deep-research

A multi-agent workflow for carrying out deep research: a broad investigation that gathers, checks, and combines evidence from websites or other materials.

In plain words
What is it for?
It helps with competitor and industry research, batches of links or data, and reports that need collected evidence and review.
Why use it?
It breaks a large research question into smaller tasks that can run in parallel, while keeping sources, results, and missing evidence organized.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/feiskyer/codex-settings/deep-research
Any agent
npx skills add feiskyer/codex-settings --skill deep-research
Clone the repo
git clone --depth 1 https://github.com/feiskyer/codex-settings

Made for: Claude Code, Codex.

Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,285 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00119 $0.01285
Opus 5 $0.00060 $0.00642
Sonnet 5 $0.00024 $0.00257
Haiku 4.5 $0.00012 $0.00128

Measured 3d ago against content hash da27b3cf6c7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/aggregate.py, scripts/run_children.py, tests/test_deep_research_scripts.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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 · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Research

把深度调研作为可重复、可审计的生产流程执行。主控负责目标澄清、样本摸底、子任务设计、结果核验和最终综合;子进程负责边界清晰的采集或局部分析。

核心约束

  1. 保持用户当前模型和推理配置,不传 --model,不覆盖无关配置。
  2. 子进程默认使用 workspace-write;只有确实需要 shell 网络访问时才启用 runner 的 --network
  3. 先检查当前会话可用的 Skills、连接器和 MCP,再按来源适配能力;不要假设固定服务或工具名存在。
  4. 不使用 --dangerously-bypass-approvals-and-sandbox
  5. 所有运行产物写入独立的 .research/<name>/ 目录。
  6. 在开始批量执行前向用户展示拆分方案;需要明显成本、长时间运行或外部系统访问时,等待明确同意。

Bundled scripts

先解析当前 Skill 的绝对目录并记为 <skill-dir>

  • scripts/run_children.py:跨平台并行执行 codex exec,负责超时、重试、日志和结果状态。
  • scripts/aggregate.py:按 manifest 顺序聚合成功的子报告,缺失或空结果时失败。

两个脚本都使用 Python 标准库,不生成临时 shell 脚本。

Workflow

1. 澄清与摸底

明确目标、受众、时间范围、来源边界、评价标准和最终格式。通过当前可用工具获取少量真实样本,记录代表性来源和缺口,避免只凭经验拆分。

2. 创建运行目录

使用不重复的语义化名称,例如:

.research/20260712-codex-skills-a3f2/
├── prompts/
├── logs/
├── child_outputs/
├── raw/
├── cache/
└── manifest.json

把网页原文、数据和解析结果缓存到 raw/cache/,避免重复抓取。

3. 设计子任务

每个子任务只负责一个明确边界,Prompt 至少包含:

  1. 子目标、输入和允许访问的范围
  2. 输出结构和证据要求
  3. 失败时必须说明原因,不得编造结果
  4. 输出自然语言 Markdown,并把来源链接放在对应结论附近

将 Prompt 分别写入 prompts/,然后创建 manifest:

{
  "tasks": [
    {
      "id": "market-history",
      "title": "市场历史",
      "prompt_file": "prompts/market-history.md"
    },
    {
      "id": "current-competitors",
      "title": "当前竞品",
      "prompt_file": "prompts/current-competitors.md"
    }
  ]
}

id 只能包含字母、数字、点、下划线和短横线。Prompt 必须位于本次运行目录内。

4. 预检和执行

先预览命令,不启动 Codex 子进程:

python3 "<skill-dir>/scripts/run_children.py" \
  --run-dir ".research/<name>" \
  --workspace "$PWD" \
  --dry-run

检查 manifest 和 Prompt 后执行:

python3 "<skill-dir>/scripts/run_children.py" \
  --run-dir ".research/<name>" \
  --workspace "$PWD" \
  --parallel 8 \
  --timeout 600 \
  --retries 1

只有子任务必须通过 shell 直接联网时才添加 --network。根据任务成本调整并发和超时,先用 1–2 个子任务验证链路,再扩大并发。

Runner 固定输出:

  • child_outputs/<id>.md
  • logs/<id>.log
  • results.json

5. 核验和失败处理

读取 results.json,检查失败、超时、空输出和引用缺失。只重试失败的边界任务;不要因为单个失败重新运行所有成功任务。需要改变模型、权限或来源范围时先说明原因。

Read the full file on GitHub · 137 lines

Files

What ships with it

4 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. 3d ago First seen · 137 lines · 119 tokens per session scan A da27b3cf6c7f

Subscribe to this mod's changes

deep-research is a skill published in the GitHub repository feiskyer/codex-settings (236 stars, last pushed 20d ago), licensed MIT. It adds 119 tokens to every session and 1,285 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

skill-creator

Create, refine, and benchmark agent skills. Use when building a new skill, updating an existing one, running evals, checking trigger quality, or improving a skill description.

feiskyer/claude-code-settings · 39 tokens

deep-research

Multi-agent research orchestration: split a research goal into parallel sub-goals, run each via headless claude -p subprocesses, aggregate results into a polished report file. Use for systematic web/document research, competitive or industry analysis, batch link/dataset processing, and long-form evidence synthesis.…

feiskyer/claude-code-settings · 94 tokens

github-review-pr

Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for…

feiskyer/claude-code-settings · 90 tokens

brainstorming

Explore user intent, requirements, and design options through collaborative dialogue before implementation. Use before building new features, components, or systems — whenever the user describes something to build and design decisions are involved. Triggers: "brainstorm", "help me design", "think through the…

feiskyer/claude-code-settings · 93 tokens

grill-me

针对方案或设计的高强度追问式面试(adversarial design review / grill session),暴露假设漏洞与缺失约束,过程中同步维护领域模型(术语表和 ADR)。手动调用 /grill-me。.

feiskyer/claude-code-settings · 58 tokens

gpt-image-skill

Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc). Use ONLY when the user explicitly names OpenAI or GPT as the provider: "gpt image", "openai image", "generate image with openai", "用 openai 画图", "用 GPT 生成图片". For generic image requests without a provider, use nanobanana-skill instead.…

feiskyer/claude-code-settings · 115 tokens