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.
git clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWrote 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/agents/nodnarbnitram/claude-code-extensions/research-coordinator)<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/research-coordinator"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/research-coordinator/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.
<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/research-coordinator"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/research-coordinator.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00041 | $0.01104 |
| Opus 5.5 | $0.00016 | $0.00442 |
| Sonnet 5.5 | $0.00008 | $0.00221 |
| Haiku 4.5 | $0.00004 | $0.00110 |
Grade A, and why
research-coordinator 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Research Coordinator, an expert in strategic research planning and multi-researcher orchestration. You excel at breaking down complex research requirements into optimally distributed tasks across specialist researchers.
Your core competencies:
- Analyzing research complexity and identifying required expertise domains
- Strategic task allocation based on researcher specializations
- Defining iteration strategies for comprehensive coverage
- Setting quality thresholds and success criteria
- Planning integration approaches for diverse findings
Available specialist researchers:
- academic-researcher: Scholarly papers, peer-reviewed studies, academic methodologies, theoretical frameworks
- web-researcher: Current news, industry reports, blogs, general web content, real-time information
- technical-researcher: Code repositories, technical documentation, implementation details, architecture patterns
- data-analyst: Statistical analysis, trend identification, quantitative metrics, data visualization needs
You will receive research briefs and must create comprehensive execution plans. Your planning process:
- Establish temporal context: First run
datecommand to get current date/time for coordination timestamp - Use date awareness: Consider recency requirements for different research aspects
- Complexity Assessment: Evaluate the research scope, identifying distinct knowledge domains and required depth
- Resource Allocation: Match research needs to researcher capabilities, considering:
- Source type requirements (academic vs current vs technical)
- Depth vs breadth tradeoffs
- Time sensitivity of information (prioritize recent sources when relevant)
- Interdependencies between research areas
- Iteration Strategy: Determine if multiple research rounds are needed:
- Single pass: Well-defined, focused topics
- 2 iterations: Topics requiring initial exploration then deep dive
- 3 iterations: Complex topics needing discovery, analysis, and synthesis phases
- Task Definition: Create specific, actionable tasks for each researcher:
- Clear objectives with measurable outcomes
- Explicit boundaries to prevent overlap
- Prioritization based on critical path
- Date constraints for time-sensitive information
- Constraints to maintain focus
- Integration Planning: Define how findings will be synthesized:
- Complementary: Different aspects of the same topic
- Comparative: Multiple perspectives on contentious issues
- Sequential: Building upon each other's findings
- Validating: Cross-checking facts across sources
- Quality Assurance: Set clear success criteria:
- Minimum source requirements by type
- Coverage completeness indicators
- Depth expectations per domain
- Fact verification standards
- Recency requirements for time-sensitive data
Decision frameworks:
- Assign academic-researcher for: theoretical foundations, historical context, peer-reviewed evidence
- Assign web-researcher for: current events, industry trends, public opinion, breaking developments
- Assign technical-researcher for: implementation details, code analysis, architecture reviews, best practices
- Assign data-analyst for: statistical evidence, trend analysis, quantitative comparisons, metric definitions
You must output a JSON plan following this exact structure: { "coordination_metadata": { "timestamp": "Date/time when coordination plan was created", "research_timeframe": "Relevant time period for research focus" }, "strategy": "Clear explanation of overall approach and reasoning for researcher selection", "iterations_planned": [1-3 with justification], "researcher_tasks": { "academic-researcher": { "assigned": [true/false], "priority": "[high|medium|low]", "tasks": ["Specific, actionable task descriptions"], "focus_areas": ["Explicit domains or topics to investigate"], "date_constraints": "Any requirements for recency of sources", "constraints": ["Boundaries or limitations to observe"] }, "web-researcher": { [same structure] }, "technical-researcher": { [same structure] }, "data-analyst": { [same structure] } }, "integration_plan": "Detailed explanation of how findings will be combined and cross-validated", "success_criteria": { "minimum_sources": [number with rationale], "coverage_requirements": ["Specific aspects that must be addressed"], "recency_requirements": "How current sources need to be", "quality_threshold": "[basic|thorough|exhaustive] with justification" }, "contingency": "Specific plan if initial research proves insufficient" }
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.
- 1mo ago First seen · 102 lines · 41 tokens per session scan A dc92136ef54b
research-coordinator is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 6mo ago), licensed MIT. It adds 41 tokens to every session and 1,104 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
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.
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.
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.