Deep Research

A method for producing a detailed research report about a topic by breaking it into several questions, examining evidence, and combining the findings. It also records uncertainties and questions that remain open.

In plain words
What is it for?
Use it for literature reviews, technology or market landscapes, structured topic analysis, and reports that need cross-cutting conclusions.
Why use it?
It gives research tasks a consistent structure and keeps evidence, reasoning, synthesis, and unanswered questions together. It is intended for broad analysis rather than a short factual lookup.

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/agentera/agently/deep-research
Any agent
npx skills add AgentEra/Agently --skill deep-research
Clone the repo
git clone --depth 1 https://github.com/AgentEra/Agently

Made for: Claude Code, Codex.

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 225 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 $0.00053 $0.00225
Opus 5 $0.00026 $0.00112
Sonnet 5 $0.00011 $0.00045
Haiku 4.5 $0.00005 $0.00022

Measured yesterday against content hash 500d1dc32d15, 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.

examples/archived/pre-4.1.3.8-skills-orchestration/agent_auto_orchestration/skills/deep-research/SKILL.md · 26 lines

What it actually says

Deep Research

You are a senior research analyst. Given a topic, produce a deep report in ONE pass.

Method

  1. Decompose the topic into 3-5 key dimensions (e.g. technology, market, adoption, risks, outlook) appropriate to the subject.
  2. For each dimension: analyze with specific evidence and reasoning, not generic description. Note where your knowledge is uncertain or may be out of date.
  3. Synthesize cross-cutting insights that connect the dimensions.
  4. List open questions a follow-up round should investigate.

Be analytical and specific. Distinguish established facts from inference. Do not fabricate sources, figures, or citations.

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 First seen · 26 lines · 53 tokens per session scan A 500d1dc32d15

Subscribe to this mod's changes

Deep Research is a skill published in the GitHub repository AgentEra/Agently (1,644 stars, last pushed 3d ago), licensed Apache-2.0. It adds 53 tokens to every session and 225 once invoked, about $0.0003 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.