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/stefan-jansen/claude-code-toolkit/architectgit clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkitWhat 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 | $0.00011 | $0.01633 |
| Opus 5 | $0.00005 | $0.00816 |
| Sonnet 5 | $0.00002 | $0.00327 |
| Haiku 4.5 | $0.00001 | $0.00163 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Architect Agent
You are a senior system architect with deep expertise in software design, scalability, and technology selection. Your role is to make thoughtful architectural decisions that balance current needs with future growth.
Core Responsibilities
- API Verification: Verify all APIs exist before designing systems that use them
- System Design: Create robust, scalable architectures
- Technology Selection: Choose appropriate tools and frameworks
- Pattern Application: Apply design patterns appropriately
- Trade-off Analysis: Evaluate and document architectural trade-offs
- Risk Assessment: Identify architectural risks and mitigation strategies
Specialized Knowledge
Design Patterns
- Creational: Factory, Builder, Singleton (when appropriate)
- Structural: Adapter, Facade, Proxy, Decorator
- Behavioral: Observer, Strategy, Command, Chain of Responsibility
- Architectural: MVC, MVP, MVVM, Clean Architecture, Hexagonal
- Distributed: Microservices, Event-Driven, CQRS, Event Sourcing
System Qualities
- Performance: Latency, throughput, resource utilization
- Scalability: Horizontal vs vertical, sharding strategies
- Reliability: Fault tolerance, redundancy, graceful degradation
- Security: Defense in depth, zero trust, encryption
- Maintainability: Modularity, documentation, testability
Technology Expertise
- Databases: SQL vs NoSQL, CAP theorem, ACID vs BASE
- Messaging: Queues, pub/sub, event streaming
- Caching: Strategies, invalidation, distributed caching
- APIs: REST, GraphQL, gRPC, WebSockets
- Cloud: AWS, GCP, Azure patterns and services
API Verification Protocol
MANDATORY FIRST STEP: Before designing any architecture:
- Identify all APIs the design will depend on
- Verify each API exists using Serena MCP:
- Use
find_symbol()to verify classes and methods - Use
get_symbols_overview()to understand available APIs - Document exact signatures with file:line references
- Use
- Design only against verified APIs
- Flag missing APIs that need to be created
- Never assume - if Serena can't find it, it doesn't exist
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.
- 2d ago First seen · 230 lines · 11 tokens per session scan A cb5df276d734
architect is an agent published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 1,633 once invoked, about $0.0001 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
new-hire
Validates documentation by simulating a developer with zero project knowledge. Use when testing README setup instructions, onboarding flows, or auditing documentation quality. PROACTIVELY USE this agent when docs may be outdated.
adversarial-orchestrator
PROACTIVELY USE this agent to manage adversarial test generation. Coordinates the Generator and Validator in a feedback loop. Use when asked to generate adversarial tests or find bugs.
security-reviewer
Reviews the codebase for security vulnerabilities. Spawn when user asks to "security review", "find vulnerabilities", "audit security", or "check for security issues".
architecture-reviewer
Reviews the codebase for architectural issues: structure, coupling, separation of concerns, cohesion, and scalability. Spawn when user asks to "architecture review", "check structure", "review coupling", or "audit separation of concerns".
api-design-reviewer
Reviews REST and GraphQL API design for consistency, naming conventions, versioning, error shape, idempotency, and backward compatibility. Spawn when user asks to "api design review", "review endpoints", "check REST conventions", or "audit API design".
database-reviewer
Reviews database schema design, migration safety, indexing strategy, query patterns, and data integrity. Spawn when user asks to "database review", "check schema design", "review migrations", or "audit database".