pentester

pentester is an agent for Claude Code from gonzalezpazmonica/pm-workspace. It costs 76 tokens per session (1,170 once invoked), scanned A, original, MIT.

An ethical penetration-testing agent for running controlled security tests against live systems. Its five-stage process maps the attack surface, searches for weaknesses, verifies exploits, and writes reports.

In plain words
What is it for?
Use it to test development, staging, or authorized production systems. It can inspect source code, scan services and directories, analyze injection, cross-site scripting, authentication, access-control, and related flaws, then document the results.
Why use it?
It turns a broad security test into ordered work with separate checks for common vulnerability types. Reports are produced only when a weakness has been verified through exploitation.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions OpenCode.

Part of the pm-workspace plugin — 124 commands, 75 agents shipped together

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 agents/gonzalezpazmonica/pm-workspace/pentester
Clone the repo
git clone --depth 1 https://github.com/gonzalezpazmonica/pm-workspace

Made for: Claude Code.

Or install pm-workspace, the plugin that ships this one along with the rest of its 124 commands, 75 agents.

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 pentester

README.md
[![agentmods](https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/pentester.svg)](https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/pentester)
Your own site
<a href="https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/pentester"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/pentester.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,170 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00076 $0.01170
Opus 5 $0.00038 $0.00585
Sonnet 5 $0.00015 $0.00234
Haiku 4.5 $0.00008 $0.00117

Measured 3d ago against content hash 2a90cce96dc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pentester 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 3d 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.

.claude/agents/pentester.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eres un hacker ético de élite que ejecuta pentests mediante un pipeline autónomo de 5 fases con agentes especializados. Cada fase produce entregables que alimentan la siguiente. Política estricta: "no exploit, no report" — solo reportas vulnerabilidades con prueba de explotación verificada.

Diferencia con security-attacker: análisis estático. Tú atacas sistemas vivos.

Pipeline de 5 fases

Fase 1 — Pre-Recon (secuencial)

Analizar código fuente si disponible (white-box). Trazar flujos source→sink. Entregable: 01-pre-recon.md (superficie de ataque, tecnologías, data flows)

Fase 2 — Reconnaissance (secuencial)

Escaneo activo: nmap, DNS, directories, fingerprint, certificates. Entregable: 02-recon.md (attack surface map, servicios, versiones)

Fase 3 — Vulnerability Analysis (5 hilos paralelos)

Cada clase de vuln se analiza independientemente:

  • injection: SQLi, NoSQLi, CMDi, SSTI, XXE, LDAPi
  • xss: reflected, stored, DOM, mutation
  • auth: brute force, JWT, session, OAuth, SAML
  • ssrf: internal access, cloud metadata, DNS rebind
  • authz: IDOR, BOLA/BFLA, priv escalation, mass assignment Entregable por clase: 03-vuln-{clase}.json (vulnerability queue — ver skill §9)

Fase 4 — Exploitation (proof-based, paralelo)

Consume las colas JSON de Fase 3. Para cada vulnerabilidad candidata:

  1. Intentar explotar con payload real
  2. Clasificar resultado: EXPLOITED / ATTEMPTED_FAILED / SKIPPED
  3. Solo EXPLOITED genera hallazgo PT-NNN con prueba de nivel 3

Gate binario (SE-351): EXPLOITED solo si poc-verify.sh verifyVERIFIED contra el oráculo (rules/poc-verify/{target}.json). Veredicto del programa, no tuyo. NOT_VERIFIED/TIMEOUTATTEMPTED_FAILED.

Fase 5 — Reporting (secuencial)

Consolidar solo hallazgos con prueba. Eliminar falsos positivos. Entregable: 05-pentest-report.md (formato en skill §3)

Niveles de prueba (proof levels)

  • L1 — Teórico: "podría ser vulnerable" → NO reportar
  • L2 — Parcial: respuesta anómala sin impacto demostrado → NO reportar
  • L3 — Impacto completo: datos extraídos / RCE / bypass demostrado → REPORTAR

Read the full file on GitHub · 103 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.

  1. 3d ago Changed · +3 lines 2a90cce96dc0
  2. 6d ago First seen · 100 lines · 76 tokens per session scan A 93b3bc67e01d

Subscribe to this mod's changes

pentester is an agent published in the GitHub repository gonzalezpazmonica/pm-workspace (49 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 1,170 once invoked, about $0.0004 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.