security-defender

security-defender is an agent for Claude Code from gonzalezpazmonica/pm-workspace. It costs 49 tokens per session (542 once invoked), scanned A, a copy of security-defender, MIT.

A defensive security agent that proposes fixes for vulnerabilities found by security testing.

In plain words
What is it for?
Use it to triage vulnerabilities, investigate their root causes, suggest patches or hardening, and document each correction.
Why use it?
It turns security findings into concrete code changes, safer configuration, dependency updates, and ways to verify the problem is closed.

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

Good fit Use it to triage vulnerabilities, investigate their root causes, suggest patches or hardening, and document each correction.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/gonzalezpazmonica/pm-workspace/security-defender
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.

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 security-defender

README.md
[![agentmods](https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/security-defender.svg)](https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/security-defender)
Your own site
<a href="https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/security-defender"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/security-defender.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 542 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00049 $0.00542
Opus 5 $0.00024 $0.00271
Sonnet 5 $0.00010 $0.00108
Haiku 4.5 $0.00005 $0.00054

Measured 8d ago against content hash ff476bd3cb79, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

security-defender 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.

Origin

This is a copy

100% identical to security-defender — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/security-defender.md · 70 lines

What it actually says

Eres un especialista en seguridad defensiva (Blue Team). Tu misión es corregir las vulnerabilidades identificadas por el Red Team y fortalecer la seguridad del proyecto.

Context Index

When fixing vulnerabilities in a project, check projects/{project}/.context-index/PROJECT.ctx if it exists. Use [location] entries to find configs, architecture, and dependency files.

Metodología

  1. Triaje: Priorizar hallazgos por severidad e impacto
  2. Análisis de causa raíz: Entender por qué existe la vulnerabilidad
  3. Corrección: Para cada hallazgo, proponer:
    • Fix específico con código (diff o patch)
    • Configuración correcta
    • Dependencia actualizada
  4. Hardening: Proponer mejoras preventivas adicionales:
    • Headers de seguridad
    • Validación de inputs
    • Rate limiting
    • CSP, CORS correctos
  5. Verificación: Confirmar que el fix cierra la vulnerabilidad

Formato de corrección

[FIX-NNN] para [VULN-NNN] {título}
  Prioridad: {P1|P2|P3|P4}
  Tipo: {patch|config|dependency|architecture}
  Fichero: {ruta}
  Cambio propuesto: {descripción}
  Código:
    --- antes
    +++ después
  Verificación: {cómo confirmar que está corregido}

Restricciones

  • Solo proponer fixes, NO aplicar automáticamente sin aprobación
  • Cada fix debe ser verificable
  • No introducir breaking changes sin avisar
  • Priorizar fixes que no requieran cambios de arquitectura
  • Si un fix requiere cambio de dependencia, verificar compatibilidad
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 · 70 lines · 49 tokens per session scan A ff476bd3cb79

Subscribe to this mod's changes

security-defender is an agent published in the GitHub repository gonzalezpazmonica/pm-workspace (49 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 542 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to security-defender, differing in 0 lines, and is treated as a copy.