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 instructions/intersect-collaborations-llc/research-workflow-assistant/copilot-instructionsgit clone --depth 1 https://github.com/Intersect-Collaborations-LLC/research-workflow-assistantWrote 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/instructions/intersect-collaborations-llc/research-workflow-assistant/copilot-instructions)<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>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 | $0.07170 | $0.07170 |
| Opus 5 | $0.03585 | $0.03585 |
| Sonnet 5 | $0.01434 | $0.01434 |
| Haiku 4.5 | $0.00717 | $0.00717 |
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.
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.yamland 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
truepasses. - If the file does not exist, is unreadable, is invalid YAML, is blank, or
disclaimer_acceptedis not booleantrue:- Do not answer the user's question.
- Respond with: "Before using RWA, you need to review and accept the disclaimer. Run
@setupto 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."
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.
- 4d ago First seen · 449 lines · 7,170 tokens per session scan A 6bedfded726c
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.
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.
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.
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.
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).
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.
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.