deep-research

deep-research is a skill for Codex from pieable/dragon-ball-agent. It costs 42 tokens per session (4,104 once invoked), scanned A, original, MIT.

A guide for researching unfamiliar or complex questions by finding multiple sources, alternatives, counterexamples, and a traceable conclusion.

In plain words
What is it for?
Use it to explore unclear topics, compare possible approaches, investigate a stuck project, verify important claims, and combine evidence from several sources.
Why use it?
It reduces the risk of relying on a single search result when the answer needs broad coverage or careful verification.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md.

Good fit Use it to explore unclear topics, compare possible approaches, investigate a stuck project, verify important claims, and combine evidence from several sources.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pieable/dragon-ball-agent/deep-research
Install

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.

Any agent
npx skills add pieable/dragon-ball-agent --skill deep-research
Clone the repo
git clone --depth 1 https://github.com/pieable/dragon-ball-agent

Made for: Codex.

Wrote 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.

agentmods badge for deep-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/pieable/dragon-ball-agent/deep-research/github.svg)](https://agentmods.dev/skills/pieable/dragon-ball-agent/deep-research)
Your own site
<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/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.

agentmods 80×15 button for deep-research

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,104 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.04104
Opus 5.5 $0.00017 $0.01642
Sonnet 5.5 $0.00008 $0.00821
Haiku 4.5 $0.00004 $0.00410

Measured 22d ago against content hash 45adf7be2dab, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 22d 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.

skills/deep-research/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Research

按任务需要主动使用本 Skill 和适合的研究分工,无需用户专门点名。依据问题的独立性、连续判断需要和总投入选择直接执行或委派,下文的研究方法适用于两种执行方式。

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

直接执行时,当前负责人连续完成来源发现、原文取证、补查和综合,承担下文研究负责人的工作。模型选择沿用当前配置,使用本 Skill 不自动升级为 Astra。

委派执行

以下角色分工及上级核验限制只适用于委派执行。

Root 负责理解用户、确定研究边界和处理跨阶段决定。research-lead 连续负责研究结构、取证安排、冲突处理和阶段综合。web-researcher 在所负责的问题内自主发现候选、追查实现、沿新线索扩展并核验来源,explorer 负责本地材料取证。已经委派的调查由原负责人继续,接收方核对决定性原文并使用结果。

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。

研究阶段需要同一个负责人持续掌握相互关联的调查、判断和综合,或需要组织多条路线时,可以交给 research-lead。按独立责任和实际依赖选择分工,不以来源路线数量作为设置负责人的门槛。边界清楚的单项调查直接委派,避免增加只转述任务和结果的中间层。

Root 或 research-lead 接受会改变自己所负责决定的关键事实时,读取已定位的必要原文,核对主张是否得到支持,不以报告已出现矛盾为前提。只补查决定性事实、具体矛盾和证据缺口,不重复已经委派的搜索或接管整条取证路线。

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。

建立并调用项目研究经验

项目研究所需的案例库、套路库、来源表、研究笔记和接续入口可以自行建立、复用和更新,无需另行请示。先查已有资料,把有来源、能帮助当前或后续调查的经验保存在项目内,沿用已有目录约定;没有约定时可放在 research/research-experience-library。材料少时先用简短记录,随实际积累完善。

在项目 AGENTS.md 或现有的接续说明中留下简短入口与适用局面,使接续工作的 agent 知道这份经验存在。索引概括案例和套路的用途,正文按需读取。需要选路线、解释冲突或从失败中转向时,根据当前证据和障碍查找结构相似的经验,核对来源及条件,选择下一步,并说明什么结果会改变判断。新证据改变理解时重新选择,无需固定间隔读取全部材料。

案例保留研究者当时知道什么、采取了什么动作、哪些证据导致转向及实际结果。套路记录可迁移的动作、适用条件和仍待验证部分。实际使用后更新项目中的经验与索引,失败路径也保留。具体项目案例和套路由项目维护。具有跨项目复用价值的经验也可以保存在当前项目的研究资料中,注明来源与适用条件。修改全局 Skill、角色指令和用户长期偏好另按对应任务处理。

建立覆盖结构

开始深度研究时,先通过领域的标准工作流程、代表性案例和失败经验建立任务框架,检查主要环节及其依赖是否清楚,候选的适用条件是否有证据,是否还有会改变任务分解或路线的重要未知。已有可靠材料可以复用,发现新的环节、依赖或限制时重新检查原有框架,并据此调整后续研究。

在建立领域工作流程时,进一步回答以下问题,补足用户未提出但专业研究需要完成的细致工作:

  1. 该领域的顶尖专家会做哪些用户没有要求、但会影响结果的事情?
  2. 他们会从哪些最原始的素材入手?用户或模型已经整理的材料可能隐藏了什么?
  3. 他们会使用哪些具体方法和工具?分别需要什么输入、怎样分析、产出什么结果?
  4. 除了用户和模型自身的判断,还有什么独立证据、实验或外部评判者可以检验结果是否正确?

Read the full file on GitHub · 119 lines

Files

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.

Changes

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.

  1. 22d ago Changed · +19 lines 45adf7be2dab
  2. 23d ago Changed · +12 lines 8cc7dcdf863d
  3. 1mo ago Changed · +33 lines · -67 tokens per session 785ede7b3c0d
  4. 2mo ago First seen · 55 lines · 109 tokens per session scan A 4a569c3a5710

Subscribe to this mod's changes

deep-research is a skill published in the GitHub repository pieable/dragon-ball-agent (11 stars, last pushed 23d ago), licensed MIT. It adds 42 tokens to every session and 4,104 once invoked, about $0.0002 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 2026-08-31.

Related

deep-research compared with skills from other repositories

deep-research next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
deep-researchpieable/dragon-ball-agentSkill1123d agoMITA42Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code