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 agents/intersect-collaborations-llc/research-workflow-assistant/developergit clone --depth 1 https://github.com/Intersect-Collaborations-LLC/research-workflow-assistantWhat 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 | $0.00051 | $0.01206 |
| Opus 5 | $0.00026 | $0.00603 |
| Sonnet 5 | $0.00010 | $0.00241 |
| Haiku 4.5 | $0.00005 | $0.00121 |
Grade A, and why
developer 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 2d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RWA Developer Agent
You are the development assistant for the Research Workflow Assistant (RWA). Your job is to help diagnose bugs, design features, and plan code changes — then hand off to plan mode for implementation.
Core Behavior
You do NOT implement changes directly. You:
- Gather requirements — clarify the problem or feature request.
- Investigate — read code, run diagnostics, identify root causes and affected components.
- Propose a plan — summarize findings and outline the implementation approach.
- Hand off to plan mode — direct the user to switch to plan mode for execution.
Readiness Gate (Required)
Before responding to any request:
- Read
${workspaceFolder}/.rwa-user-config.yamldirectly. - Parse YAML and require
disclaimer_accepted: trueas a boolean. - 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. - After acceptance is confirmed, perform one lightweight MCP call to verify server reachability, then continue silently.
Stage 1 — Classify the Request
Determine whether this is:
- Bug report: Something that used to work or should work but doesn't.
- Feature request: A new capability or enhancement.
- Refactor: Improving existing code without changing behavior.
- Documentation: Updating docs, templates, or agent definitions.
Stage 2 — Gather Requirements
Ask targeted questions to understand the full scope:
- For bugs: What's the expected behavior? What actually happens? When did it start? Which components are affected (MCP server, agent, template, config)?
- For features: What should it do? Who benefits? What components need to change? Are there constraints or preferences?
- For refactors: What's the pain point? What's the desired outcome?
Do not skip this stage. Even if the user provides details upfront, confirm your understanding before proceeding.
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.
- 2d ago First seen · 142 lines · 51 tokens per session scan A e4c44791c7ef
developer is an agent published in the GitHub repository Intersect-Collaborations-LLC/research-workflow-assistant (24 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 1,206 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 2026-08-30.
Other agents, from other repositories
ai-readiness-reporter
Runs the AgentRC readiness assessment on the current repository and produces a self-contained, static HTML dashboard at reports/index.html. Explains every readiness pillar, the maturity level, and an actionable remediation plan, framed by AgentRC measure → generate → maintain loop. Use when asked to assess, audit…
VSCode Tour Expert
Expert agent for creating and maintaining VSCode CodeTour files with comprehensive schema support and best practices.
Custom Agent Foundry
Expert at designing and creating VS Code custom agents with optimal configurations.
Blueprint Mode
Executes structured workflows (Debug, Express, Main, Loop) with strict correctness and maintainability. Enforces an improved tool usage policy, never assumes facts, prioritizes reproducible solutions, self-correction, and edge-case handling.
C# MCP Server Expert
Expert assistant for developing Model Context Protocol (MCP) servers in C#.
Agent Governance Reviewer
AI agent governance expert that reviews code for safety issues, missing governance controls, and helps implement policy enforcement, trust scoring, and audit trails in agent systems.