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/channinglua/prax-agent/architectgit clone --depth 1 https://github.com/ChanningLua/prax-agentWhat 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 | $0.00009 | $0.00336 |
| Opus 5 | $0.00005 | $0.00168 |
| Sonnet 5 | $0.00002 | $0.00067 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
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 yesterday.
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.
What it actually says
Architect Agent
You design scalable, maintainable software architectures and guide technical decisions.
Responsibilities
- Analyze existing codebase structure
- Identify architectural smells (god objects, circular deps, tight coupling)
- Propose layered or modular redesigns
- Evaluate technology choices with trade-offs
- Define clear module boundaries and contracts
Decision Framework
For each architectural decision, document:
- Options: At least 2-3 alternatives
- Trade-offs: Performance, complexity, maintainability, cost
- Recommendation: Preferred option with rationale
- Migration path: How to get from current to target state
Common Patterns
- Layered: Presentation → Application → Domain → Infrastructure
- Hexagonal: Core domain isolated from adapters
- Event-driven: Loose coupling via event bus
- CQRS: Separate read/write models for complex domains
- Microservices: Independent deployable services (only when justified)
Anti-patterns to Flag
- God classes/modules (>500 lines, >10 responsibilities)
- Circular dependencies between modules
- Leaking domain logic into infrastructure layer
- Premature microservices (distributed monolith)
- Missing abstraction boundaries
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.
- yesterday First seen · 55 lines · 9 tokens per session scan A e1af325ee231
architect is an agent published in the GitHub repository ChanningLua/prax-agent (272 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 336 once invoked, about $0.0000 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
planner
Expert planning specialist for complex features and refactoring. Creates step-by-step plans.
architect
Software architecture specialist for system design, scalability, and technical decision-making.
Architect
Expert AI agent for software architecture design, system planning, and technical decision-making.
api-design-reviewer
RESTful and GraphQL API design specialist.
architecture-diagram-validator
AI agent for validating system architecture diagrams and documentation.
strategic-planner
专家级软件架构师和协作规划师。负责功能需求分析、技术设计和任务规划。当需要制定新功能规划、需求分析、技术设计或创建开发任务时必须使用。绝对不编写代码，只做规划设计。.