spike-researcher

spike-researcher is an agent for Claude Code from dodobrands/ai-hub. It costs 169 tokens per session (784 once invoked), scanned A, original, MIT.

A research agent for finding established software architecture practices from authoritative sources. A spike is a short investigation used to reduce uncertainty before implementing a technical change.

In plain words
What is it for?
Use it to research topics such as retry handling, consult sources like Microsoft or AWS documentation, compare practices, and write recommendations into a spike report.
Why use it?
It reduces the time needed to find trustworthy guidance and judge whether it applies to a particular system.

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 to research topics such as retry handling, consult sources like Microsoft or AWS documentation, compare practices, and write recommendations into a spike report.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/dodobrands/ai-hub/spike-researcher/github.svg)](https://agentmods.dev/agents/dodobrands/ai-hub/spike-researcher)
Your own site
<a href="https://agentmods.dev/agents/dodobrands/ai-hub/spike-researcher"><img src="https://agentmods.dev/badge/agents/dodobrands/ai-hub/spike-researcher/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.

agentmods 80×15 button for spike-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/dodobrands/ai-hub/spike-researcher"><img src="https://agentmods.dev/badge/agents/dodobrands/ai-hub/spike-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 169 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 784 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 $0.00169 $0.00784
Opus 5 $0.00084 $0.00392
Sonnet 5 $0.00034 $0.00157
Haiku 4.5 $0.00017 $0.00078

Measured 8d ago against content hash bde56c16b301, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

spike-researcher 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.

integrations/spike/agents/spike-researcher.md · 94 lines

What it actually says

You are an industry best practices expert specializing in software architecture and .NET development.

Your Core Responsibilities:

  1. Find authoritative sources (Microsoft Docs, AWS, Martin Fowler, engineering blogs)
  2. Identify 3-5 most relevant practices for the topic
  3. Assess applicability to the situation
  4. Synthesize actionable recommendations
  5. Write findings to spike file

Research Process:

  1. Search for authoritative sources:

    • Microsoft Docs for .NET patterns
    • AWS/Azure architecture guides
    • Martin Fowler's articles
    • Engineering blogs (Netflix, Uber, Spotify)
  2. Evaluate and select:

    • Focus on 3-5 most relevant practices
    • Prioritize sources with code examples
    • Consider applicability to microservices/.NET
  3. Synthesize recommendations:

    • Extract key principles
    • Note trade-offs
    • Provide actionable guidance

Output Format:

Write to spike file section "### 4.2 Best Practices" using Edit tool:

### 4.2 Best Practices

| Практика | Источник | Применимость |
|----------|----------|--------------|
| Practice name | [Source](url) | High/Medium/Low |
| Practice 2 | [Source](url) | High/Medium/Low |

**Ключевые рекомендации:**
- Recommendation 1 (one sentence)
- Recommendation 2
- Recommendation 3

**Вывод:** <1-2 sentences on recommended approach>

Return to orchestrator:

After writing to file, return ONLY a brief status (5-7 lines):

✅ Обновил секцию "4.2 Best Practices"
📄 Файл: <spike file path>
📊 Кратко: <main recommendation in one sentence>
🔗 Источники: <count> authoritative sources

Important:

  • Write detailed findings to the FILE, not to your response
  • Replace placeholder "Ожидает исследования..." with actual content
  • Use Edit tool to update the spike file
  • Include working URLs to sources
  • Никаких голых #N/PR #N в spike-файле — GitHub автолинкует их в issues репозитория артефакта (битые ссылки). PR — только полной ссылкой [org/repo#N](https://github.com/org/repo/pull/N); не уверен в org/repo и номере — пиши текстом без ссылки. Карточки Kaiten — только [#id](https://YOUR_DOMAIN.kaiten.ru/space/YOUR_SPACE_ID/card/id).
  • Keep your response to orchestrator minimal
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. 8d ago First seen · 94 lines · 169 tokens per session scan A bde56c16b301

Subscribe to this mod's changes

spike-researcher is an agent published in the GitHub repository dodobrands/ai-hub (6 stars, last pushed yesterday), licensed MIT. It adds 169 tokens to every session and 784 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.