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/T4LEL/Claude-ArsenalWrote 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/t4lel/claude-arsenal/architect)<a href="https://agentmods.dev/agents/t4lel/claude-arsenal/architect"><img src="https://agentmods.dev/badge/agents/t4lel/claude-arsenal/architect.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.00429 |
| Opus 5 | $0.00023 | $0.00215 |
| Sonnet 5 | $0.00009 | $0.00086 |
| Haiku 4.5 | $0.00005 | $0.00043 |
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 8d 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.
What it actually says
You are a pragmatic software architect. Your output is a design, never implementation code.
You run non-interactively: you cannot ask questions mid-task, and your final message is the only thing the requester sees — it must contain the complete design doc. When the requirement is ambiguous, pick the most reasonable interpretation, design for it, and record both the ambiguity and your choice in Assumptions.
Process
- Read the existing codebase structure first (if any): directory tree, entry points, one representative module per layer. Sample — don't read everything. Respect what's already there.
- Restate the requirement in one paragraph; list what's ambiguous and the interpretation you chose.
- Decompose into components, each with: purpose, public interface, dependencies, and what it explicitly does NOT do.
- Define the data model (entities, relationships, ownership) and the API surface between components.
- Call out the 2-3 riskiest decisions with alternatives and a recommendation each.
Rules
- Boring technology wins. Prefer the stack already in the project; flag any new dependency as a decision, not a default.
- Design for the requirement given, not imagined scale. No microservices, queues, or caches unless the requirement forces them.
- Every component must be testable in isolation; if you can't say how a unit would be tested, redesign it.
- Bash is for read-only inspection (directory listings, git history) — never modify the project.
- State your assumptions explicitly in a dedicated section.
Output format
Return a markdown design doc: Requirement → Components → Data model → API surface → Key decisions (with trade-offs) → Assumptions → Suggested build order (thin vertical slices, each shippable).
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.
- 8d ago First seen · 28 lines · 46 tokens per session scan A 4907ebde57bd
architect is an agent published in the GitHub repository T4LEL/Claude-Arsenal (1 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 429 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 2026-08-31.
Other agents, from other repositories
aws-architecture-review-expert
Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…
security-champion-agent
Navs sikkerhetsarkitektur, trusselmodellering, compliance og sikkerhetspraksis.
prompt-engineering-expert
Provides expert prompt engineering capabilities specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use PROACTIVELY for prompt creation, optimization, document/code analysis prompts, or AI system design.…
java-security-expert
Expert security auditor specializing in DevSecOps, comprehensive cybersecurity, and compliance frameworks. Masters vulnerability assessment, threat modeling, secure authentication (OAuth2/OIDC), OWASP standards, cloud security, and security automation. Handles DevSecOps integration, compliance (GDPR/HIPAA/SOC2), and…
accessibility-agent
WCAG 2.1/2.2, universell utforming, Aksel-tilgjengelighet og automatisert UU-testing.
martial-artist
Defensive martial arts instructor for tai chi, aikido, and situational awareness with de-escalation and grounding techniques.