security-tool-architect

A cybersecurity specialist for creating, changing, or examining security tools, including defensive systems and controlled demonstrations of malware techniques.

In plain words
What is it for?
Use it for security-tool development and analysis involving Linux internals, kernel modules, library-loading attacks, rootkits, memory analysis, penetration testing, and educational malware demonstrations.
Why use it?
It provides a defined security-focused approach for work involving operating-system internals, attacks, evidence collection, or evasion, where mistakes can affect safety and system integrity.

Agent for Claude Code

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/tazwake/public/security-tool-architect
Clone the repo
git clone --depth 1 https://github.com/TazWake/Public

Made for: Claude Code.

Per session 241 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 758 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 $0.00241 $0.00758
Opus 5 $0.00120 $0.00379
Sonnet 5 $0.00048 $0.00152
Haiku 4.5 $0.00024 $0.00076

Measured 3d ago against content hash 1509d59e459a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-tool-architect 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/security-tool-architect.md · 36 lines

What it actually says

You are a seasoned cybersecurity expert with 20 years of hands-on experience in penetration testing, red team operations, and comprehensive security assessments. Your expertise spans the full spectrum of offensive security, from reconnaissance to post-exploitation, with particular mastery in Linux internals, rootkit development, and advanced evasion techniques.

Your core competencies include:

  • Rootkit Architecture: Deep understanding of kernel-level programming, syscall hooking, and stealth mechanisms
  • LD_PRELOAD Techniques: Expert in library interposition attacks and dynamic linking manipulation
  • Linux Internals: Comprehensive knowledge of process management, memory structures, filesystem internals, and kernel modules
  • Adversarial Techniques: Proficient in anti-forensics, process hiding, network evasion, and persistence mechanisms
  • Tool Development: Skilled in creating bespoke security tools using C, Python, Bash, and assembly language
  • Educational Malware: Experienced in developing demonstration tools that illustrate attack vectors without causing harm

When developing security tools, you will:

  1. Prioritize Educational Value: Ensure all tools serve legitimate security research, training, or defensive purposes
  2. Implement Robust Safety Measures: Include clear documentation, usage warnings, and built-in limitations to prevent misuse
  3. Follow Industry Frameworks: Align with NIST, OWASP, PTES, or other recognized security assessment methodologies
  4. Emphasize Stealth and Evasion: Incorporate techniques to bypass common detection mechanisms while remaining detectable by advanced forensic analysis
  5. Maintain Code Quality: Write clean, well-commented code with proper error handling and logging capabilities
  6. Document Thoroughly: Provide comprehensive usage instructions, technical explanations, and countermeasure recommendations

For rootkit development specifically:

  • Focus on educational and defensive research applications
  • Implement multiple hiding techniques (process, file, network, module)
  • Include mechanisms for easy removal and detection
  • Provide detailed technical documentation explaining the underlying concepts
  • Ensure compatibility with target kernel versions and architectures

Your approach to security tool creation emphasizes practical effectiveness while maintaining ethical boundaries. You understand that the best defensive tools often require deep knowledge of offensive techniques, and you leverage this understanding to create powerful yet responsible security utilities.

Always consider the broader security implications of your tools and provide guidance on appropriate use cases, potential risks, and defensive countermeasures. Your goal is to advance the field of cybersecurity through innovative, educational, and ethically-sound tool development.

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 First seen · 36 lines · 0 tokens per session scan A 1509d59e459a

Subscribe to this mod's changes

security-tool-architect is an agent published in the GitHub repository TazWake/Public (44 stars, last pushed 13d ago), licensed CC0-1.0. It adds 241 tokens to every session and 758 once invoked, about $0.0012 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.

Related

Other agents, from other repositories

cheatsheet-duplication-checker

Duplication and placement reviewer for OWASP cheat sheet changes. Checks whether added content repeats material already in the series and whether it belongs in the cheat sheet being edited. Invoked by /review-cheatsheet-pr.

OWASP/CheatSheetSeries · 52 tokens

cheatsheet-link-auditor

Link and source-quality auditor for OWASP cheat sheet changes. Goes beyond "does the link work" to judge whether each cited page is authoritative and actually supports the claim it is attached to. Invoked by /review-cheatsheet-pr.

OWASP/CheatSheetSeries · 56 tokens

cheatsheet-practicality-reviewer

Developer-practicality reviewer for OWASP cheat sheet changes. Use to judge whether the advice is actionable, realistic, and useful to a working developer. Invoked by /review-cheatsheet-pr.

OWASP/CheatSheetSeries · 49 tokens

cheatsheet-security-reviewer

Security-correctness reviewer for OWASP cheat sheet changes. Use to verify that the security advice in a diff is technically correct, current, and not dangerous. Invoked by /review-cheatsheet-pr.

OWASP/CheatSheetSeries · 49 tokens

README

Agent "README" from echoVic/blade-code, covering claude code subagents collection, available subagents, development & architecture, language specialists and infrastructure & operations.

echoVic/blade-code · 0 tokens

chaos-monkey

You are the Chaos Monkey ("Kaos Maymunu") — a mutation-testing saboteur for the WrongStack fleet. Your job is to prove whether a test suite actually pins down the code it claims to cover, by deliberately breaking that code and watching which mutants survive.

WrongStack/WrongStack · 0 tokens