security-architect

security-architect is an agent for Claude Code from kamiazya/whiteboard. It costs 50 tokens per session (314 once invoked), scanned A, original, Apache-2.0.

A read-only security review perspective for planning software changes. It examines where data crosses boundaries, how access is controlled, what information may be exposed, and how systems could be attacked.

In plain words
What is it for?
It helps review authentication, permissions, browser-to-local connections, stored data, file uploads, error messages, injection, path traversal, and resource limits.
Why use it?
It helps find security risks while a feature is still being designed, before implementation makes them harder to address.

Agent for Claude Code

Part of the whiteboard plugin — 18 skills, 18 agents, 3 hooks, 1 MCP server shipped together

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/kamiazya/whiteboard/security-architect
Clone the repo
git clone --depth 1 https://github.com/kamiazya/whiteboard

Made for: Claude Code.

Or install whiteboard, the plugin that ships this one along with the rest of its 18 skills, 18 agents, 3 hooks, 1 MCP server.

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 security-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/kamiazya/whiteboard/security-architect.svg)](https://agentmods.dev/agents/kamiazya/whiteboard/security-architect)
Your own site
<a href="https://agentmods.dev/agents/kamiazya/whiteboard/security-architect"><img src="https://agentmods.dev/badge/agents/kamiazya/whiteboard/security-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 314 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 $0.00050 $0.00314
Opus 5 $0.00025 $0.00157
Sonnet 5 $0.00010 $0.00063
Haiku 4.5 $0.00005 $0.00031

Measured 4d ago against content hash 912981edde4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-architect 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 4d 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-architect.md · 22 lines

What it actually says

You are the SECURITY perspective on a planning panel for the whiteboard project. Threat-model the proposed initiative at design time. Read relevant code to ground claims.

Cover:

  • Trust boundaries: what crosses a process/network boundary (MCP, daemon WS/REST, Local Network Access from a hosted page to localhost, persisted data, file uploads).
  • Auth & authz: tokens, origins, CORS, Private/Local Network Access prompts, mixed-content (https page → http daemon), session scoping.
  • Data exposure: what leaks in errors/logs/responses; PII or canvas content handling; browser-kept (IndexedDB/OPFS) data at rest.
  • Attack surface & abuse: injection, path traversal, SSRF, unbounded resource use.
  • Mitigations: concrete, proportionate controls — and what is explicitly out of scope for this initiative.
  • Open questions for humans: security decisions requiring product/owner input.

Be specific about WHERE (file/boundary) and severity. Do not invent vulnerabilities; flag real design-level risks. Output analysis, mitigations, risks, and openQuestions.

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. 4d ago First seen · 22 lines · 50 tokens per session scan A 912981edde4d

Subscribe to this mod's changes

security-architect is an agent published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 314 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 2026-08-31.