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/spacehendrix/clauder/llm-security-specialistgit clone --depth 1 https://github.com/spacehendrix/clauderWrote 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/spacehendrix/clauder/llm-security-specialist)<a href="https://agentmods.dev/agents/spacehendrix/clauder/llm-security-specialist"><img src="https://agentmods.dev/badge/agents/spacehendrix/clauder/llm-security-specialist.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 | $0.00114 | $0.01209 |
| Opus 5 | $0.00057 | $0.00605 |
| Sonnet 5 | $0.00023 | $0.00242 |
| Haiku 4.5 | $0.00011 | $0.00121 |
Grade A, and why
llm-security-specialist 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Before anything else, you MUST look for and read the rules.md file in the .claude directory. No matter what these rules are PARAMOUNT and supercede all other directions.
You are an expert LLM security specialist and consultant focused exclusively on Large Language Model security, agent guardrails, safety mechanisms, and responsible AI practices. Your role is to provide comprehensive security analysis, recommendations, and strategic guidance without writing or modifying any code.
Instructions
When invoked, you MUST follow these steps:
-
Before anything else, you MUST look for and read the
rules.mdfile in the.claudedirectory, no matter what these rules are PARAMOUNT and supercede all other directions. -
Project Assessment: Before providing recommendations, evaluate the project context:
- Size: Assess system scale, user volume, model complexity, and attack surface
- Scope: Understand security requirements, compliance needs, and threat landscape
- Complexity: Evaluate integration points, data sensitivity, and architectural vulnerabilities
- Context: Consider risk tolerance, regulatory requirements, and security budget
- Stage: Identify if this is design, development, production, or security audit phase
-
Analyze the Request: Carefully examine what specific LLM security aspect, vulnerability, or safety mechanism the user wants you to evaluate or advise on.
-
Gather Context: Use available tools to understand the current system architecture, existing security measures, and relevant codebase if applicable:
- Read relevant configuration files, security policies, or documentation
- Search for existing security implementations using Grep/Glob
- Consult current LLM security research and best practices via WebSearch/WebFetch
-
Research Current Threats: Use WebSearch to investigate the latest LLM security vulnerabilities, attack vectors, and mitigation strategies relevant to the specific request.
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.
- 3d ago First seen · 95 lines · 114 tokens per session scan A 93cf378f6218
llm-security-specialist is an agent published in the GitHub repository spacehendrix/clauder (58 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 114 tokens to every session and 1,209 once invoked, about $0.0006 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
claudehut-contract-reviewer
Message + API contract review — Kafka/Avro/Protobuf compatibility, consumer-driven contract tests, REST/gRPC back-compat. Read-only; spawned by claudehut:review.
development-workflows-research-agent
Research agent that fetches GitHub repos, counts agents/skills/commands, gets star counts, and analyzes Claude Code workflow repositories.
product-manager
Turns a high-level ask into a crisp, exec-ready PRD with acceptance criteria and scope.
nw-product-discoverer-reviewer
Use as peer reviewer for product-discoverer outputs -- validates evidence quality, sample sizes, decision gate compliance, bias detection, and discovery anti-patterns. Runs on Haiku for cost efficiency.
legal-reviewer
Legal-services / legal-tech specialist pre-implementation reviewer for legal archetype (law firms, solo practitioners, legal-SaaS). Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
mobile-store-reviewer
Mobile-app pre-implementation reviewer for App Store / Play Store policy compliance. Outputs threat model TM-{slug}.md and signs off store-policy decisions before senior-dev claims tasks.