research-workflow-assistant copilot-instructions.md

research-workflow-assistant copilot-instructions.md is an instructions file for GitHub Copilot from Intersect-Collaborations-LLC/research-workflow-assistant. It costs 7,170 tokens per session, scanned A, original, MIT.

Project instructions for a research assistant that supports researchers from charities, government, universities, or independent projects. They define its role and require a disclaimer and setup check before most responses.

In plain words
What is it for?
They guide research-related conversations, check user settings, confirm required disclaimers, and verify access to the project's supporting service.
Why use it?
They prevent the assistant from presenting itself as a researcher or taking ownership of a person's work, while ensuring required configuration and connected services are ready.

Instructions file for GitHub Copilot

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 instructions/intersect-collaborations-llc/research-workflow-assistant/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/Intersect-Collaborations-LLC/research-workflow-assistant

Made for: GitHub Copilot.

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-workflow-assistant copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/intersect-collaborations-llc/research-workflow-assistant/copilot-instructions.svg)](https://agentmods.dev/instructions/intersect-collaborations-llc/research-workflow-assistant/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/intersect-collaborations-llc/research-workflow-assistant/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/intersect-collaborations-llc/research-workflow-assistant/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 7,170 This file is loaded in full into every session.
When invoked 7,170 The same file — it is already loaded in full.
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 $0.07170 $0.07170
Opus 5 $0.03585 $0.03585
Sonnet 5 $0.01434 $0.01434
Haiku 4.5 $0.00717 $0.00717

Measured 4d ago against content hash 6bedfded726c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-workflow-assistant copilot-instructions.md 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 4d 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/copilot-instructions.md · 449 lines

How it starts

The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Workflow Assistant: Global Agent Instructions

This file provides global instructions for all AI agents operating within this repository. These rules are non-negotiable and apply to every agent interaction.

Core Identity

You are the Research Workflow Assistant (RWA), not an author, collaborator, or co-investigator. You are a tool that helps human researchers work more efficiently while maintaining full intellectual ownership of their research. The project is commonly referred to as RWA. Both "RWA" and "Research Workflow Assistant" are interchangeable.

Audience: Any researcher (NGO staff, government analysts, academic faculty, public sector, independent researchers, students). Do not assume the user is in academia or pursuing a degree.

Disclaimer & Readiness Gate (Non-Negotiable)

Before responding to any user request (except the @setup agent itself), every agent must perform a quick readiness check:

1. Disclaimer Acceptance Check

  • Resolve the config path as ${workspaceFolder}/.rwa-user-config.yaml and read that file directly.
  • Do not rely on filename search alone for this check; hidden-file indexing can be inconsistent.
  • Parse YAML type-safely. Only the boolean value true passes.
  • If the file does not exist, is unreadable, is invalid YAML, is blank, or disclaimer_accepted is not boolean true:
    • Do not answer the user's question.
    • Respond with: "Before using RWA, you need to review and accept the disclaimer. Run @setup to get started."
    • Stop. Do not proceed with any other action.

2. MCP Server Reachability Check

  • After confirming the disclaimer is accepted, attempt one lightweight MCP tool call (e.g., detect_zotero_storage, list_projects, or any tool that returns quickly) to verify at least one MCP server is reachable.
  • If the check succeeds: Proceed with the user's request silently. Do not announce that the readiness check passed.
  • If the check fails (all tool calls error): Inform the user: "MCP servers are not responding. Please open the Command Palette (Ctrl+Shift+P) → 'MCP: List Servers' and ensure servers are started. Then open a new Copilot Chat session."

Read the full file on GitHub · 449 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. 4d ago First seen · 449 lines · 7,170 tokens per session scan A 6bedfded726c

Subscribe to this mod's changes

research-workflow-assistant copilot-instructions.md is an instructions file published in the GitHub repository Intersect-Collaborations-LLC/research-workflow-assistant (24 stars, last pushed 5d ago), licensed MIT. It adds 7,170 tokens to every session, about $0.0358 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.

Related

Other instructions, from other repositories

mcp-server-excel llm-testing-philosophy.instructions.md

Instructions for sbroenne/mcp-server-excel, covering llm testing philosophy, what are llm tests?, the golden rule, what never belongs in a test and ❌ xfail or skip markers.

sbroenne/mcp-server-excel · 3,451 tokens

mcp-server-excel readme-management.instructions.md

Instructions for sbroenne/mcp-server-excel, covering readme management - quick reference, core entry documents, feature documentation, critical rules and tool & action counts must match.

sbroenne/mcp-server-excel · 2,648 tokens

mcp-server-excel development-workflow.instructions.md

Instructions for sbroenne/mcp-server-excel, covering development workflow, branch protection, development process, pr review comment workflow and retrieve inline code review comments using github cli.

sbroenne/mcp-server-excel · 1,518 tokens

mcp-server-excel extension-development.instructions.md

Instructions for sbroenne/mcp-server-excel, covering vs code extension development instructions, extension overview, changelog and changesets (critical), version management and automatic version management (unified release workflow).

sbroenne/mcp-server-excel · 1,427 tokens

mcp-server-excel copilot-instructions.md

Copilot instructions for sbroenne/mcp-server-excel, covering github copilot instructions - excelmcp, repository map, environment, working rules and build and validation.

sbroenne/mcp-server-excel · 1,206 tokens

mcp-server-excel excel-connection-types-guide.instructions.md

Instructions for sbroenne/mcp-server-excel, covering excel connection types - llm quick reference, critical: loadto operation limitations, connection action compatibility, decision tree: connection vs power query and recommended workflows.

sbroenne/mcp-server-excel · 1,113 tokens