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/fuyuxiang/echo-agent/deep-researchnpx skills add fuyuxiang/echo-agent --skill deep-researchgit clone --depth 1 https://github.com/fuyuxiang/echo-agentWrote 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/fuyuxiang/echo-agent/deep-research)<a href="https://agentmods.dev/skills/fuyuxiang/echo-agent/deep-research"><img src="https://agentmods.dev/badge/skills/fuyuxiang/echo-agent/deep-research.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 | $0.00021 | $0.00450 |
| Opus 5 | $0.00010 | $0.00225 |
| Sonnet 5 | $0.00004 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
deep-research 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.
What it actually says
Deep Research
Multi-step research workflow that produces cited reports from multiple sources.
Workflow
- Decompose — Break the question into 3-5 sub-questions
- Search — Run multiple searches per sub-question (diverse keywords)
- Extract — Fetch and extract content from top URLs
- Cross-reference — Compare claims across sources, flag conflicts
- Synthesize — Write structured report with inline citations
Usage
python3 scripts/research_report.py "What are the best practices for LLM agent memory in 2026?"
python3 scripts/research_report.py "Compare FastAPI vs Litestar performance" --depth deep
Output Format
Reports follow this template:
# Research Report: {Topic}
**Date:** YYYY-MM-DD
**Sources consulted:** N
## Summary
2-3 sentence overview of findings.
## Key Findings
### Finding 1
Detail with evidence. [Source 1][1] confirms that...
### Finding 2
...
## Conflicting Information
Where sources disagree, note both positions.
## Conclusion
Actionable synthesis.
## Sources
[1]: https://... — Title
[2]: https://... — Title
Depth Levels
| Level | Searches | Pages Read | Time |
|---|---|---|---|
| quick | 2-3 | 3-5 | ~30s |
| normal | 5-8 | 8-12 | ~2min |
| deep | 10-15 | 15-25 | ~5min |
Combining with Other Skills
- Use
web-searchfor the search step - Use
web-extractfor the extraction step - Use
summarizeskill for per-page summaries before synthesis - Store results with
note-takingskill
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 75 lines · 21 tokens per session scan A 240e368e2bc5
deep-research is a skill published in the GitHub repository fuyuxiang/echo-agent (988 stars, last pushed 4d ago), licensed MIT. It adds 21 tokens to every session and 450 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 2026-08-30.
Other skills, from other repositories
pptx
从论文、大纲或结构化文本生成 PowerPoint (.pptx) 演示文稿。Use when 用户需要把一篇论文/文章/大纲做成幻灯片、slides、演示文稿、PPT、deck。Don't use when 只需纯文本总结、生成 Word/PDF、或修改已有 pptx 的单个像素级样式。.
ai-style
当任务是用中文撰写或改写面向读者的文案（产品发布稿、公众号文章、邮件、README 等）， 或用户反馈文字「AI 味太重」「不像人写的」时，加载本 Skill。.
triage
你是当前任务的分诊协调者。先识别用户的全部目标、顺序依赖和验收条件，再按 “事实检索 → 计算/执行 → 写作”顺序逐步请求切换到需要的专业能力。不要替专业 能力完成它的工作，也不要在信息缺失时臆造结果。.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
kungfu-agent-onboarding
Discover the exact Kungfu Project, WorkConsole, WorkRef, Skill catalog, and Core Work state admitted to this Amp process.
data_analysis
基于已确认数据执行可审计的数学计算和描述统计。.