conduct-research

conduct-research is a command for coding agents from psd401/psd-claude-plugins. It costs 0 tokens per session (807 once invoked), scanned A, a copy of conduct-research, MIT.

A command that splits a research question into smaller questions and sends them to several AI research agents at the same time.

In plain words
What is it for?
Use it to investigate a topic, compare alternatives, check current changes, understand how something works, or find practical advice.
Why use it?
It removes the need to plan every search angle and combine separate research efforts yourself. It can cover facts, recent information, comparisons, practical details, strategies, and common mistakes.

Command

Part of the psd-productivity plugin — 38 skills, 1 command, 8 agents shipped together

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 commands/psd401/psd-claude-plugins/conduct-research
Clone the repo
git clone --depth 1 https://github.com/psd401/psd-claude-plugins

Or install psd-productivity, the plugin that ships this one along with the rest of its 38 skills, 1 command, 8 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 conduct-research

README.md
[![agentmods](https://agentmods.dev/badge/commands/psd401/psd-claude-plugins/conduct-research.svg)](https://agentmods.dev/commands/psd401/psd-claude-plugins/conduct-research)
Your own site
<a href="https://agentmods.dev/commands/psd401/psd-claude-plugins/conduct-research"><img src="https://agentmods.dev/badge/commands/psd401/psd-claude-plugins/conduct-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 807 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.00807
Opus 5 $0.00000 $0.00404
Sonnet 5 $0.00000 $0.00161
Haiku 4.5 $0.00000 $0.00081

Measured 4d ago against content hash 4f45eb3bf312, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conduct-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 4d 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.

Origin

This is a copy

100% identical to conduct-research — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/psd-productivity/skills/research/commands/conduct-research.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conduct Research Command

Orchestrate parallel multi-LLM research on a topic.

Usage

/conduct-research [topic or question]

Workflow

Step 1: Query Decomposition

Break the research topic into 3-7 focused sub-queries. Consider:

  • Factual: What are the basic facts?
  • Current: What's the latest information?
  • Comparative: How does it compare to alternatives?
  • Practical: How does it work in practice?
  • Optimization: What are the best strategies?
  • Gotchas: What are common mistakes or pitfalls?

Example for "maximize Alaska Airlines miles for Japan":

  1. Current Alaska redemption rates to Japan partners
  2. JAL vs Cathay vs other OneWorld options for Japan routes
  3. Best credit card strategies for earning Alaska miles
  4. Award availability patterns and booking tips
  5. Recent program changes or devaluations

Step 2: Parallel Agent Execution

Launch researcher agents in parallel using the Task tool. Each agent gets relevant sub-queries:

Perplexity Agent (current info)

  • Sub-queries about recent changes, current rates, latest news

Gemini Agent (comparisons)

  • Sub-queries comparing options, trade-offs

OpenAI Agent (structure)

  • Sub-queries about processes, frameworks, how things work

Claude Agent (synthesis)

  • Sub-queries about recommendations, implications

Use this pattern:

Launch 4 Task agents in parallel:
- Task: perplexity-researcher with [sub-queries 1, 2]
- Task: gemini-researcher with [sub-queries 3, 4]
- Task: openai-researcher with [sub-query 5]
- Task: claude-researcher with [synthesis query]

Step 3: Result Collection

Gather results from all agents (typically 15-45 seconds).

Step 4: Synthesis

Combine all findings into a cohesive report:

  1. Identify Consensus - What do multiple sources agree on?
  2. Flag Conflicts - Where do sources disagree?
  3. Score Confidence - High (4/4 agree), Medium (3/4), Low (2/4 or conflicting)
  4. Extract Actions - What should the user actually do?

Read the full file on GitHub · 123 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. 4d ago First seen · 123 lines · 0 tokens per session scan A 4f45eb3bf312

Subscribe to this mod's changes

conduct-research is a command published in the GitHub repository psd401/psd-claude-plugins (2 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 807 tokens. A static security scan graded it A with 0 findings. It is 100% identical to conduct-research, differing in 0 lines, and is treated as a copy.