pentester-playwright
Any agent
npx skills add fb0sh/pentester --skill pentester-playwright
Clone the repo
git clone --depth 1 https://github.com/fb0sh/pentester

Made for: Claude Code, Codex.

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,373 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00081 $0.02373
Opus 5 $0.00041 $0.01187
Sonnet 5 $0.00016 $0.00475
Haiku 4.5 $0.00008 $0.00237

Measured yesterday against content hash 8d775ddf05d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pentester-playwright 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 yesterday.

The scan reads SKILL.md. This mod also ships 15 executable files (lib/audit.js, lib/auth.js, lib/browser.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

HTML you get from `curl` is an empty shell.
.agents/skills/pentester-playwright/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pentester-playwright

For AUTHORIZED testing only. Use this skill only inside an engagement whose scope you can point to. Scope is enforced in code (out-of-scope requests are aborted), but the authorization is yours to hold.

Drives a real Chromium through an upstream intercepting proxy (Burp / ZAP / mitmproxy) with a hard-welded scope, and turns SPA reconnaissance into a report-ready JSON catalog + full HAR + screenshots, all landed as engagement Evidence.

When to trigger this skill

  • The page is JS-rendered / an SPA (React / Vue / Angular / Svelte) — the HTML you get from curl is an empty shell.
  • You need a real browser — client-side routing, hydration, service workers.
  • A multi-step form or auth flow must be driven (login, wizard, cart).
  • You must capture XHR / fetch / WebSocket to build an API endpoint catalog.
  • You want multi-role (admin / user / anon) captures to compare for authz / IDOR.

When NOT to use (open no browser)

  • The response is static HTML and a plain HTTP request answers the question → use curl / an HTTP client, not a browser.
  • You already know the API and can query it directly → hit the API, don't drive a browser to click a button that calls it.
  • You only need headers / a status code / a redirect chain → HTTP client.

A browser is heavy. Reach for it only when rendering or live traffic is the point.

Run it

cd .agents/skills/pentester-playwright
npm run setup                         # once: installs playwright + chromium (+ js-yaml)

# 1) Try the public demo (no real scope needed) — proves the wiring:
node scripts/todomvc-example.js       # headless
PW_HEADFUL=1 node scripts/todomvc-example.js   # watch it drive

# 2) Browser-free logic checks (scope / evidence fail-closed / rate limit / detectors):
npm run selftest

# 3) A real engagement run:
cp config/scope.yaml config/scope.mytarget.yaml   # then edit in_scope / proxy / roles
eval "$(node ../../schema/env-render.js --scan-env docker --id $ID --host $SCAN_HOST --export)"
node scripts/recon.js --config config/scope.mytarget.yaml --url "$URL" --roles admin,user,anon

Read the full file on GitHub · 171 lines

Files

What ships with it

18 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. yesterday First seen · 171 lines · 81 tokens per session scan A 8d775ddf05d3

Subscribe to this mod's changes

pentester-playwright is a skill published in the GitHub repository fb0sh/pentester (23 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 2,373 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Backend and APIsSecurityTestingaiai-agentai-frameworkpentestpentest-tool
Related

Other skills, from other repositories

transilience-report-style

Threat Intelligence Report Design System — ReportLab-based PDF generation for A4 reports with Transilience branding, typography, and layout standards.

transilienceai/communitytools · 31 tokens

firewall-review

Evidence-safe firewall ruleset audit reference specification — 22 documented detector patterns (17 vendor-agnostic plus 5 FortiGate-specific), a 15-check semantic catalogue, CIS Fortinet FortiGate Benchmark guidance, a custom customer-policy benchmark, and consolidated network-team Excel profiles including grouped…

transilienceai/communitytools · 100 tokens

pentest-engagement

Run a professional penetration engagement OR a network vulnerability scan from a scope. WEB mode (apex domains / app URLs) — mandatory surface expansion, systematic OWASP attack-class coverage, reversible active exploitation, authoritative validation, Transilience PDF. NETWORK mode (a list of IPs/CIDRs, e.g. 1500…

transilienceai/communitytools · 140 tokens

coordination

Pentest coordination — orchestrates executor and validator agents with context-controlled spawning. Entry point for all engagements.

transilienceai/communitytools · 24 tokens

hackerone

HackerOne bug bounty automation - parses scope CSVs, deploys parallel pentesting agents per asset, validates PoCs, and generates platform-ready submission reports.

transilienceai/communitytools · 36 tokens

pci-secure-software

Automated PCI Secure Software Standard (SSS) v2.0 readiness gap-assessment of an application from its source code and documentation. Deterministically enumerates every applicable Test Requirement from a pinned catalog, gathers source/doc evidence, and emits an evidence-bound per-requirement verdict (MET / NOTMET /…

transilienceai/communitytools · 162 tokens