deep-research

deep-research is a command for Claude Code from jo-duchan/tapflow. It costs 71 tokens per session (427 once invoked), scanned A, original, MIT.

A deep-analysis command for difficult implementation, bug, and design problems, using Fable 5. It compares several possible approaches, selects one, and examines edge cases and next steps.

In plain words
What is it for?
Use it for persistent bugs, complex designs, or repeated failed fixes to map alternatives, risks, affected files, tests, and implementation order.
Why use it?
It provides a structured way to investigate problems whose causes or trade-offs are not clear after a quick attempt.

Command for Claude Code

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 commands/jo-duchan/tapflow/deep-research
Clone the repo
git clone --depth 1 https://github.com/jo-duchan/tapflow

Made for: Claude Code.

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/commands/jo-duchan/tapflow/deep-research.svg)](https://agentmods.dev/commands/jo-duchan/tapflow/deep-research)
Your own site
<a href="https://agentmods.dev/commands/jo-duchan/tapflow/deep-research"><img src="https://agentmods.dev/badge/commands/jo-duchan/tapflow/deep-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 427 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 $0.00071 $0.00427
Opus 5 $0.00036 $0.00214
Sonnet 5 $0.00014 $0.00085
Haiku 4.5 $0.00007 $0.00043

Measured yesterday against content hash 9e9dc7177470, 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 yesterday.

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.

.claude/commands/deep-research.md · 39 lines

What it actually says

아래 문제를 깊이 분석한다: $ARGUMENTS

컨텍스트

tapflow — iOS/Android 시뮬레이터를 브라우저에서 조작하는 오픈소스 셀프호스팅 라이브러리. TypeScript 모노레포: agent-core · ios-agent · android-agent · relay · dashboard · cli

분석 순서

1. 문제 재정의 주어진 문제를 내 언어로 재서술한다. 숨겨진 가정이나 모호한 부분을 명시적으로 드러낸다.

2. 해결 접근법 탐색 최소 3가지 접근법을 제시한다. 각 접근법마다:

  • 핵심 아이디어
  • 장점 / 단점 (복잡도, 성능, 정확성, 유지보수성)

3. 최선 접근법 선정 왜 이 접근법이 나머지보다 나은지 근거를 명확히 밝힌다.

4. 엣지케이스 · 실패 모드 무엇이 잘못될 수 있는가? 어떻게 방어할 것인가?

5. 구체적인 다음 단계

  • 변경해야 할 핵심 파일과 위치
  • 먼저 작성해야 할 테스트 케이스
  • 구현 순서 (의존성 순)

규칙

  • 결론으로 급하게 뛰어가지 않는다. 각 단계를 충분히 전개한다.
  • 자명하지 않은 통찰을 놓치지 않는다.
  • 코드 스니펫이 이해에 도움이 된다면 적극적으로 포함한다.
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. yesterday Changed · +2 tokens per session 9e9dc7177470
  2. 4d ago First seen · 39 lines · 69 tokens per session scan A 4a98e15b9b3b

Subscribe to this mod's changes

deep-research is a command published in the GitHub repository jo-duchan/tapflow (583 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 427 once invoked, about $0.0004 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.