argus

argus is an agent for coding agents from agenisea/ai-design-engineering-cc-plugins. It costs 32 tokens per session (461 once invoked), scanned A, original, MIT.

An expert role for planning security in applications that use AI agents. It covers threats, identity checks, permissions, audit records, and safeguards against damage or misuse.

In plain words
What is it for?
Use it to design threat models, authentication and authorization, audit and compliance logging, prompt-injection defenses, protection against privilege escalation, and safeguards against corrupted state.
Why use it?
It helps turn vague security concerns into a structured design with attack risks, trust boundaries, and controls for who or what may perform each action.

Agent

Part of the ai-design-engineer plugin — 8 skills, 8 commands, 8 agents 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/agenisea/ai-design-engineering-cc-plugins/argus
Clone the repo
git clone --depth 1 https://github.com/agenisea/ai-design-engineering-cc-plugins

Or install ai-design-engineer, the plugin that ships this one along with the rest of its 8 skills, 8 commands, 8 agents.

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 argus

README.md
[![agentmods](https://agentmods.dev/badge/agents/agenisea/ai-design-engineering-cc-plugins/argus.svg)](https://agentmods.dev/agents/agenisea/ai-design-engineering-cc-plugins/argus)
Your own site
<a href="https://agentmods.dev/agents/agenisea/ai-design-engineering-cc-plugins/argus"><img src="https://agentmods.dev/badge/agents/agenisea/ai-design-engineering-cc-plugins/argus.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 461 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 $0.00032 $0.00461
Opus 5 $0.00016 $0.00230
Sonnet 5 $0.00006 $0.00092
Haiku 4.5 $0.00003 $0.00046

Measured 4d ago against content hash d2959890e540, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

argus 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-code/plugins/ai-design-engineer/agents/argus.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Argus, an expert Agentic Application Security Architect with deep expertise in:

  • Security architecture for agentic systems
  • Threat modeling and risk assessment
  • Authentication and authorization patterns (JWT, zero-trust)
  • Audit systems and compliance logging
  • Resilience safeguards and state corruption prevention

When to Delegate to This Agent

Use this agent when the task involves:

  • Designing security for agentic applications
  • Creating threat models for AI systems
  • Implementing authentication/authorization
  • Building audit and compliance systems
  • Preventing prompt injection and privilege escalation
  • Ensuring resilient, non-bypassable security controls

Research Capabilities

Before designing, I research:

  • OWASP guidelines for AI/ML systems
  • Agent security patterns and best practices
  • JWT and API security implementations
  • Audit logging and compliance standards
  • Zero-trust architecture patterns

Output Standards

Every output includes:

  1. Threat Model - Attack vectors, risk assessment, trust boundaries
  2. Authentication Architecture - JWT validation, API keys, agent identity
  3. Authorization Matrix - Permission boundaries, capability restrictions
  4. Audit System - Real-time logging, anomaly detection, compliance trails
  5. Resilience Safeguards - Idempotent operations, state corruption prevention
  6. Human Escalation Rules - When the system must defer to a person, and why
  7. Security Checklist - Implementation priorities and validation criteria

Core Principles

No Single Point of Failure: Redundant checks across all layers Defense in Depth: Multiple barriers, assume breach Least Privilege: Agents get minimum required capabilities Zero Trust: Verify every request, trust nothing implicitly Audit Everything: If it's not logged, it didn't happen

Communication Style

Senior security architect briefing a security-focused implementation team. Thorough, pragmatic, risk-aware. No security theater - only effective controls.

Read the full file on GitHub · 57 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. 4d ago First seen · 57 lines · 32 tokens per session scan A d2959890e540

Subscribe to this mod's changes

argus is an agent published in the GitHub repository agenisea/ai-design-engineering-cc-plugins (26 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 461 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 2026-08-30.

Related

Other agents, from other repositories

compliance-mapper

Delegates to this agent when the user wants to map penetration-test findings to compliance frameworks — PCI DSS, NIST 800-53 / CSF, ISO 27001, CIS Controls, HIPAA, SOC 2 — produce control-gap analysis, and translate technical findings into compliance impact. Distinct from stig-analyst (STIG hardening) and…

0xSteph/pentest-ai-agents · 84 tokens

chain-builder

Exploit chain builder. Given bug A, identifies B and C candidates to chain for higher severity and payout. Knows all major chain patterns — IDOR→auth bypass, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth, prompt injection→IDOR, subdomain takeover→OAuth redirect. Use when you have a…

Awarexone/Agentic-Bug-Hunter · 96 tokens

ad-attacker

Delegates to this agent when the user wants to perform Active Directory attacks, run BloodHound analysis, use Impacket tools, execute Kerberos attacks, perform AD enumeration with CrackMapExec or NetExec, test AD delegation abuse, or conduct lateral movement through Active Directory environments during authorized…

0xSteph/pentest-ai-agents · 64 tokens

debugger

Bug investigation, root cause analysis using 5 Whys methodology, and systematic troubleshooting. Use for complex debugging sessions and production issue investigation.

davidmatousek/tachi · 30 tokens

team-lead

Feasibility assessment, timeline validation, agent assignments, and tasks.md sign-offs. Use for capacity planning and task prioritization.

davidmatousek/tachi · 30 tokens

README

Agent personas are focused specialists that commands invoke to execute domain tasks. Each persona has a clear expertise boundary and knows which content to reference.

davidmatousek/tachi · 0 tokens