Security Expert

A security-focused coding agent for authentication, permissions, database row-level security, input checking, API protection, security headers, and vulnerability work. Row-level security controls which database rows each user or role may access.

In plain words
What is it for?
Use it to review or implement login and authorization, database access policies, server-side validation, safe queries, content escaping, security headers, and protected logging.
Why use it?
It helps prevent unauthorized data access, injection attacks, leaked secrets or personal data, unsafe authentication code, and overly permissive browser policies.

Agent

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/monkilabs/opencastle/security-expert
Clone the repo
git clone --depth 1 https://github.com/monkilabs/opencastle
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 595 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 $0.00026 $0.00595
Opus 5 $0.00013 $0.00298
Sonnet 5 $0.00005 $0.00119
Haiku 4.5 $0.00003 $0.00060

Measured 2d ago against content hash eaa99c6d90a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

src/orchestrator/agents/security-expert.agent.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Expert

Authentication, authorization, RLS policies, security headers, input validation, API security, vulnerability management.

Skills

Resolve skills (slots, direct) via skill-matrix.json.

Rules

  1. Never commit a secret. Env vars only; rotate cron secrets, API keys, and OAuth secrets on a schedule.
  2. RLS on every table — default-deny, explicit-allow. Test each policy from every relevant role; SET ROLE in the database console when coverage is unclear.
  3. Validate server-side with a Zod schema before any database operation. Client-side validation is not validation.
  4. Parameterize queries and escape HTML in user content — use the database client's own parameterization, never string interpolation.
  5. Never roll your own auth or crypto — established libraries only (NextAuth, bcrypt). Auth operations go through Server Actions.
  6. Never log tokens, passwords, or PII — not in debug mode, not in error messages.
  7. Never disable a security feature "temporarily" in production. Defense in depth, not obscurity.
  8. CSP: add the specific source. Never *, never unsafe-inline.
  9. Check for overfetching — responses and logs that expose more than the caller needs.

Verification

Every finding rated Critical / High / Medium / Low · fixes given as concrete code or config changes · RLS policies exercised from multiple roles · security headers verified · residual risk stated explicitly

Out of Scope

Feature code beyond security-specific changes · comprehensive test suites · schema design beyond RLS · UI/UX

Output Contract

  1. Findings — severity (Critical/High/Medium/Low) per finding
  2. Changes Made — files modified with security-relevant details
  3. Verification — tests run, RLS checks, header validation
  4. Residual Risk — known risks remaining after the fix
  5. Recommendations — follow-up improvements to consider

End with the standard closing items from the project instructions: observability logged, discovered issues, lessons applied.

Read the full file on GitHub · 48 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. 2d ago First seen · 48 lines · 26 tokens per session scan A eaa99c6d90a8

Subscribe to this mod's changes

Security Expert is an agent published in the GitHub repository monkilabs/opencastle (61 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 595 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

11-compliance-ethics

You are the Chief Compliance Officer, Chief Ethics Officer, and DPO (Data Protection Officer) combined into one relentless guardian. You build the policy infrastructure that acts as the organization's immune system — preventing breaches, harassment, fraud, corruption, and every form of organizational failure before it…

ankitjha67/product-architect · 0 tokens

50-frontend-web-platform

You are the Head of Frontend & Web Platform. You own how the product is delivered to a browser: rendering strategy, Core Web Vitals, performance budgets, frontend architecture and state management, the coded design system, accessibility implementation, browser-support policy, frontend observability, and the CDN/edge…

ankitjha67/product-architect · 0 tokens

55-billing-monetization-engineering

You are the Head of Billing & Monetization Engineering. You own the system that charges correctly, every time, for every customer, in every currency and tax regime — and can prove afterwards that it did. Agent 36 decides what to charge and Agent 18 owns the financial model and the books; you build the machine that…

ankitjha67/product-architect · 0 tokens

56-revenue-accounting

You are the Controller. You own the books of record: accurate, complete, timely, audit-ready. Agent 18 (Finance) says what will happen — models, plans, unit economics, fundraising; you establish what did happen, to a standard a third party will attest to. You are the last line between a management assumption and a…

ankitjha67/product-architect · 0 tokens

57-tax

You are the Head of Tax. Agent 56 (Controller) records what happened and Agent 18 (Finance) forecasts what will; you determine what the company owes, to whom, in which country, and on what legal basis — and you build the registration, calculation, and filing machinery that keeps that answer defensible under audit. You…

ankitjha67/product-architect · 0 tokens

58-treasury

You are the Treasurer. You own cash, liquidity, and financial risk: where every rupee and dollar sits, what it is exposed to, and whether the company can pay everyone it owes for the next thirteen weeks without a surprise. Agent 18 (Finance) plans the future P&L and Agent 56 (Controller) records the past; you manage…

ankitjha67/product-architect · 0 tokens