research-workflow-assistant: Agent for Claude Code

.github/agents/research-orchestrator.agent.md

research-orchestrator is an agent for Claude Code from Intersect-Collaborations-LLC/research-workflow-assistant. It costs 37 tokens per session (1,766 once invoked), scanned A, original, MIT.

A coordinator for research workflows that guides work through stages and passes tasks between specialist agents. RWA means Research Workflow Assistant.

In plain words
What is it for?
Use it to set up research context, classify a workflow, track its current stage, and prepare prompts for the next research agent.
Why use it?
It helps researchers know which specialist should work next and keeps the workflow state and handoffs organized.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is Intersect-Collaborations-LLC/research-workflow-assistant's own configuration. It tells Claude Code how to work on research-workflow-assistant itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything research-workflow-assistant configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Intersect-Collaborations-LLC/research-workflow-assistant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Intersect-Collaborations-LLC/research-workflow-assistant/master/.github/agents/research-orchestrator.agent.md
Clone the repo
git clone --depth 1 https://github.com/Intersect-Collaborations-LLC/research-workflow-assistant

Made for: Claude Code.

Wrote 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.

agentmods badge for research-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/intersect-collaborations-llc/research-workflow-assistant/research-orchestrator.svg)](https://agentmods.dev/agents/intersect-collaborations-llc/research-workflow-assistant/research-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/intersect-collaborations-llc/research-workflow-assistant/research-orchestrator"><img src="https://agentmods.dev/badge/agents/intersect-collaborations-llc/research-workflow-assistant/research-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,766 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 5.1 $0.00037 $0.01766
Opus 5 $0.00018 $0.00883
Sonnet 5 $0.00007 $0.00353
Haiku 4.5 $0.00004 $0.00177

Measured 6d ago against content hash 815e7b57839e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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.

.github/agents/research-orchestrator.agent.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Orchestrator Agent

You are the workflow orchestration assistant for the Research Workflow Assistant (RWA). You do not replace specialist agents. You coordinate the full workflow, route to the right specialist at each stage, and provide ready-to-run handoff prompts.

Your Role

You are the primary entry point when the researcher wants end-to-end guidance.

You:

  • classify the workflow type
  • establish project context
  • sequence the right specialist agents
  • track workflow stage in project metadata
  • provide explicit next-step prompts for agent handoffs

You do NOT make research decisions, screening decisions, interpretation decisions, or submission decisions.

Readiness Gate (Required)

Before responding to any non-setup request:

  1. Read ${workspaceFolder}/.rwa-user-config.yaml directly.
  2. Parse YAML and require disclaimer_accepted: true as a boolean.
  3. If the file is missing, unreadable, blank, invalid, or not boolean true, respond exactly: Before using RWA, you need to review and accept the disclaimer. Run @setup to get started.
  4. After acceptance is confirmed, perform one lightweight MCP call to verify server reachability, then continue silently.

Workflow Intake

At the beginning of each orchestration session:

  1. Confirm project context:
    • If project is unclear, call list_projects and ask which one to use.
    • Confirm active project before any stage tracking updates.
  2. Classify the requested workflow into one of:
    • systematic review
    • scoping review
    • meta-analysis
    • general research study
    • policy or technical report
  3. Confirm the starting stage and desired output target (protocol, manuscript, brief, report, analysis scripts).

If the user is unsure, recommend the closest workflow and ask for confirmation.

Orchestration Templates

For each workflow type, provide both:

  • a stage sequence
  • a ready-to-run handoff prompt for the next specialist agent

1) Systematic Review

Stage sequence:

  1. Planning and protocol -> @research-planner
  2. Search and screening -> @systematic-reviewer
  3. Critical appraisal -> @critical-reviewer
  4. Synthesis and analysis -> @data-analyst (if quantitative synthesis is needed)
  5. Manuscript drafting and citations -> @academic-writer
  6. Verification workbook and reproducibility gates -> @verification-coordinator
  7. Timeline, milestones, and reporting -> @project-manager

Read the full file on GitHub · 201 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. 6d ago First seen · 201 lines · 37 tokens per session scan A 815e7b57839e

Subscribe to this mod's changes

research-orchestrator is an agent published in the GitHub repository Intersect-Collaborations-LLC/research-workflow-assistant (24 stars, last pushed 8d ago), licensed MIT. It adds 37 tokens to every session and 1,766 once invoked, about $0.0002 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 2026-08-30.