deep-researcher

deep-researcher is an agent for Claude Code from air-gapped/skills. It costs 39 tokens per session (327 once invoked), scanned A, original, MIT.

A web research agent that investigates one specific angle of a broader research question. It uses authoritative online sources and reports findings, disagreements, follow-up questions, and confidence.

In plain words
What is it for?
Use it to gather sourced facts, numbers, dates, code examples, or quotes about one part of a larger topic.
Why use it?
It keeps research focused and preserves evidence from earlier rounds, so the main investigation does not repeat the same work.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to gather sourced facts, numbers, dates, code examples, or quotes about one part of a larger topic.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/air-gapped/skills/deep-researcher
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.

Clone the repo
git clone --depth 1 https://github.com/air-gapped/skills

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-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/air-gapped/skills/deep-researcher.svg)](https://agentmods.dev/agents/air-gapped/skills/deep-researcher)
Your own site
<a href="https://agentmods.dev/agents/air-gapped/skills/deep-researcher"><img src="https://agentmods.dev/badge/agents/air-gapped/skills/deep-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 327 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00039 $0.00327
Opus 5 $0.00019 $0.00163
Sonnet 5 $0.00008 $0.00065
Haiku 4.5 $0.00004 $0.00033

Measured 7d ago against content hash b17f5017a6c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

deep-researcher 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 7d 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.

.claude/agents/deep-researcher.md · 44 lines

What it actually says

You are a research agent investigating a specific angle of a broader topic.

Your spawn prompt supplies:

  • BROADER QUESTION: — the overall research question
  • YOUR ANGLE: — the specific angle you investigate
  • PRIOR LEARNINGS: — findings from previous rounds (may be empty); do not re-derive them, build on them

Instructions:

  1. Use WebSearch to find 3-5 authoritative sources on your angle
  2. For each promising result, use WebFetch to read the full content
  3. Extract SPECIFIC information: names, numbers, dates, code snippets, direct quotes. Vague summaries are not useful.
  4. Note any contradictions between sources
  5. Identify 1-2 follow-up questions that emerged

Return your findings in this exact format:

LEARNINGS:

  • [Specific finding] (Source: [url])
  • [Specific finding] (Source: [url]) ...

CONTRADICTIONS:

  • [Source A] says X, but [Source B] says Y ...

FOLLOW_UPS:

  • [Question that needs deeper investigation] ...

SOURCES:

  • [url]: [one-line description of what it contained and its credibility] ...

CONFIDENCE: [high/medium/low] — how well-supported are your findings?

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. 7d ago First seen · 44 lines · 39 tokens per session scan A b17f5017a6c7

Subscribe to this mod's changes

deep-researcher is an agent published in the GitHub repository air-gapped/skills (5 stars, last pushed 6d ago), licensed MIT. It adds 39 tokens to every session and 327 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

unity-reviewer

Unity-specific code reviewer focusing on MonoBehaviour patterns, serialization, performance, and Unity best practices. Use after implementing Unity code to catch Unity-specific issues.

DmitriyYukhanov/claude-plugins · 34 tokens

unity-simplifier

Simplifies Unity C# code for clarity and maintainability while preserving functionality. Focuses on Unity-specific patterns and conventions.

DmitriyYukhanov/claude-plugins · 29 tokens

python-reviewer

Python-specific code reviewer focusing on type safety, PEP 8 compliance, and Python best practices. Use after implementing Python code to catch Python-specific issues.

DmitriyYukhanov/claude-plugins · 35 tokens

typescript-reviewer

TypeScript-specific code reviewer focusing on type safety, async patterns, and frontend best practices. Use after implementing TypeScript code to catch TypeScript-specific issues.

DmitriyYukhanov/claude-plugins · 35 tokens

sync-spec-kit-agent

Analyzes implementation changes on a feature branch and updates the spec-kit specification folder (.specify/specs/ /) to reflect the current state — new requirements, architecture changes, completed tasks, research findings, and any drift from the original specification. Context: User finished implementing something…

lukaskellerstein/claude-my-marketplace · 229 tokens

visual-fixer-page

Fixes visual issues on ONE page of a built website — starts its own dev server on an assigned port, inspects every section and element using Playwright DOM inspection, compares against the design document, and fixes all issues directly in the source files for that page only. Multiple instances run in parallel, each…

lukaskellerstein/claude-my-marketplace · 170 tokens