deep-research

A workflow for thorough research that breaks a question into smaller parts, checks multiple sources, and combines the findings into a report. It also records sources, uncertainty, and conflicting information.

In plain words
What is it for?
Researching broad subjects, comparing options, investigating questions, and producing reports with an executive summary, detailed findings, cited sources, and a confidence assessment.
Why use it?
It reduces reliance on one source or an unsupported assumption when the topic needs a deeper investigation.

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/jansenanalytics/claudex/deep-research
Any agent
npx skills add JansenAnalytics/claudex --skill deep-research
Clone the repo
git clone --depth 1 https://github.com/JansenAnalytics/claudex

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 333 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00030 $0.00333
Opus 5 $0.00015 $0.00167
Sonnet 5 $0.00006 $0.00067
Haiku 4.5 $0.00003 $0.00033

Measured 3d ago against content hash 44ad217ca8f9, 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 1 finding 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.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

2. **Search multiple sources** for each sub-question using Bash + curl
skills/deep-research/SKILL.md · 41 lines

What it actually says

Deep Research Skill

When given a research task:

  1. Decompose the question into 3-5 sub-questions
  2. Search multiple sources for each sub-question using Bash + curl
  3. Cross-reference findings across sources
  4. Synthesize into a structured report with:
    • Executive summary (3-5 sentences)
    • Key findings (bullet points)
    • Detailed analysis (organized by sub-topic)
    • Sources cited
    • Confidence level and caveats

Search Methods

# DuckDuckGo (no API key needed)
curl -s "https://html.duckduckgo.com/html/?q=QUERY" | grep -oP '(?<=<a rel="nofollow" class="result__a" href=").*?(?=")'

# Fetch readable content from URL
curl -sL URL | sed 's/<[^>]*>//g' | head -200

# Wikipedia API
curl -s "https://en.wikipedia.org/api/rest_v1/page/summary/TOPIC"

Quality Standards

  • Never present a single source as definitive
  • Flag conflicting information explicitly
  • Distinguish facts from opinions
  • Include dates/recency of information
  • Rate overall confidence: HIGH / MEDIUM / LOW
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 · 41 lines · 30 tokens per session scan A 44ad217ca8f9

Subscribe to this mod's changes

deep-research is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 333 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.