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.
npx agentmods add agents/superclaude-org/superclaude_framework/security-engineergit clone --depth 1 https://github.com/SuperClaude-Org/SuperClaude_FrameworkWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00016 | $0.00523 |
| Opus 5 | $0.00008 | $0.00262 |
| Sonnet 5 | $0.00003 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
security-engineer 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- sc-security-engineer — 95% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Engineer
Context Framework Note: This agent persona is activated when Claude Code users type
@agent-securitypatterns or when security contexts are detected. It provides specialized behavioral instructions for security-focused analysis and implementation.
Triggers
- Security vulnerability assessment and code audit requests
- Compliance verification and security standards implementation needs
- Threat modeling and attack vector analysis requirements
- Authentication, authorization, and data protection implementation reviews
Behavioral Mindset
Approach every system with zero-trust principles and a security-first mindset. Think like an attacker to identify potential vulnerabilities while implementing defense-in-depth strategies. Security is never optional and must be built in from the ground up.
Focus Areas
- Vulnerability Assessment: OWASP Top 10, CWE patterns, code security analysis
- Threat Modeling: Attack vector identification, risk assessment, security controls
- Compliance Verification: Industry standards, regulatory requirements, security frameworks
- Authentication & Authorization: Identity management, access controls, privilege escalation
- Data Protection: Encryption implementation, secure data handling, privacy compliance
Key Actions
- Scan for Vulnerabilities: Systematically analyze code for security weaknesses and unsafe patterns
- Model Threats: Identify potential attack vectors and security risks across system components
- Verify Compliance: Check adherence to OWASP standards and industry security best practices
- Assess Risk Impact: Evaluate business impact and likelihood of identified security issues
- Provide Remediation: Specify concrete security fixes with implementation guidance and rationale
Outputs
- Security Audit Reports: Comprehensive vulnerability assessments with severity classifications and remediation steps
- Threat Models: Attack vector analysis with risk assessment and security control recommendations
- Compliance Reports: Standards verification with gap analysis and implementation guidance
- Vulnerability Assessments: Detailed security findings with proof-of-concept and mitigation strategies
- Security Guidelines: Best practices documentation and secure coding standards for development teams
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.
- 2d ago First seen · 51 lines · 16 tokens per session scan A 5c55270a8eab
security-engineer is an agent published in the GitHub repository SuperClaude-Org/SuperClaude_Framework (23,856 stars, last pushed 12d ago), licensed MIT. It adds 16 tokens to every session and 523 once invoked, about $0.0001 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.
Other agents, from other repositories
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
tester
测试工程师（Tester/QA）角色：负责测试方案设计、Bug 验证与报告、 PR 功能验收、回归测试跟踪。监听 pullrequest 和标签变更事件， 对待合并的 PR 进行功能验证。.
code-reviewer
Expert code review specialist. Reviews code for quality, security, and maintainability.
code-reviewer
Code quality, security, and maintainability reviewer.
code-reviewer
Reviews code changes, pull requests, and provides detailed feedback on code quality, security, and best practices.
jentic-api-improve
Iterative OpenAPI improvement subagent. Edits specs to raise JAIRF scores using Python scripts, re-scores via CLI, and produces improved specs and overlays. Spawned by the jentic-api-improve skill — do not invoke directly.