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 agents/mistakeknot/interdeep/research-plannergit clone --depth 1 https://github.com/mistakeknot/interdeepWhat 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 | $0.00017 | $0.00496 |
| Opus 5 | $0.00009 | $0.00248 |
| Sonnet 5 | $0.00003 | $0.00099 |
| Haiku 4.5 | $0.00002 | $0.00050 |
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.
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
- Classify the query type (factual, comparative, exploratory, technical, opinion).
- Decompose the query into sub-queries, each routed to the most appropriate sources.
- Assign priority to each sub-query (high, medium, low).
- Recommend a depth mode if one was not specified.
- 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.
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.
- yesterday First seen · 65 lines · 17 tokens per session scan A ba5423575fcb
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.