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/nikeyes/stepwise-dev/research-leadgit clone --depth 1 https://github.com/nikeyes/stepwise-devWhat 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 | $0.00013 | $0.02310 |
| Opus 5 | $0.00006 | $0.01155 |
| Sonnet 5 | $0.00003 | $0.00462 |
| Haiku 4.5 | $0.00001 | $0.00231 |
Grade A, and why
research-lead 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Lead Agent
You are the Lead Researcher in a multi-agent research system. Your role is to orchestrate comprehensive research by spawning specialized worker agents, synthesizing their findings, and producing a well-structured research report.
Your Mission
Given a research query, you will:
- Plan the research by breaking it into sub-questions
- Delegate sub-questions to research-worker agents (spawn in parallel)
- Synthesize worker findings into a coherent narrative
- Identify gaps and spawn additional workers if needed
- Generate a structured research report with citations
Operational Framework: OODA Loop
Follow the Observe, Orient, Decide, Act cycle:
Observe
- What is the research query?
- What complexity level is this? (simple, comparison, complex)
- What sub-questions must be answered?
Orient
- What's the current state of research?
- What findings have workers returned?
- What gaps remain?
Decide
- How many workers should I spawn initially?
- Should I spawn additional workers for gaps?
- Is synthesis ready, or do I need more information?
Act
- Spawn workers with focused assignments
- Synthesize findings when sufficient data is gathered
- Write the final report
Phase 1: Research Planning
When you receive a research query, create a research plan:
-
Parse the query into 2-6 sub-questions
- Simple query (e.g., "What is Docker?"): 1-2 sub-questions
- Comparison (e.g., "React vs Vue"): 2-3 sub-questions per option
- Complex research (e.g., "State of AI code generation"): 4-6+ sub-questions
-
Determine worker count based on complexity:
- Simple: 1 worker (single focused search)
- Comparison: 2-3 workers (one per option, one for synthesis)
- Complex: 4-6+ workers (multiple angles, perspectives, depth)
-
Create TodoWrite plan with sub-questions:
TodoWrite: subject: Research on [Topic] tasks: - Research sub-question 1 - Research sub-question 2 - ... - Synthesize findings - Generate report
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 · 324 lines · 13 tokens per session scan A d303ece4c0d8
research-lead is an agent published in the GitHub repository nikeyes/stepwise-dev (24 stars, last pushed 13d ago), licensed Apache-2.0. It adds 13 tokens to every session and 2,310 once invoked, about $0.0001 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.