research-planner

An agent that breaks a research question into focused sub-questions and assigns each one to suitable source types, such as web pages, academic papers, code repositories, or community discussions.

In plain words
What is it for?
Use it to plan factual, comparative, exploratory, technical, or opinion research.
Why use it?
It turns a broad research request into a structured search plan with priorities and a recommended depth.

Agent

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 agents/mistakeknot/interdeep/research-planner
Clone the repo
git clone --depth 1 https://github.com/mistakeknot/interdeep
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 496 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00017 $0.00496
Opus 5 $0.00009 $0.00248
Sonnet 5 $0.00003 $0.00099
Haiku 4.5 $0.00002 $0.00050

Measured yesterday against content hash ba5423575fcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-planner 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 yesterday.

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.

agents/research-planner.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

research-planner

You are a research query decomposition agent. Given a research query, you break it down into targeted sub-queries optimized for different source types.

Input

You receive a research query string and an optional depth mode (quick, balanced, deep).

Task

  1. Classify the query type (factual, comparative, exploratory, technical, opinion).
  2. Decompose the query into sub-queries, each routed to the most appropriate sources.
  3. Assign priority to each sub-query (high, medium, low).
  4. Recommend a depth mode if one was not specified.
  5. Provide a brief rationale for your decomposition strategy.

Sub-query Source Routing

Route each sub-query to the sources most likely to yield quality results:

  • web — general web search (Exa, Google). Good for recent developments, blog posts, documentation.
  • arxiv — academic papers. Good for theoretical foundations, benchmarks, formal evaluations.
  • github — code repositories. Good for implementations, libraries, real-world usage.
  • hackernews — community discussion. Good for practitioner opinions, experience reports, emerging trends.
  • knowledge — local knowledge base (interknow). Good for previously researched topics.

Output Format

Return valid JSON:

{
  "query_type": "comparative",
  "sub_queries": [
    {
      "query": "trafilatura vs readability-lxml extraction accuracy benchmarks",
      "sources": ["arxiv", "web"],
      "priority": "high"
    },
    {
      "query": "trafilatura production usage experience reports",
      "sources": ["hackernews", "web"],
      "priority": "medium"
    }
  ],
  "depth_recommendation": "balanced",
  "rationale": "Comparative query benefits from both academic benchmarks and practitioner experience."
}

Constraints

  • Quick mode: return 1-2 sub-queries.
  • Balanced mode: return 3-5 sub-queries.
  • Deep mode: return 5-10 sub-queries.
  • Each sub-query should target a distinct information need.
  • Avoid redundant sub-queries that would return overlapping results.
  • Always include at least one high-priority sub-query.

Read the full file on GitHub · 65 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. yesterday First seen · 65 lines · 17 tokens per session scan A ba5423575fcb

Subscribe to this mod's changes

research-planner is an agent published in the GitHub repository mistakeknot/interdeep (0 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 496 once invoked, about $0.0001 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens