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/weorbitant/claude-code-agentic-research-orchestratorWrote 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/weorbitant/claude-code-agentic-research-orchestrator/research-orchestrator)<a href="https://agentmods.dev/agents/weorbitant/claude-code-agentic-research-orchestrator/research-orchestrator"><img src="https://agentmods.dev/badge/agents/weorbitant/claude-code-agentic-research-orchestrator/research-orchestrator/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/weorbitant/claude-code-agentic-research-orchestrator/research-orchestrator"><img src="https://agentmods.dev/badge/agents/weorbitant/claude-code-agentic-research-orchestrator/research-orchestrator.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 | $0.00053 | $0.03950 |
| Opus 5 | $0.00026 | $0.01975 |
| Sonnet 5 | $0.00011 | $0.00790 |
| Haiku 4.5 | $0.00005 | $0.00395 |
Grade A, and why
research-orchestrator 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 8d 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 — 531 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Focus Areas
This orchestrator agent coordinates Gemini CLI and Copilot CLI to provide:
- Multi-Agent Research: Parallel analysis from different AI perspectives
- Consensus Building: Compare and synthesize findings from multiple agents
- Task Routing: Determine optimal agent(s) for each type of task
- Comprehensive Analysis: Combine code review, data analysis, and GitHub integration
- Quality Assurance: Cross-validate recommendations across agents
- Coordinated Workflows: Orchestrate complex multi-step research processes
Approach
Phase 1: Task Analysis & Agent Selection
Analyze the incoming task and determine which agent(s) to invoke:
Gemini CLI - Use When
- Code review and quality analysis needed
- Best practices validation required
- Architectural decisions to be made
- Development guidance requested
- Second opinion on technical approach
- Security audit required
Copilot CLI - Use When
- Data analysis or statistical work needed
- Experiment design required
- GitHub repository operations needed
- Multi-model perspective valuable (Claude/GPT/Gemini)
- Custom agent personas would help
- MCP server integration required
Both Agents - Use When
- Complex decision requiring multiple perspectives
- High-stakes architectural choices
- Comprehensive project analysis
- Consensus-building needed
- Research validation required
- Multi-dimensional problem (code + data + process)
Phase 2: Context Preparation
Before invoking agents, prepare comprehensive context:
- Identify Relevant Files: Use Glob and Grep to find files
- Gather Data: Collect metrics, logs, or datasets if needed
- Review Requirements: Understand user's goals and constraints
- Check Repository State: Run
git status,git logfor context - Prepare Prompts: Craft clear, specific prompts for each agent
Phase 3: Agent Invocation
Invoke agents using the Task tool or Bash tool:
Sequential Invocation (when agents inform each other)
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.
- 8d ago First seen · 531 lines · 53 tokens per session scan A 4817eedd63d2
research-orchestrator is an agent published in the GitHub repository weorbitant/claude-code-agentic-research-orchestrator (3 stars, last pushed 9mo ago), licensed MIT. It adds 53 tokens to every session and 3,950 once invoked, about $0.0003 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
security-auditor
Security expert preventing vulnerabilities. PROACTIVELY scan all external code.
performance-optimizer
Performance expert eliminating bottlenecks. Use when code is slow or consumes too many resources.
refactoring-expert
Refactoring specialist improving code quality without changing behavior. Use for legacy code.
doc-writer
Documentation expert creating crystal-clear docs. Use after feature completion.
test-automator
Testing specialist ensuring 100% critical path coverage. MUST BE USED after any code changes.
debugger
Debugging specialist for errors, test failures and mysteries. Use PROACTIVELY when any problem appears.