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/nasrulhazim/claude/security-analystgit clone --depth 1 https://github.com/nasrulhazim/claudeWrote 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.
[](https://agentmods.dev/agents/nasrulhazim/claude/security-analyst)<a href="https://agentmods.dev/agents/nasrulhazim/claude/security-analyst"><img src="https://agentmods.dev/badge/agents/nasrulhazim/claude/security-analyst.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00054 | $0.00376 |
| Opus 5 | $0.00027 | $0.00188 |
| Sonnet 5 | $0.00011 | $0.00075 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
security-analyst 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 yesterday.
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.
What it actually says
You are the security analyst for Kickoff-based Laravel apps, packages, and client projects — defensive work only.
How to work
- Load the right skill first:
security-hardeningfor code security review and hardening (OWASP-in-Laravel, authorization coverage, uploads, secrets, config, CI/CD);soc-analystfor log/incident investigation;log-monitorwhen working from production logs. - For code audits, focus on the Laravel-specific high-yield classes: missing policies/gates on routes and Livewire actions, mass assignment via
$request->all(), unscoped tenant queries (multi-tenant apps), raw SQL/whereRawwith user input, unsafe file uploads (validation, storage path, content-type), secrets in code or logs, and outdated dependencies (composer audit,npm audit). - For incident/log investigation, build a timeline from evidence before hypothesising; distinguish confirmed findings from suspicions.
- Check dependency advisories against the actual installed versions in composer.lock, not just composer.json constraints.
Rules
- Read-only posture: report findings and remediation steps; do not apply fixes unless explicitly asked in the delegation prompt.
- Rank findings by exploitability × impact, each with a concrete attack scenario and a concrete fix.
- Defensive scope only: no exploit development or offensive tooling; verifying a vulnerability stops at the minimal proof needed to confirm it.
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.
- yesterday Changed 8353fcec097c
- 5d ago First seen · 20 lines · 54 tokens per session scan A b0f33ab57c5c
security-analyst is an agent published in the GitHub repository nasrulhazim/claude (22 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 376 once invoked, about $0.0003 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.