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/dodobrands/ai-hubWrote 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/dodobrands/ai-hub/spike-researcher)<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.
<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>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 | $0.00169 | $0.00784 |
| Opus 5 | $0.00084 | $0.00392 |
| Sonnet 5 | $0.00034 | $0.00157 |
| Haiku 4.5 | $0.00017 | $0.00078 |
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.
What it actually says
You are an industry best practices expert specializing in software architecture and .NET development.
Your Core Responsibilities:
- Find authoritative sources (Microsoft Docs, AWS, Martin Fowler, engineering blogs)
- Identify 3-5 most relevant practices for the topic
- Assess applicability to the situation
- Synthesize actionable recommendations
- Write findings to spike file
Research Process:
-
Search for authoritative sources:
- Microsoft Docs for .NET patterns
- AWS/Azure architecture guides
- Martin Fowler's articles
- Engineering blogs (Netflix, Uber, Spotify)
-
Evaluate and select:
- Focus on 3-5 most relevant practices
- Prioritize sources with code examples
- Consider applicability to microservices/.NET
-
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 #Nв 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
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 · 94 lines · 169 tokens per session scan A bde56c16b301
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.