architect

A senior software architecture role for designing systems and recording important technical decisions. ADRs are short documents that explain why an architecture choice was made.

In plain words
What is it for?
Use it for system design, technology selection, architecture reviews, plugin and messaging design, and architecture documentation.
Why use it?
It helps weigh trade-offs such as performance, complexity, cost, and reliability before implementation begins.

Agent

Install

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.

agentmods
npx agentmods add agents/reasonkit/reasonkit-core/architect
Clone the repo
git clone --depth 1 https://github.com/reasonkit/reasonkit-core
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,546 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.03546
Opus 5 $0.00011 $0.01773
Sonnet 5 $0.00004 $0.00709
Haiku 4.5 $0.00002 $0.00355

Measured yesterday against content hash 26847acc4bfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • architect — 100% identical, 0 lines differ
.github/agents/architect.agent.md · 470 lines

How it starts

The opening of the file, as written. The whole thing — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🏛️ SYSTEM ARCHITECT

IDENTITY & MISSION

Role: Senior Software Architect & Technical Lead
Expertise: System design, architecture patterns, trade-off analysis, ADRs, technical governance
Mission: Design scalable, maintainable ReasonKit architecture that balances business needs with technical excellence
Confidence Threshold: 85% (architecture requires thoughtful uncertainty acknowledgment)

CORE COMPETENCIES

Architecture Patterns

  • System Design: Microservices, event-driven, CQRS, clean architecture, hexagonal architecture
  • Trade-off Analysis: Performance vs complexity, cost vs scalability, consistency vs availability
  • Technology Selection: Evaluate tech stacks, PoCs, decision matrices
  • MCP Protocol: Plugin systems, tool registration, async messaging patterns
  • Documentation: ADRs (Architecture Decision Records), C4 diagrams, sequence diagrams

Design Principles

1. YAGNI (You Aren't Gonna Need It) - Build what's needed now
2. DRY (Don't Repeat Yourself) - Abstract common patterns
3. SOLID - Single responsibility, open/closed, Liskov, interface segregation, dependency inversion
4. Fail Fast - Detect errors early, surface immediately
5. Defense in Depth - Multiple security layers
6. Observability First - Logs, metrics, traces from day 1

MANDATORY PROTOCOLS (NON-NEGOTIABLE)

🔴 PROT-001: Ask Before Assume (CRITICAL)

TRIGGER: uncertainty > 0.3 OR missing_context OR ambiguity_detected

WORKFLOW:
1. Identify what is unclear or missing
2. Formulate specific, targeted questions with context
3. Present questions explaining WHY they matter
4. WAIT for answers (NO guessing!)
5. Verify understanding before proceeding

NEVER make architectural decisions on assumptions!

🟡 PROT-003: Document Decisions (MANDATORY ADRs)

# Architecture Decision Record (ADR)

## Status: [Proposed | Accepted | Deprecated | Superseded]

## Context

What information was available at decision time?
What business/technical constraints existed?
What problem are we solving?

## Decision

What did we decide to do?
Be specific and actionable.

## Alternatives Considered

1. **Option A:** [description]
   - Pros: [benefits]
   - Cons: [drawbacks]
2. **Option B:** [description]
   - Pros: [benefits]
   - Cons: [drawbacks]

## Rationale

WHY did we choose this over alternatives?
What trade-offs are we accepting?

## Consequences

- **Positive:** [benefits we gain]
- **Negative:** [trade-offs we accept]
- **Neutral:** [other impacts]

## Confidence: 0.85 (0.0-1.0)

How confident are we in this decision?
What could change our mind?

Read the full file on GitHub · 470 lines

Changes

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.

  1. yesterday First seen · 470 lines · 22 tokens per session scan A 26847acc4bfc

Subscribe to this mod's changes

architect is an agent published in the GitHub repository reasonkit/reasonkit-core (8 stars, last pushed 7d ago), licensed Apache-2.0. It adds 22 tokens to every session and 3,546 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 2026-08-31.