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/pieable/dragon-ball-agent/deep-researchnpx skills add pieable/dragon-ball-agent --skill deep-researchgit clone --depth 1 https://github.com/pieable/dragon-ball-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/pieable/dragon-ball-agent/deep-research)<a href="https://agentmods.dev/skills/pieable/dragon-ball-agent/deep-research"><img src="https://agentmods.dev/badge/skills/pieable/dragon-ball-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 | $0.00109 | $0.02371 |
| Opus 5 | $0.00055 | $0.01185 |
| Sonnet 5 | $0.00022 | $0.00474 |
| Haiku 4.5 | $0.00011 | $0.00237 |
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 5d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
研究的目标是在约定范围内形成正确、覆盖足够并可追溯的判断。探索型任务中,足够大且具有实质差异的候选空间本身是重要中间结果:搜索用于带回更多路径、解释、类比、灵感和来源入口,再由研究负责人组织收敛。搜索次数、来源数量、代理数量和并行度不能单独作为完成标准,最终交付也不是搜索结果的拼接。但不能因为已经找到一个可写的答案就过早停止扩展。
选择执行结构
Root 负责理解用户、确定研究边界和处理会改变整体结论的判断。research-lead 负责多条来源路线的研究结构、分派、冲突处理和阶段综合。web-researcher 负责网络来源的发现、收集和一条路线内的核验,explorer 负责边界明确的本地材料取证。使用本 Skill 不改变这项分工,材料重要也不自动把搜索责任移到上级。
能够写清问题、来源范围、交付证据和停止条件的单项网络取证,由 Root 直接交给 web-researcher;边界明确的本地材料取证直接交给 explorer。不要先创建 research-lead,再让它把同一个小问题整体转交给搜索执行者。
只有当研究阶段包含多条相对独立的来源路线,需要持续扩大候选覆盖、根据第一批结果补查、处理来源冲突并形成阶段综合时,才让 research-lead 连续负责整个研究阶段并组织执行者。任务规模不大或只有一两条证据路线时不增加这一层。实施途中才出现实质性的覆盖和整合责任时,再升级给 research-lead。
Root 或 research-lead 只有在取证报告已经定位到具体来源和片段,而一个明确的矛盾或解释差异仍会改变自己负责的判断时,才读取解决该问题所需的最小原文片段。这是对具体证据的定向核验,不是重新发现来源、重复已经委派的搜索,或者接管一整条取证路线。
主任务交给 research-lead 的开放研究合同以目标、背景、边界和结果为核心:说明要理解什么、当前为何需要调查及已有状态、不可越过的对象、时间、来源和权限范围,以及最终要交回的候选图、判断或报告和相应证据。查询、来源路线、候选分类和答案结构通常留给负责人根据搜索结果改写。用户明确限制或当前是精确取证时再固定。问题已经清楚时直接开始。缺少的信息会改变研究方向或重要行动时提问。最终使用的结论都要能追溯到具体来源。
建立覆盖结构
了解陌生领域时,先用权威教材、手册或综述确定术语、主要问题和重要分歧,再查专业数据库、一手材料、参考文献和被引文献。权威专家材料或访谈用于核对术语与争议,最终结论仍落到可追溯证据。
持续跟踪新闻、公司或事件时,先检查已有名单、官方公告入口、监管披露、事件日历、邮件或 RSS,再用网页搜索补充清单之外的线索。优先复用已经验证的来源入口,不重复从宽泛搜索开始。
进入深度研究后,先定位研究原点,明确对象、范围和当前状态。只看当前现象不足以判断时,沿时间关系追溯造成现状的条件和选择,并明确希望达到的目标。答案取决于方案或对象比较时,在相近条件下选择参照,说明比较维度、可比条件和材料限制。再把这些关系转成需要解决的主张、候选空间、可能产生原始记录的来源系统、相互竞争的解释和仍会改变答案的未知。新证据可以缩小、扩展或改写这套覆盖结构。
发散、收敛和多轮搜索
研究先判断当前需要发散还是已经可以收敛。用户需要灵感、多条可选路径、陌生问题的版图,或者最初问题结构本身可能限制答案时,先有意识扩大覆盖:从不同因果机制、对象、行动路线、类比和来源系统寻找实质不同的候选,不只验证主任务最先提出的解释。候选可以暂时只是有根据的线索,但必须与事实、已反证内容和未知分开标记。候选差异以会带来不同理解、行动或证据路径为准,不用同义改写凑数量。新增独立搜索已很少产生新分支,或者达到用户约定的探索范围和成本时,再转入收敛。
问题、对象和完成条件已经明确的确定性取证可以直接收窄。进入收敛后,按证据强弱、适用条件、用户价值、成本和风险比较候选。只继续深入会改变主要结论、候选取舍或重要不确定性的方向。发散阶段提供广度,收敛阶段提供可信度,二者都不要求伪装成已经穷尽所有可能。
广度搜索用于发现尚未进入覆盖结构的重要分支和来源入口,深度搜索沿引用链、候选项和冲突追到能够直接支持或推翻主张的材料。两者的投入由实际覆盖变化决定,不使用固定角度、固定查询数或固定代理数代替判断。
大规模开放研究默认进行多轮自适应搜索,而不是一轮预设并行后直接成稿。第一轮以扩大覆盖和建立候选图为主。收到材料后先综合新出现的分支、矛盾、术语、来源入口和证据缺口,再用这些发现重写下一轮搜索问题。第二轮及后续轮次应追踪上一轮无法预先确定的高价值线索、反例和冲突,不重复同一批查询。每轮转换前记录新增和淘汰的候选、被改写的问题、尚未解决的冲突,以及下一轮预期会改变哪项理解、行动或风险判断。至少完成一次由前一轮结果驱动的后续搜索,除非用户停止、来源不可达,或当前只是对象与完成条件已经封闭的确定性取证。后续搜索仍有合理预期改变候选图、行动或关键未知,而且收益高于时间、调用和边界成本时继续。一轮综合后已很少出现实质新分支,而且剩余缺口不会改变主要结论或约定的灵感覆盖时才停止。
What ships with it
2 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.
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.
- 5d ago First seen · 55 lines · 109 tokens per session scan A 4a569c3a5710
deep-research is a skill published in the GitHub repository pieable/dragon-ball-agent (11 stars, last pushed 3d ago), licensed MIT. It adds 109 tokens to every session and 2,371 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…