deep-researcher

deep-researcher is an agent for Claude Code from joaquimscosta/arkhe-claude-plugins. It costs 48 tokens per session (771 once invoked), scanned A, original, MIT.

A technical research assistant that investigates software topics using web and code examples, then saves the findings in a reusable cache. The cache stores research for later use across projects or by a team.

In plain words
What is it for?
Use it to research architectures, technologies, implementation patterns, or best practices, and to refresh previously saved research notes.
Why use it?
It reduces repeated research and keeps related findings organized with titles, aliases, tags, sources, and dates.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths; names the TodoWrite tool.

Part of the core plugin — 5 skills, 7 commands, 6 agents shipped together

Good fit Use it to research architectures, technologies, implementation patterns, or best practices, and to refresh previously saved research notes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/joaquimscosta/arkhe-claude-plugins/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/joaquimscosta/arkhe-claude-plugins

Made for: Claude Code.

Or install core, the plugin that ships this one along with the rest of its 5 skills, 7 commands, 6 agents.

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/joaquimscosta/arkhe-claude-plugins/deep-researcher/github.svg)](https://agentmods.dev/agents/joaquimscosta/arkhe-claude-plugins/deep-researcher)
Your own site
<a href="https://agentmods.dev/agents/joaquimscosta/arkhe-claude-plugins/deep-researcher"><img src="https://agentmods.dev/badge/agents/joaquimscosta/arkhe-claude-plugins/deep-researcher/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for deep-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/joaquimscosta/arkhe-claude-plugins/deep-researcher"><img src="https://agentmods.dev/badge/agents/joaquimscosta/arkhe-claude-plugins/deep-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 771 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 $0.00048 $0.00771
Opus 5 $0.00024 $0.00385
Sonnet 5 $0.00010 $0.00154
Haiku 4.5 $0.00005 $0.00077

Measured 10d ago against content hash e2d406e39047, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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.

plugins/core/agents/deep-researcher.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert research analyst. Conduct deep technical research using EXA tools and cache results for reuse.

Scripts

The caller provides scripts_dir. If not provided, Glob for **/deep-research/scripts/cache_manager.py and use its parent directory.

# Save research to cache
python3 {scripts_dir}/cache_manager.py put "{slug}" \
  --title "{Title}" --content-file /tmp/research-{slug}.md \
  --aliases "alias1,alias2" --tags "tag1,tag2"

# Update promoted docs (refresh only)
python3 {scripts_dir}/promote.py {slug} --refresh

Research Steps

1. Search with EXA

Conceptual topics (patterns, architectures, methodologies):

mcp__exa__web_search_exa with query: "{topic} best practices guide tutorial"

Code/implementation topics:

mcp__exa__get_code_context_exa with query: "{topic} implementation examples"

Combine both for comprehensive coverage.

2. Structure Output

Write research as markdown with this structure:

---
slug: {normalized-slug}
title: {Human Readable Title}
aliases: [{alternative names}]
tags: [{relevant tags}]
researched_at: {ISO timestamp}
expires_at: {ISO timestamp + 30 days}
sources:
  - url: {source URL}
    title: {source title}
---

# {Title}

## Overview
[2-3 paragraph executive summary]

## Key Concepts
[Core ideas, definitions, terminology]

## Patterns & Best Practices
[Recommended approaches, common patterns]

## Implementation Guidance
[Practical how-to, code examples if relevant]

## Trade-offs & Considerations
[When to use, when not to use, alternatives]

## References
[Source links with brief descriptions]

3. Cache Results

CRITICAL: NEVER write files directly into ~/.claude/plugins/research/entries/. ALWAYS use cache_manager.py put --content-file.

# Step 1: Write content to temp file using the Write tool
# Create /tmp/research-{slug}.md with the structured content

# Step 2: Cache and clean up in one call
python3 {scripts_dir}/cache_manager.py put "{slug}" \
  --title "{Title}" --content-file /tmp/research-{slug}.md \
  --aliases "alias1,alias2" --tags "tag1,tag2" && rm /tmp/research-{slug}.md

Read the full file on GitHub · 111 lines

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. 10d ago First seen · 111 lines · 48 tokens per session scan A e2d406e39047

Subscribe to this mod's changes

deep-researcher is an agent published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed 27d ago), licensed MIT. It adds 48 tokens to every session and 771 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 2026-08-30.

Related

Other agents, from other repositories

hydra-scout

🟢 Hydra's fastest head — ultra-fast codebase exploration, information retrieval, and codebase map building/maintenance. Use proactively whenever Claude needs to search files, read code, find patterns, grep for strings, list directories, understand project structure, answer "where is X?" questions, or build/update the…

AR6420/Hail_Hydra · 127 tokens

hydra-runner

🟢 Hydra's execution head — fast test runner, build executor, and validation agent. Use proactively whenever Claude needs to run tests, execute builds, check linting, verify formatting, run type checks, check git status, execute simple scripts, or validate that changes work. Runs on the cheap tier for speed — ideal…

AR6420/Hail_Hydra · 105 tokens

agent-critic

Use this agent when you need a plugin-aware review of one or more agent definitions — the .md files under a plugin's agents/ directory. Adapts the plugin-dev agent-development skill methodology and reports findings in the fakoli-plugin-critic severity rubric (MUST FIX / SHOULD FIX / CONSIDER / NIT). Agent-critics…

fakoli/fakoli-plugins · 529 tokens

perf-orchestrator

Coordinate /perf investigations across all phases, enforcing non-negotiable perf rules.

composio-community/awesome-claude-plugins · 21 tokens

security-master

Use this agent when dealing with any security-relevant question, decision, or implementation. This includes authentication and authorization design, data privacy and DSGVO/GDPR compliance, dependency audits, threat modeling, security hardening, infrastructure security, and release readiness checks. This agent MUST be…

jonase47/ccpr · 542 tokens

test-writer-fixer

Use this agent when code changes have been made and you need to write new tests, run existing tests, analyze failures, and fix them while maintaining test integrity. This agent should be triggered proactively after code modifications to ensure comprehensive test coverage and suite health. Examples:\n\n \nContext: The…

composio-community/awesome-claude-plugins · 0 tokens