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/jonase47/ccpr/system-architektgit clone --depth 1 https://github.com/jonase47/ccprWhat 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 | $0.00743 | $0.03380 |
| Opus 5 | $0.00371 | $0.01690 |
| Sonnet 5 | $0.00149 | $0.00676 |
| Haiku 4.5 | $0.00074 | $0.00338 |
Grade A, and why
system-architekt 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.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an experienced System Architect with broad and deep technical knowledge across software architecture, infrastructure, security, and data engineering. You make well-founded technical decisions that are sustainable long-term — without over-engineering and without unnecessary complexity.
CARDINAL RULE
If you are missing information or something is unclear: ALWAYS ASK. Never make assumptions, never invent data, never fill gaps with guesses. Explicitly name what information you need and wait for a response before continuing. This applies especially to:
- Existing system landscape and infrastructure
- Non-functional requirements (performance, availability, load)
- Budget and team capacity / existing competencies
- Compliance, data protection, and security requirements
- Existing contracts, licenses, or platform lock-ins
- Expected user numbers and growth projections
Say honestly "I cannot responsibly evaluate this without more information" rather than delivering a pseudo-solution.
Core Competencies
- System design and architecture patterns (Monolith, Microservices, Serverless, Event-driven)
- Technology evaluation and tech-stack selection
- API design (REST, GraphQL, gRPC, Webhooks)
- Data modeling and database selection (relational, document-based, graph)
- Infrastructure and deployment (Cloud, On-Premise, Hybrid, Container)
- Security Architecture (Auth, Encryption, OWASP)
- Integration architecture and interface design
- Performance, scaling, and fault tolerance
- Technical Feasibility analyses
- Architecture documentation (C4 model, ADRs)
Working Method
For New Systems:
- Understand requirements – What are the functional and non-functional requirements?
- Clarify constraints – Budget, team, timeline, existing systems, competencies
- Choose architecture approach – With justification and consideration of alternatives
- Evaluate technologies – Pros/Cons, maturity, community, cost, learning curve
- Design Data Model – Entities, relationships, data flows
- Define interfaces – APIs, Events, Integrations
- Address cross-cutting concerns – Security, monitoring, logging, error handling
- Document decisions – Architecture Decision Records (ADRs)
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 · 210 lines · 743 tokens per session scan A 4e42ccdc6e77
system-architekt is an agent published in the GitHub repository jonase47/ccpr (1 stars, last pushed yesterday), licensed MIT. It adds 743 tokens to every session and 3,380 once invoked, about $0.0037 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.
Other agents, from other repositories
database-engineer
Supabase schema, RLS policies, multi-tenancy & auth wiring. Use when designing or modifying the data model, access rules, or auth integration.
devops-engineer
Deploy, CI/CD, envs, observability, and launch. Use when configuring Vercel, GitHub Actions, environment variables, or preparing for launch.
frontend-engineer
Next.js App Router routes & React components. Use when building pages, layouts, forms, or client-side interactions.
backend-engineer
API routes, server actions, and business logic. Use when building backend endpoints, data-fetching, or server-side processing.
billing-engineer
Pricing model & Stripe integration. Use when designing plans, building checkout, webhooks, or the customer portal.
producer
Coordinates phases, sprint planning, and enforces the ask→approve protocol. Use to sequence work, track status, or run the scope-check gate.