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.
npx agentmods add commands/psd401/psd-claude-plugins/conduct-researchgit clone --depth 1 https://github.com/psd401/psd-claude-pluginsWrote 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.
[](https://agentmods.dev/commands/psd401/psd-claude-plugins/conduct-research)<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>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.
| Model | Per session | Once 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 |
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.
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.
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":
- Current Alaska redemption rates to Japan partners
- JAL vs Cathay vs other OneWorld options for Japan routes
- Best credit card strategies for earning Alaska miles
- Award availability patterns and booking tips
- 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:
- Identify Consensus - What do multiple sources agree on?
- Flag Conflicts - Where do sources disagree?
- Score Confidence - High (4/4 agree), Medium (3/4), Low (2/4 or conflicting)
- Extract Actions - What should the user actually do?
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.
- 4d ago First seen · 123 lines · 0 tokens per session scan A 4f45eb3bf312
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.