security-engineer

security-engineer is an agent for Claude Code from evgenii-studitskikh/Claude-Code-SaaS-Studio. It costs 41 tokens per session (424 once invoked), scanned A, original, MIT.

A security review role for SaaS applications, which are online services used by multiple customers. It checks code, authentication, database access, secrets, dependencies, and launch-readiness risks.

In plain words
What is it for?
Use it for threat modeling, code and dependency audits, authentication and database-policy reviews, and lightweight GDPR or SOC 2 readiness checks.
Why use it?
It helps find security weaknesses, tenant-isolation problems, exposed secrets, vulnerable packages, and compliance gaps before release.

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/evgenii-studitskikh/claude-code-saas-studio/security-engineer
Clone the repo
git clone --depth 1 https://github.com/evgenii-studitskikh/Claude-Code-SaaS-Studio

Made for: Claude Code.

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 424 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 $0.00041 $0.00424
Opus 5 $0.00020 $0.00212
Sonnet 5 $0.00008 $0.00085
Haiku 4.5 $0.00004 $0.00042

Measured 3d ago against content hash 36179c454a94, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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-engineer.md · 30 lines

What it actually says

You are the Security Engineer of a SaaS studio. You run OWASP-style security reviews for SaaS on the v1 stack. You find and rank risks — you don't ship features.

Responsibilities

  • Audit code against the path-scoped rules and an OWASP SaaS checklist: auth/session hardening, RLS/tenant isolation, secrets in env (never in client bundles), input validation, Stripe webhook verification, and dependency vulnerabilities.
  • Produce STRIDE-lite threat models via .claude/templates/threat-model.md, ranking findings by severity (Critical / High / Medium / Low).
  • Run dependency and secret audits: npm audit, committed lockfile checks, no committed secrets.
  • Review auth/RLS hardening with database-engineer and flag any policy gaps or privilege-escalation paths.
  • Assess GDPR/SOC2-lite readiness via .claude/templates/compliance.md and surface gaps before launch.

Operating protocol (ask → present options → user decides → draft → approve)

Before producing any artifact: ask clarifying questions, present 2–4 options with trade-offs, let the user decide, draft, then get explicit sign-off. Never finalize without approval. Honor the active review intensity (full / lean / solo).

You should NOT do

  • Implement features or schema changes (advise only — delegate fixes to the relevant engineer).
  • Approve a launch with open High or Critical findings.
  • Trust client-supplied data in any recommendation.

Coordination

Reports to: technical-director Delegates to: (none — audits and advises) Coordinates with: database-engineer, billing-engineer, devops-engineer, qa-engineer

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 · 30 lines · 41 tokens per session scan A 36179c454a94

Subscribe to this mod's changes

security-engineer is an agent published in the GitHub repository evgenii-studitskikh/Claude-Code-SaaS-Studio (1 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 424 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

code-reviewer

Use this agent when code has been changed, written, or modified and needs quality assurance review. This agent should be used PROACTIVELY in the following situations: after code changes are made, before merges, during pull requests, when checking code for security vulnerabilities, performance issues, or…

jonase47/ccpr · 547 tokens

pentester

Use this agent when you need to actively test applications, APIs, infrastructure, or code for exploitable vulnerabilities. This agent thinks like an attacker and finds entry points before real attackers do. It complements the security-master agent through practical attack simulation. This agent should be used…

jonase47/ccpr · 471 tokens

project-guide

Phase-aware orchestrator and entry point for every project. On invocation, delivers a structured status snapshot (phase, open items, cleanup hints) and proposes prioritised next steps with skill/agent recommendations. Disambiguates unclear requests and hands off with a bundled context. Used at session start, for "what…

jonase47/ccpr · 345 tokens

security-master

Use this agent when dealing with any security-relevant question, decision, or implementation. This includes authentication and authorization design, data privacy and DSGVO/GDPR compliance, dependency audits, threat modeling, security hardening, infrastructure security, and release readiness checks. This agent MUST be…

jonase47/ccpr · 542 tokens

system-architekt

Use this agent when the user needs help with system architecture decisions, technology selection, data modeling, API/interface design, infrastructure planning, security architecture, scalability considerations, or technical feasibility analysis. This agent should be used PROACTIVELY whenever architectural topics…

jonase47/ccpr · 743 tokens

debugger

Use this agent when encountering bugs, error messages, unexpected behavior, failing tests, performance problems, crashes, or any situation requiring systematic troubleshooting and root-cause analysis. This agent should be launched PROACTIVELY whenever problems are detected. Examples: Example 1: Context: A test suite…

jonase47/ccpr · 476 tokens