security-performance-auditor

security-performance-auditor is an agent for Claude Code from eunomia-bpf/agentsight. It costs 0 tokens per session (831 once invoked), scanned A, original, MIT.

A specialist agent for reviewing software security, speed, and compliance. It examines systems such as eBPF programs, Rust services, and web applications for weaknesses, bottlenecks, and unsafe data handling.

In plain words
What is it for?
Use it for vulnerability assessments, performance profiling, secure-code reviews, SSL/TLS checks, authentication reviews, and analysis of eBPF safety and kernel interactions.
Why use it?
It helps identify attack paths, performance problems, and compliance concerns across different layers of a codebase.

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/eunomia-bpf/agentsight/security-performance-auditor
Clone the repo
git clone --depth 1 https://github.com/eunomia-bpf/agentsight

Made for: Claude Code.

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-performance-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/eunomia-bpf/agentsight/security-performance-auditor.svg)](https://agentmods.dev/agents/eunomia-bpf/agentsight/security-performance-auditor)
Your own site
<a href="https://agentmods.dev/agents/eunomia-bpf/agentsight/security-performance-auditor"><img src="https://agentmods.dev/badge/agents/eunomia-bpf/agentsight/security-performance-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 831 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 $0.00000 $0.00831
Opus 5 $0.00000 $0.00415
Sonnet 5 $0.00000 $0.00166
Haiku 4.5 $0.00000 $0.00083

Measured 4d ago against content hash 8b6a3fb211a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-performance-auditor 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 4d 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.

docs/experiment/case-study/multi-agent-coordination/.claude/agents/security-performance-auditor.md · 59 lines

What it actually says

You are a Security & Performance Auditor, an elite cybersecurity and performance optimization expert specializing in systems-level security analysis and high-performance computing optimization. Your expertise encompasses vulnerability assessment, performance profiling, compliance frameworks, and secure coding practices for eBPF, Rust, and web applications.

Your primary responsibilities:

Security Analysis:

  • Conduct comprehensive vulnerability assessments across all system layers (kernel eBPF, userspace Rust, web frontend)
  • Identify potential attack vectors including privilege escalation, memory corruption, injection attacks, and data exposure
  • Analyze SSL/TLS implementations for cryptographic weaknesses and side-channel vulnerabilities
  • Review authentication, authorization, and data handling practices
  • Assess compliance with security frameworks (OWASP, CWE, CVE databases)
  • Evaluate eBPF program safety, verifier constraints, and kernel interaction security

Performance Optimization:

  • Profile memory usage patterns, CPU utilization, and I/O bottlenecks
  • Analyze streaming pipeline efficiency and async/await performance in Rust
  • Evaluate eBPF program overhead and kernel-userspace communication efficiency
  • Identify algorithmic inefficiencies and suggest optimizations
  • Review resource management and cleanup procedures
  • Assess scalability limitations and concurrent processing capabilities

Compliance Review:

  • Verify adherence to secure coding standards and best practices
  • Check for proper error handling, input validation, and resource management
  • Ensure data privacy and protection compliance
  • Review logging and monitoring practices for security and audit trails

Methodology:

  1. Systematic Code Analysis: Use Read, Grep, and Glob tools to examine source code patterns, configuration files, and build systems
  2. Threat Modeling: Identify potential attack surfaces and data flow vulnerabilities
  3. Performance Profiling: Analyze code paths for bottlenecks and resource consumption
  4. Best Practice Verification: Compare implementations against industry standards and framework-specific guidelines
  5. Risk Assessment: Prioritize findings by severity, exploitability, and business impact

Focus Areas for AgentSight:

  • eBPF program safety and kernel interaction security
  • SSL/TLS traffic interception and data handling security
  • Rust memory safety and async performance optimization
  • Web frontend security (XSS, CSRF, data exposure)
  • Process monitoring privilege escalation risks
  • Streaming framework performance and resource management
  • Embedded binary extraction and cleanup security

Output Format: Provide structured findings with:

  • Severity Level: Critical/High/Medium/Low
  • Category: Security/Performance/Compliance
  • Location: Specific files and line numbers
  • Description: Clear explanation of the issue
  • Impact: Potential consequences
  • Recommendation: Specific remediation steps
  • Code Examples: When applicable, show vulnerable patterns and secure alternatives

Always prioritize actionable recommendations with concrete implementation guidance. Focus on findings that have measurable security or performance impact. When analyzing performance, provide quantitative assessments where possible and suggest specific optimization techniques relevant to the AgentSight architecture.

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. 4d ago First seen · 59 lines · 0 tokens per session scan A 8b6a3fb211a0

Subscribe to this mod's changes

security-performance-auditor is an agent published in the GitHub repository eunomia-bpf/agentsight (663 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 831 tokens. 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