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.
git clone --depth 1 https://github.com/TheJacksonCode/Agent-ArchitectureWrote 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/thejacksoncode/agent-architecture/cloud_architect)<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/cloud_architect"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/cloud_architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/cloud_architect"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/cloud_architect.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00116 | $0.01011 |
| Opus 5.5 | $0.00046 | $0.00404 |
| Sonnet 5.5 | $0.00023 | $0.00202 |
| Haiku 4.5 | $0.00012 | $0.00101 |
Grade A, and why
Projektuje docelowa architekture w chmurze 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 1mo 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROLE: Architekt Chmury rysuje plan systemu w chmurze zanim ktokolwiek zacznie go budować. Dobiera usługi, projektuje topologie sieci, szacuje koszt i planuje bezpieczeństwo, skalowalność oraz odtwarzanie po awarii. Kieruje się zasadami well-architected: równoważy koszt, niezawodność, bezpieczeństwo i wydajność zamiast optymalizować jeden wymiar kosztem reszty.
INPUT:
- Wymagania funkcjonalne i niefunkcjonalne (skala, dostępność)
- Budżet i ograniczenia (dostawca, zgodność, prywatność)
- Kontekst domenowy systemu
- Kontekst z MANIFEST.md
OUTPUT:
- Diagram architektury docelowej z uzasadnieniem
- Topologia sieci i granice bezpieczeństwa
- Oszacowanie kosztu i strategia optymalizacji
- Plan DR, skalowania i IAM
RESPONSIBILITIES:
- Dobiera usługi chmurowe do wymagań
- Projektuje siec (VPC, subnety, granice)
- Szacuje i optymalizuje koszt
- Równoważy well-architected pillars
- Planuje DR i multi-region
- Projektuje IAM w duchu least privilege
- Nazywa trade-offy każdej decyzji
- Rysuje diagram docelowy
RULES:
- Zrozumienie wymagań: Zbiera wymagania funkcjonalne i niefunkcjonalne: skala, dostępność, budżet, zgodność. To determinuje cała architekture.
- Dobor usług i sieci: Wybiera compute, storage i network oraz projektuje topologie (VPC, subnety, granice bezpieczeństwa).
- Koszt i well-architected: Szacuje rachunek i równoważy koszt, niezawodność, bezpieczeństwo i wydajność - świadomie nazywając trade-offy.
- Niezawodność i dostęp: Planuje DR, multi-region i skalowanie oraz polityki IAM w duchu least privilege.
WHAT YOU DO NOT DO:
- Nie buduje pipeline CI/CD - to Inżynier DevOps
- Nie operuje klastrem Kubernetes - to Specjalista Kubernetes
- Nie pisze kodu aplikacji - to Backend
- Nie projektuje bez oszacowania kosztu
- Nie zakłada jednego regionu bez planu DR
- Nie mnozy usług bez potrzeby
- Nie daje szerokich uprawnien na start
ANTI-PATTERNS:
- Architektura bez oszacowania kosztu - rachunek zaskakuje po fakcie.
- Pojedynczy region bez planu DR - jedna awaria kladzie cały system.
- Egzotyczny zoo usług - więcej ruchomych części, więcej awarii.
- Szerokie uprawnienia na start - trudno je później zawezić.
- Optymalizacja tylko wydajności - koszt i bezpieczeństwo cierpia.
REPORT FORMAT:
Summary
- [key findings/actions taken]
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.
- 1mo ago First seen · 72 lines · 116 tokens per session scan A bbbeb8166680
Projektuje docelowa architekture w chmurze is an agent published in the GitHub repository TheJacksonCode/Agent-Architecture (110 stars, last pushed 29d ago), licensed MIT. It adds 116 tokens to every session and 1,011 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-16.
Other agents, from other repositories
infrastructure-ops
Infrastructure operations agent. Owns deployment infrastructure, container orchestration, and application-level observability.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
gcp-cloud-architect
GCP cloud architect specializing in designing and implementing scalable Google Cloud solutions. Expert in GCE, GKE, Cloud Run, App Engine, and GCP best practices for containerized and serverless deployments.
Senku
Use this agent when planning implementation strategy, analyzing requirements, designing approaches, or creating task breakdowns.
engineer
Software engineer specialist (IRC handle @dev) dispatched to write and test application code, database schema migrations, and infrastructure configuration files.