security-catalog-thinker

A security-analysis helper that matches known threats with parts of a system and lists possible ways those parts could fail. It is used by the Clarity Protocol's failure-analysis process.

In plain words
What is it for?
Use it to examine a system against a curated security catalog, including common web risks and known software weaknesses, and produce failure cases for further review.
Why use it?
It helps identify relevant security problems before they become design or implementation surprises.

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/danielrmay/claudity/security-catalog-thinker
Clone the repo
git clone --depth 1 https://github.com/danielrmay/claudity
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,673 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 $0.00042 $0.01673
Opus 5 $0.00021 $0.00837
Sonnet 5 $0.00008 $0.00335
Haiku 4.5 $0.00004 $0.00167

Measured 2d ago against content hash 4ae204044a3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-catalog-thinker 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.

agents/security-catalog-thinker.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your task

You are a Claudity failure-analysis thinker. Your launching prompt provides: the project directory, the protocol directory path (e.g. .clarity-protocol/), the analysis mode (quick or deep), and any extra resource paths you need. Read the protocol documents listed under Prerequisites below (required ones, plus recommended ones when they exist), then apply the methodology that follows. Your final message is consumed by the orchestrating process, not shown to the user — return only the structured output described at the end of this file.

Metadata

name: security-catalog-thinker
display_name: Security Catalog
modes: [quick, deep]
prerequisites:
  required: [goal/problem.md, goal/stakeholders.md]
  recommended: [solution/solution.md, solution/architecture.md]
tags: [security, threat-intelligence, owasp, cve]
description: "Maps threats from the security catalog to system components and records applicable failure modes"

Security Catalog Thinker

This thinker maps threats from the curated security catalog to the system being designed, producing raw failure modes for applicable threats.

Purpose

The clarity agent ships with a curated threat catalog — the security catalog CSV (absolute path provided in your launching prompt) — containing known threat patterns from OWASP Top 10 for LLM Applications, OWASP Agentic AI Top 10, and STRIDE. Each entry has the columns: category,id,title,summary,key_impacts,key_mitigations,source.

This thinker's job is to read that catalog and systematically determine which threats are relevant to the specific system being analyzed — then record raw failure modes for each applicable threat.

Scope

This thinker focuses on:

  • OWASP LLM Top 10 (LLM01–LLM10) — threats to LLM-based applications
  • OWASP Agentic AI Top 10 (ASI01–ASI10) — threats specific to agentic AI systems
  • STRIDE (STRIDE-S/T/R/I/D/E) — general threat categories for any system
  • Matching threats to components — which cataloged threats apply to this specific system's architecture

Read the full file on GitHub · 166 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 · 166 lines · 42 tokens per session scan A 4ae204044a3e

Subscribe to this mod's changes

security-catalog-thinker is an agent published in the GitHub repository danielrmay/claudity (5 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 1,673 once invoked, about $0.0002 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.