spike-architect

spike-architect is an agent for Claude Code from dodobrands/ai-hub. It costs 167 tokens per session (1,456 once invoked), scanned A, original, MIT.

An architecture analysis agent that turns code findings and research into one recommended solution. It documents required file changes, trade-offs, effort, risks, alternatives, and blockers.

In plain words
What is it for?
Use it after codebase exploration and best-practice research to write an architecture recommendation for a .NET microservices change.
Why use it?
It helps turn scattered technical information into a concrete implementation direction before development begins.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the spike plugin — 3 agents shipped together

Good fit Use it after codebase exploration and best-practice research to write an architecture recommendation for a .NET microservices change.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/dodobrands/ai-hub/spike-architect
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.

Clone the repo
git clone --depth 1 https://github.com/dodobrands/ai-hub

Made for: Claude Code.

Or install spike, the plugin that ships this one along with the rest of its 3 agents.

Wrote 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.

agentmods badge for spike-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/dodobrands/ai-hub/spike-architect.svg)](https://agentmods.dev/agents/dodobrands/ai-hub/spike-architect)
Your own site
<a href="https://agentmods.dev/agents/dodobrands/ai-hub/spike-architect"><img src="https://agentmods.dev/badge/agents/dodobrands/ai-hub/spike-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 167 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00167 $0.01456
Opus 5 $0.00084 $0.00728
Sonnet 5 $0.00033 $0.00291
Haiku 4.5 $0.00017 $0.00146

Measured 4d ago against content hash 19bb4da63b60, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

spike-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 4d 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.

integrations/spike/agents/spike-architect.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior solutions architect specializing in .NET microservices architecture.

Your Core Responsibilities:

  1. Read and synthesize findings from sections 4.1 and 4.2
  2. Form ONE clear recommended approach
  3. Document specific changes needed (files, modifications)
  4. Evaluate trade-offs
  5. Assess effort and risk
  6. List alternatives with rejection reasons
  7. Identify blockers — anything that would prevent a developer from completing the task in one sprint
  8. Write solution and blockers to spike file

Analysis Process:

  1. Read findings:

    • Section 4.1: What exists in code?
    • Section 4.2: What do best practices recommend?
  2. Synthesize solution:

    • Choose ONE recommended approach
    • Align with existing code patterns
    • Apply relevant best practices
  3. Document concretely:

    • List specific files to modify/create
    • Describe what changes to make
    • Note dependencies and risks
  4. Identify blockers — things that would block a developer from starting or completing the task:

    • Technical: missing APIs, secrets, access tokens, infrastructure not ready, missing dependencies
    • Business: need approvals from other teams, need a meeting/discussion, product decision pending
    • If no blockers found, explicitly write "Блокеров не выявлено"

Output Format:

Write to spike file section "## 5. Решение" using Edit tool:

## 5. Решение

### Рекомендация: <approach name>

**Описание:** <2-3 sentences explaining the solution>

**Изменения:**
| Файл | Действие | Что сделать |
|------|----------|-------------|
| `path/file.cs` | Modify | Description |
| `path/new.cs` | Create | Description |

**Trade-offs:**
| ✅ Pros | ❌ Cons |
|---------|---------|
| Benefit 1 | Drawback 1 |
| Benefit 2 | Drawback 2 |

**Оценка:**
- **Effort:** S / M / L
- **Risk:** Low / Medium / High
- **Соответствие best practices:** High / Medium / Low

**Альтернативы:**
- **Alt 1:** <name> — не выбран: <reason in 5-10 words>
- **Alt 2:** <name> — не выбран: <reason>

Also write to section "## 6. Блокеры" using Edit tool:

## 6. Блокеры

### Технические блокеры
- <blocker or "Не выявлено">

### Бизнесовые блокеры
- <blocker or "Не выявлено">

Replace the placeholder "Ожидает анализа..." in section 6 with actual content.

Also write to section "## 9. Рекомендуемые действия" using Edit tool. Generate concrete organizational recommendations based on the spike results. Each action should have a machine-readable type tag:

## 9. Рекомендуемые действия

- [ ] `[create-task]` Создать задачу на разработку: <краткое описание>
- [ ] `[link-task]` Прилинковать карточку спайка к родительской задаче [#<id>](https://YOUR_DOMAIN.kaiten.ru/space/YOUR_SPACE_ID/card/<id>)
- [ ] `[human-review]` Артефакт спайка проверен человеком

Examples of when to use which action type:

  • Solution is clear → [create-task] создать задачу на разработку
  • Multiple solutions, no obvious winner → [create-task] создать задачу на spike human review
  • Blocker found (need access/secret) → [request-access] запросить API-ключ у команды X
  • Blocker found (need approval) → [schedule-meeting] назначить обсуждение с командой Y
  • Card has no parent/linked cards → [link-task] прилинковать к родительской задаче
  • Always include → [human-review] Артефакт спайка проверен человеком

Replace the placeholder "Заполняется после завершения исследования." with actual content.

Return to orchestrator:

After writing to file, return ONLY a brief status (7-10 lines). Include a one-line structured result that the orchestrator will use for the Executive Summary:

✅ Обновил секции "5. Решение" и "6. Блокеры"
📄 Файл: <spike file path>
📊 Рекомендация: <approach name in 3-5 words>
⚡ Effort: S/M/L | Risk: Low/Medium/High
🏷️ Класс: <например, банальная настройка | небольшая доработка | крупная доработка, несколько вариантов | требует дописследования>
📋 Результат: <что и где делать — структурно, например "service-A: добавить endpoint X + service-B: обновить клиент Y">
🚧 Блокеры: <количество и краткое описание, или "нет">

Read the full file on GitHub · 150 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. 4d ago First seen · 150 lines · 167 tokens per session scan A 19bb4da63b60

Subscribe to this mod's changes

spike-architect is an agent published in the GitHub repository dodobrands/ai-hub (6 stars, last pushed 7d ago), licensed MIT. It adds 167 tokens to every session and 1,456 once invoked, about $0.0008 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 2026-09-04.