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.
npx agentmods add skills/craftos-dev/craftbot/research-assistantnpx skills add CraftOS-dev/CraftBot --skill research-assistantgit clone --depth 1 https://github.com/CraftOS-dev/CraftBotWrote 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/skills/craftos-dev/craftbot/research-assistant)<a href="https://agentmods.dev/skills/craftos-dev/craftbot/research-assistant"><img src="https://agentmods.dev/badge/skills/craftos-dev/craftbot/research-assistant.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 | $0.00030 | $0.00562 |
| Opus 5 | $0.00015 | $0.00281 |
| Sonnet 5 | $0.00006 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
research-assistant 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Assistant
Help users research topics by gathering information, analyzing sources, and providing clear summaries.
When to Use
- User wants to learn about a topic
- Comparing products, services, or options
- Gathering background information
- Fact-checking or verifying claims
- Understanding complex subjects
Research Process
Step 1: Clarify the Research Scope
Before starting, understand:
- What specific question needs answering?
- What depth is needed? (quick overview vs. deep dive)
- Any particular sources to prioritize or avoid?
- What format does the user want results in?
Step 2: Gather Information
- Search multiple sources - Use web search to find relevant information
- Verify credibility - Prioritize authoritative sources
- Note key facts - Record important findings with source references
- Identify patterns - Look for consensus and disagreements
Step 3: Analyze and Synthesize
- Cross-reference information across sources
- Identify the most reliable and relevant facts
- Note any conflicting information
- Distinguish between facts and opinions
Step 4: Present Findings
Structure the research summary as:
## Research Summary: [Topic]
### Key Findings
- [Main point 1]
- [Main point 2]
- [Main point 3]
### Detailed Analysis
[Organized breakdown of findings by subtopic]
### Sources
- [Source 1 with link]
- [Source 2 with link]
### Limitations
[Any gaps in research or uncertain areas]
### Recommendations
[Next steps or additional areas to explore]
Research Quality Guidelines
- Be thorough but focused - Cover the topic well without going off-track
- Cite sources - Always provide where information came from
- Acknowledge uncertainty - Be clear when information is unclear or conflicting
- Stay neutral - Present facts objectively, note biases in sources
- Summarize clearly - Make complex information accessible
Output Depth Levels
Quick Overview (2-3 minutes)
- Key facts only
- 3-5 bullet points
- Top 2-3 sources
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.
- 2d ago First seen · 97 lines · 30 tokens per session scan A c68aeedf4fb6
research-assistant is a skill published in the GitHub repository CraftOS-dev/CraftBot (380 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 562 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 2026-09-03.
Other skills, from other repositories
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
habit-formation
Atomic habits, cue-routine-reward loops, habit stacking, accountability systems, and behavior change.
trading-manual-writer
为"全品种操盘手册"系列撰写单个章节/小节。面向投资小白和散户，每次写一小节。输入小节标题和参考信息，输出图文并茂（含SVG插图）的Markdown文件，保存到项目markdown/目录。触发条件：用户提到"写操盘手册"、"写一节"、"写章节"、"散户操盘"、"金融工具讲解"、"写投资小白教程"、"帮我写操盘手册的XX章节"，或提供了一个金融品种/操盘主题名称并希望生成教学内容。即使用户只说"帮我写黄金操盘那一章"或"可转债怎么讲给小白听"，也应使用本skill。.
aiwg-help
Display all available AIWG CLI commands, their arguments, and usage examples.
paperlab_instructor_resource_pack
Build instructor resources from PaperLab books: lecture outlines, slide plans, question banks, solution manuals, rubrics, labs, and exam variants.