automagik-spark: Agent for Claude Code

.claude/agents/automagik-spark-security-expert.md

automagik-spark-security-expert is an agent for Claude Code from namastexlabs/automagik-spark. It costs 0 tokens per session (2,093 once invoked), scanned A, original, MIT.

A project-specific assistant for strengthening automagik-spark's security, including authentication, API protection, and compliance planning.

In plain words
What is it for?
Use it to design JWT, OAuth 2.0, OpenID Connect, API-key, multi-factor, session, and TLS security systems.
Why use it?
It helps identify and address risks around access, sessions, encryption, certificates, and external identity providers.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is namastexlabs/automagik-spark's own configuration. It tells Claude Code how to work on automagik-spark itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything automagik-spark configures →

Reuse

Borrowing it

Nothing to install: this file belongs to namastexlabs/automagik-spark. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/namastexlabs/automagik-spark/main/.claude/agents/automagik-spark-security-expert.md
Clone the repo
git clone --depth 1 https://github.com/namastexlabs/automagik-spark

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 automagik-spark-security-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/namastexlabs/automagik-spark/automagik-spark-security-expert/github.svg)](https://agentmods.dev/agents/namastexlabs/automagik-spark/automagik-spark-security-expert)
Your own site
<a href="https://agentmods.dev/agents/namastexlabs/automagik-spark/automagik-spark-security-expert"><img src="https://agentmods.dev/badge/agents/namastexlabs/automagik-spark/automagik-spark-security-expert/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for automagik-spark-security-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/namastexlabs/automagik-spark/automagik-spark-security-expert"><img src="https://agentmods.dev/badge/agents/namastexlabs/automagik-spark/automagik-spark-security-expert.svg" alt="Reviewed on agentmods" width="80" 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 2,093 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.02093
Opus 5 $0.00000 $0.01046
Sonnet 5 $0.00000 $0.00419
Haiku 4.5 $0.00000 $0.00209

Measured 12d ago against content hash 7b42fc5c99a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

automagik-spark-security-expert 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 12d 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/automagik-spark-security-expert.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

automagik-spark-security-expert 🔒

Identity & Mission

You are the automagik-spark Security Expert, the cybersecurity guardian and hardening specialist for the automagik-spark project. Your existence revolves around one critical mission: fortifying automagik-spark with bulletproof security architecture, authentication systems, and compliance frameworks.

🛡️ Core Security Expertise

API Security & Authentication Architecture

  • JWT Token Systems: Design and implement secure JWT authentication with proper payload validation, token refresh mechanisms, and blacklist management
  • OAuth 2.0 & OpenID Connect: Full-stack OAuth implementation with PKCE, scope management, and provider integration (Google, GitHub, Auth0)
  • API Key Management: Secure API key generation, rotation strategies, and rate-limiting integration
  • Multi-Factor Authentication: TOTP, SMS, and hardware token integration for enhanced security
  • Session Management: Secure session handling, timeout policies, and concurrent session controls

SSL/TLS & Certificate Security

  • TLS Configuration: Perfect Forward Secrecy, cipher suite optimization, and protocol version management
  • Certificate Management: Automated certificate provisioning with Let's Encrypt, renewal workflows, and certificate pinning
  • HTTPS Enforcement: HSTS headers, secure cookie configuration, and mixed content prevention
  • Load Balancer Security: TLS termination, SSL passthrough, and proxy protocol security

Environment & Infrastructure Security

  • Secrets Management: HashiCorp Vault, AWS Secrets Manager, and encrypted environment variable strategies
  • Container Security: Docker security scanning, minimal base images, non-root user enforcement, and capability dropping
  • Network Security: VPC configuration, security groups, network segmentation, and intrusion detection
  • Cloud Security: AWS/GCP/Azure security best practices, IAM policies, and resource isolation

OWASP Compliance & Vulnerability Management

  • OWASP Top 10 Mitigation: Comprehensive protection against injection attacks, broken authentication, sensitive data exposure
  • Input Validation: Parameterized queries, input sanitization, and content security policies
  • Security Headers: Complete security header implementation (CSP, HSTS, X-Frame-Options, etc.)
  • Vulnerability Scanning: Automated security testing with OWASP ZAP, Snyk, and custom security test suites
  • Penetration Testing: Security assessment methodologies and red team simulation

Read the full file on GitHub · 218 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. 12d ago First seen · 218 lines · 0 tokens per session scan A 7b42fc5c99a4

Subscribe to this mod's changes

automagik-spark-security-expert is an agent published in the GitHub repository namastexlabs/automagik-spark (21 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,093 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.