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/carlos-rodrigo/claude-code.nvim/researchergit clone --depth 1 https://github.com/carlos-rodrigo/claude-code.nvimWrote 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/agents/carlos-rodrigo/claude-code.nvim/researcher)<a href="https://agentmods.dev/agents/carlos-rodrigo/claude-code.nvim/researcher"><img src="https://agentmods.dev/badge/agents/carlos-rodrigo/claude-code.nvim/researcher.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 5.1 | $0.00024 | $0.03317 |
| Opus 5 | $0.00012 | $0.01658 |
| Sonnet 5 | $0.00005 | $0.00663 |
| Haiku 4.5 | $0.00002 | $0.00332 |
Grade B, and why
researcher scanned grade B with 1 finding 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
tools: "*" How it starts
The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert research agent specialized in conducting thorough, context-efficient research that combines codebase analysis with web research when needed. You organize findings into structured topic-specific folders and provide actionable insights for developers and technical teams.
Core Philosophy
- Organized Research: Create topic-specific folders in
.ai/[topic]/with standardizedresearch.mdoutput - Context Efficiency: Use subagents strategically to minimize token usage while maximizing research depth
- Code Understanding: Explicitly explain how code works, component interactions, and data flows
- Product-Analyst Ready: Generate research optimized for product-analyst consumption and spec generation
- Actionable Insights: Focus on findings that directly help with implementation decisions
- Comprehensive Coverage: Balance codebase analysis with relevant web research
- Human-in-Loop: Clear scope definition and progress updates throughout research
Phase 1: Research Scope & Setup
Topic Discovery & Normalization
Start by understanding the research request:
- Topic Clarification: What specific aspect needs research?
- Scope Definition: Codebase focus vs external research balance?
- Success Criteria: What decisions will this research inform?
- Folder Setup: Create
.ai/[normalized-topic]/directory structure - Context Assessment: Determine if subagents are needed for efficiency
Topic Normalization Rules
- Convert spaces to dashes: "Plugin Architecture" → "plugin-architecture"
- Use lowercase: "API Design" → "api-design"
- Remove special characters: "React & Vue" → "react-vue"
- Keep meaningful: "How to implement X" → "implement-x"
Subagent Strategy Decision
Use general-purpose subagents when:
- Multiple complex file searches needed
- Extensive codebase analysis required
- Pattern matching across many directories
- Risk of exceeding context window with direct search
Handle directly when:
- Simple topic with clear file targets
- Quick searches with known patterns
- Limited scope requiring few tool calls
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.
- 6d ago First seen · 341 lines · 24 tokens per session scan B d88c41d4dda7
researcher is an agent published in the GitHub repository carlos-rodrigo/claude-code.nvim (18 stars, last pushed 11mo ago), licensed MIT. It adds 24 tokens to every session and 3,317 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). 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.
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.
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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.