deep_research

deep_research is a skill for Claude Code, Codex from siddsachar/row-bot. It costs 17 tokens per session (567 once invoked), scanned A, original, Apache-2.0.

A workflow for researching a topic through multiple sources and producing a structured report. It includes checking previous knowledge, searching the web, reading promising sources closely, and checking recent academic papers when relevant.

In plain words
What is it for?
Use it for in-depth research, source gathering, academic checks, and reports with an executive summary, key findings, detailed discussion, and open questions.
Why use it?
It gives an investigation a repeatable path from an open question to organised findings. Looking at several sources and checking academic work can expose missing context or disagreement.

Skill for Claude CodeCodex

About the project

Row-Bot is a local-first desktop AI assistant that combines language models with memory and tools for working across files, repositories, workflows, and communication channels. It is intended for people who want an assistant that can run locally while keeping application data on their machine.

siddsachar/row-bot · 1,480 stars · on GitHub

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/siddsachar/row-bot/deep_research
Any agent
npx skills add siddsachar/row-bot --skill deep_research
Clone the repo
git clone --depth 1 https://github.com/siddsachar/row-bot

Made for: Claude Code, 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/siddsachar/row-bot/deep_research.svg)](https://agentmods.dev/skills/siddsachar/row-bot/deep_research)
Your own site
<a href="https://agentmods.dev/skills/siddsachar/row-bot/deep_research"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/deep_research.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 567 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 $0.00017 $0.00567
Opus 5 $0.00009 $0.00283
Sonnet 5 $0.00003 $0.00113
Haiku 4.5 $0.00002 $0.00057

Measured 5d ago against content hash 9caac6921094, 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 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.

bundled_skills/deep_research/SKILL.md · 55 lines

What it actually says

When the user asks you to research a topic in depth, write a research report, or investigate something thoroughly, follow these steps:

  1. Check Existing Knowledge — Before searching the web, review your recalled memories and use search_memory for the topic. The user may have researched this before, or you may already have saved facts, sources, or prior findings. Build on what you already know rather than starting from scratch.
  2. Clarify Scope — If the topic is broad, ask one focused question to narrow it down before proceeding. Otherwise, proceed directly.
  3. Initial Search — Run 2–3 web searches with varied queries to gather diverse perspectives on the topic.
  4. Source Deep-Dive — Pick the 3–5 most promising URLs from the search results and read their full content using the URL reader.
  5. Academic Check — If the topic is scientific or technical, search arXiv for relevant recent papers. Summarise key findings from the top 1–2 results.
  6. Synthesise — Compile findings into a structured report:
    • Executive Summary — 2–3 sentence overview
    • Key Findings — Numbered list of the most important points
    • Details — Deeper discussion organised by sub-topic
    • Open Questions — What remains unclear or debated
    • Sources — List all URLs and papers referenced
  7. Cite Everything — Every claim should reference its source with a numbered citation.
  8. Save Key Findings — Save the most important facts and conclusions to memory so future research on this topic builds on today's work. Use specific entity categories (person, concept, project, fact) and link related findings together.

Aim for thoroughness over brevity. The user wants depth — give them a report they can act on.

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. 5d ago First seen · 55 lines · 17 tokens per session scan A 9caac6921094

Subscribe to this mod's changes

deep_research is a skill published in the GitHub repository siddsachar/row-bot (1,480 stars, last pushed 7d ago), licensed Apache-2.0. It adds 17 tokens to every session and 567 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

rich-post

Send a Telegram rich-media post to ANOTHER allowlisted chat via the bot (Bot API 10.1 sendRichMessage) - text, inline images, tables, headings, lists, quotes, collapsible blocks, formulas, collages/slideshows ALL in one message bubble. Use when the owner asks to post somewhere other than the current conversation (the…

smixs/iva-agent · 129 tokens

memory-processor

Iva's daily-memory processor. Reads the day's two-sided transcript (daily/YYYY-MM-DD.md), distills noteworthy entities / decisions / ideas into typed autograph cards, links them into the graph, and produces a daily-summary card (topics + MOC) that navigates down to the raw transcript and up to the week. Model-agnostic…

smixs/iva-agent · 106 tokens

telegram-userbot

Подключение и работа с личным Telegram-аккаунтом владельца (userbot, НЕ бот). Используй, когда просят читать личные чаты/переписку/диалоги, искать по своим сообщениям, писать кому-то от своего имени, «зайди в мой телеграм», «подключи мой телеграм», «прочитай личку», «ответь в личке», «перешли сообщение», а также при…

smixs/iva-agent · 144 tokens

agent-browser

Браузерная автоматизация для интерактивных веб-задач. Используй, когда нужно открыть сайт, заполнить форму, кликнуть, сделать скриншот, залогиниться, спарсить JS-страницу или протестировать веб-приложение. Триггеры — «зайди на сайт», «заполни форму», «нажми кнопку», «скриншот страницы», «войди в аккаунт», «спарси…

smixs/iva-agent · 114 tokens

update-recovery

Restore or merge user customizations preserved during an Iva update. Use when the owner says "restore my update changes", "recover my customizations", «верни мои изменения после обновления», «восстанови мои доработки» or asks about an update conflict.

smixs/iva-agent · 60 tokens

security-defense

Procedures for handling untrusted content, suspected prompt injection, secret exposure, data exfiltration, and manual security inspection. Use for emails, web pages, forwarded messages, webhooks, group content, or a suspected leak. Do not use as a general claim that every command or model call is automatically…

smixs/iva-agent · 68 tokens