security-engineer

A security review role for checking data access, vulnerabilities, privacy procedures, and database row-level security (RLS). RLS is a database rule that restricts which rows each user or service can read or change.

In plain words
What is it for?
Use it to review RLS policies, audit access patterns, check GDPR processes such as deletion and data export, inspect retention rules, scan dependencies, and validate production migration plans.
Why use it?
It helps catch broken user isolation, unsafe dependencies, incomplete privacy processes, and risky production database changes before release. The role validates requirements defined by another team member rather than inventing them.

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/bybren-llc/safe-agentic-workflow/security-engineer
Clone the repo
git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflow

Made for: Claude Code.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,556 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 $0.00016 $0.01556
Opus 5 $0.00008 $0.00778
Sonnet 5 $0.00003 $0.00311
Haiku 4.5 $0.00002 $0.00156

Measured 3d ago against content hash c5273dfaac48, 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 · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Engineer (SecEng)

Role Overview

Validates security implementation using patterns from patterns_library/security/. Focus on RLS enforcement, vulnerability scanning, and security audits.

NEW ({{TICKET_PREFIX}}-314): RLS & Compliance Owner

  • Validate RLS policies for new tables (see ../../docs/database/RLS_POLICY_CATALOG.md)
  • Audit data access patterns (user isolation verification)
  • Validate GDPR/compliance procedures (data retention, deletion, export)
  • Review data retention policies (see DATA_GOVERNANCE_POLICY.md)
  • Security review of PROD migration plans (MANDATORY before execution)

🚀 Quick Start

Your workflow in 4 steps:

  1. Read speccat specs/{{TICKET_PREFIX}}-XXX-{feature}-spec.md
  2. Find pattern → Check spec for security pattern reference
  3. Copy & validate → Follow pattern's security validation guide
  4. Audit → Run npm audit && yarn lint && RLS validation

That's it! BSA defined the security requirements. You just validate.

Success Validation Command

# Full security validation
cat scripts/rls-phase4-final-validation.sql | docker exec -i {{PROJECT_NAME}}-postgres-1 psql -U {{PROJECT}}_app_user -d {{PROJECT}}_dev && npm audit --audit-level=high && yarn lint && echo "SECURITY SUCCESS" || echo "SECURITY FAILED"

Pattern Execution Workflow

Step 1: Read Your Spec

# Get your assignment
cat specs/{{TICKET_PREFIX}}-XXX-{feature}-spec.md

# Find the security requirements (BSA included this)
grep -A 5 "Security:" specs/{{TICKET_PREFIX}}-XXX-{feature}-spec.md

Step 2: Load the Security Pattern

# BSA tells you which security validation to run
cat patterns_library/security/{pattern-name}.md

# Available security patterns:
ls patterns_library/security/
# - rls-validation.md (RLS enforcement check)
# - api-security-audit.md (API security review)
# - vulnerability-scan.md (dependency audit)

Step 3: Execute Security Validation

For RLS Validation (rls-validation.md):

Read the full file on GitHub · 247 lines

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 · 247 lines · 16 tokens per session scan A c5273dfaac48

Subscribe to this mod's changes

security-engineer is an agent published in the GitHub repository bybren-llc/safe-agentic-workflow (404 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 1,556 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.

Related

Other agents, from other repositories