deep-research

A deep-research workflow that coordinates several helper agents to search the web in parallel and combine their findings into a detailed report with citations.

In plain words
What is it for?
Use it for definitions, how-to research, comparisons, current-state investigations, and other topics that need multiple searches and sourced synthesis.
Why use it?
It divides broad or complex research into smaller investigations and brings the results together in one structured report.

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/nikeyes/stepwise-dev/deep-research
Any agent
npx skills add nikeyes/stepwise-dev --skill deep-research
Clone the repo
git clone --depth 1 https://github.com/nikeyes/stepwise-dev

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,819 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 $0.00018 $0.02819
Opus 5 $0.00009 $0.01409
Sonnet 5 $0.00004 $0.00564
Haiku 4.5 $0.00002 $0.00282

Measured 2d ago against content hash 24f5eea4369f, 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 2d 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.

research/skills/deep-research/SKILL.md · 341 lines

How it starts

The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Research Command

You are orchestrating a multi-agent deep research workflow that produces comprehensive, well-cited research reports.

Command Workflow

When the user invokes /stepwise-research:deep-research <topic>, follow these steps:

1. Clarification Phase (Only if Needed)

If the research topic is ambiguous or unclear, ask 1-2 clarifying questions using the AskUserQuestion tool:

  • What specific aspect should be prioritized?
  • What timeframe or context is relevant?
  • Are there specific sources to include/exclude?

Skip this step if:

  • Topic is explicit (e.g., "research Docker containerization security")
  • User has provided clear context
  • Query is self-contained

2. Analyze Query Complexity

Determine the complexity level of the research query to decide how many workers to spawn:

Query Types:

  • Simple definition (e.g., "What is Docker?"): 1 worker
  • How-to guide (e.g., "How does JWT work?"): 1-2 workers
  • Comparison (2 items) (e.g., "React vs Vue"): 2-3 workers
  • Comparison (3+ items) (e.g., "Compare top 5 databases"): 3-5 workers
  • State-of-the-art (e.g., "Current state of WebAssembly"): 4-6 workers
  • Multi-faceted analysis (e.g., "Analyze enterprise AI adoption"): 5-8 workers
  • Controversial topic (e.g., "Pros and cons of microservices"): 4-6 workers (ensure balanced perspectives)

3. Generate Sub-Questions

Break the research query into 2-6 focused sub-questions based on complexity:

Example for simple query ("What is Docker?"):

  • Sub-question 1: What is Docker and what problem does it solve?

Example for comparison ("PostgreSQL vs MySQL"):

  • Sub-question 1: PostgreSQL architecture and performance characteristics
  • Sub-question 2: MySQL architecture and performance characteristics
  • Sub-question 3: Real-world benchmarks and case studies comparing both

Example for complex research ("State of WebAssembly adoption"):

  • Sub-question 1: WebAssembly capabilities and features in 2026
  • Sub-question 2: Major frameworks and tools supporting WebAssembly
  • Sub-question 3: Enterprise adoption case studies and success stories
  • Sub-question 4: Performance benchmarks and limitations
  • Sub-question 5: Security considerations and best practices
  • Sub-question 6: Future roadmap and emerging use cases

Read the full file on GitHub · 341 lines

Files

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.

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. 2d ago First seen · 341 lines · 18 tokens per session scan A 24f5eea4369f

Subscribe to this mod's changes

deep-research is a skill published in the GitHub repository nikeyes/stepwise-dev (24 stars, last pushed 13d ago), licensed Apache-2.0. It adds 18 tokens to every session and 2,819 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens