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 skills add jeffy-Peng/jeffy-skills --skill 3d-deep-researchgit clone --depth 1 https://github.com/jeffy-Peng/jeffy-skillsWrote 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/jeffy-peng/jeffy-skills/3d-deep-research)<a href="https://agentmods.dev/skills/jeffy-peng/jeffy-skills/3d-deep-research"><img src="https://agentmods.dev/badge/skills/jeffy-peng/jeffy-skills/3d-deep-research/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/skills/jeffy-peng/jeffy-skills/3d-deep-research"><img src="https://agentmods.dev/badge/skills/jeffy-peng/jeffy-skills/3d-deep-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00121 | $0.03367 |
| Opus 5.5 | $0.00048 | $0.01347 |
| Sonnet 5.5 | $0.00024 | $0.00673 |
| Haiku 4.5 | $0.00012 | $0.00337 |
Grade A, and why
3d-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 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
3D Deep Research
先建立研究底图，确认研究对象的边界、运转方式和当前状态；再用 X/Y/Z 逐层解释：X 识别显性与非显性的关键变化及其后续影响，Y 沿具体变化切开并比较成因，Z 拆开尚不清楚的作用连接。分析结果持续返回发展路径和研究底图，用证据校正解释并检查重要遗漏。
本 Skill 为主研究流程时，默认交付完整的 Markdown、HTML 和 PDF 三份报告；用户明确缩小交付范围时按其要求减少。用户点名其他研究 Skill 或选择其他工作模式时，以其作为主流程；仅在需要本方法时辅助使用，不叠加独立默认产物。不要仅因通用的 deep research 字样同时运行两套流程，也不要把普通问答扩写成长报告。
资源读取
按当前阶段读取所需资源；同一任务中已完整读取且未变化的文件直接复用。输出被截断时只补读缺失部分，不反复装载全文。
- 读取 references/evidence-protocol.md，建立来源与 Claim 账本并执行事实审计。
- 读取 references/xyz-method.md，建立研究底图并执行 X/Y/Z、路径校正和覆盖复核。
- 根据研究对象读取 references/object-adapters.md 的对应部分。
- 分析时读取 references/visual-guidelines.md，规划有解释价值的图；论点稳定后制作和检查。
- 写作时复制 assets/report-template.md，保留元数据与证据附录，按核心问题组织正文。
- 首次构建或排错时读取 references/build-runtime.md。运行现有脚本，无需预读实现；仅在明确故障需要时定位相关代码。
报告措辞
以下规则适用于正文、标题和图注；证据附录以准确、可追溯为先。
- 先直接回答研究问题，再解释依据、原因及其对用户问题的含义；用户未要求行动方案时，不自行扩成路线图。
- 先具体，后抽象。 优先说清谁做了什么、发生什么变化，再解释背后的概念。能直接说明的，不用抽象名词代替。
- 先判断，后解释。 一句话先说清主要意思，原因和必要限制随后展开，避免把多层意思挤进一句话。
- 面向目标读者使用准确、克制的专业书面语。 保留必要概念，用具体对象、关系和口径解释；不用口语化比喻替代分析，也不用抽象术语增加专业感。
- 每个核心论点说明目前支持什么判断、为什么重要、依据及作用过程是什么。每段推进一个判断；删除不增加事实、解释或决策价值的句子。
- 明确区分事实、解释和预测。证据只能支持“可能”时，不写成“证明”或“必然”。
- 不把 Claim 类型、证据门槛、X/Y/Z 等内部方法术语写进正文；它们只用于组织研究和附录说明。
- 数字首次出现时说明时间、单位、统计口径和比较对象。
- 不使用宣传式形容词、无依据的最高级，以及“值得注意的是”“不容忽视”等空洞过渡语。
- 影响判断方向、适用范围或幅度的限制紧邻相关结论；共性研究限制放入 A3，不逐段重复。同一论证只完整展开一次。
- 证据不足时，明确可支持的暂定判断和仍未解决的部分。不用反复强调“不能证明”“不等于”代替分析；证据无法区分因素重要性时不强排主次、不编造贡献比例。
表达示例（只示范论证方式，变量须按具体研究取舍）：
| 只有提醒的表达 | 增加分析的表达 |
|---|---|
| 高售价不等于高利润 | 增量利润取决于售价差、增量制造与售后成本，以及对既有机型的替代。 |
| 看得更多，未必做得更好 | 大屏的使用收益取决于任务布局与输入成本。 |
| 兼容不等于适配好 | 应分别检查布局利用、状态连续性和关键操作完成情况。 |
执行流程
0. 明确研究设定
根据用户问题和上下文明确目标读者、需要作出的判断、研究对象及类型、时间基准、范围和交付要求。无法从上下文解决且会显著改变目标或正确性的问题才追问；其余情况直接开始。形成暂定问题结构，指出最可能改变判断的未知项，再根据对象适配器建立研究底图、检查遗漏；证据可以推翻暂定结构。
必须检查的维度不等于必须写入正文的章节。篇幅按对核心问题的解释价值分配，不按类别平均分配；重要性判断须有依据，无关侧面省略，证据不足但可能改变结论的侧面进入 A3。
What ships with it
19 files 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.
- agents/openai.yaml 275 B
- assets/report-template.md 2.8 KB
- assets/report.css 4.5 KB
- references/build-runtime.md 3.3 KB
- references/evidence-protocol.md 6.4 KB
- references/object-adapters.md 4.0 KB
- references/visual-guidelines.md 4.7 KB
- references/xyz-method.md 11 KB
- scripts/build_report.py 8.0 KB runs code
- scripts/linkify_sources.py 3.0 KB runs code
- scripts/preview_report.py 3.0 KB runs code
- scripts/render_report.py 12 KB runs code
- scripts/report_artifacts.py 3.7 KB runs code
- scripts/validate_report.py 27 KB runs code
- tests/test_build_report.py 3.8 KB runs code
- tests/test_evidence_contract.py 8.6 KB runs code
- tests/test_linkify_sources.py 2.1 KB runs code
- tests/test_render_report.py 3.9 KB runs code
- tests/test_validate_report.py 15 KB runs code
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 Changed · +7 lines 82b121c8be81
- 1mo ago Changed · +4 lines 7e79bff3b504
- 1mo ago Changed · +9 lines 5c9a577b3f37
- 2mo ago Changed · +2 lines 21cf0304aeb2
- 2mo ago Changed · +6 lines c2faa769d31b
- 2mo ago First seen · 114 lines · 121 tokens per session scan A bbaa4f5ca823
3d-deep-research is a skill published in the GitHub repository jeffy-Peng/jeffy-skills (21 stars, last pushed 8d ago), licensed MIT. It adds 121 tokens to every session and 3,367 once invoked, about $0.0005 per session on Opus 5.5. 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.
3d-deep-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| 3d-deep-researchjeffy-Peng/jeffy-skills | Skill | 21 | 8d ago | MIT | A | 121 | Codex |
| research-opsericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 105 | Claude Code, Codex |
| mk:researchngocsangyem/MeowKit | Skill | 15 | 6d ago | MIT | A | 165 | Claude Code |
| idea-bib-reviewbahayonghang/my-ai-cli-toolkit | Skill | 17 | 9d ago | MIT | A | 126 | Claude Code, Codex |
| link-evidencekdcube/kdcube | Skill | 27 | yesterday | MIT | A | 25 | Claude Code |
| net-deep-researchh4444433333/net-deep-research | Skill | 72 | 2mo ago | MIT-0 | A | 73 | Claude Code, Codex |
| ftdericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 128 | Claude Code, Codex |