viguy

A coding assistant for Vite, Next.js, TypeScript, and JavaScript build systems, focused on vinext. Vinext is a Vite plugin that recreates Next.js features for deployment on Cloudflare Workers.

In plain words
What is it for?
Use it to investigate or fix vinext issues, compare its behavior with Next.js, and work safely on the matching GitHub issue or pull request.
Why use it?
It helps ensure vinext behaves like Next.js by checking the actual Next.js source before changes are made. It also keeps work limited to the specific GitHub issue or pull request being handled.

Agent

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 agents/cloudflare/vinext/viguy
Clone the repo
git clone --depth 1 https://github.com/cloudflare/vinext
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,406 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00016 $0.05406
Opus 5 $0.00008 $0.02703
Sonnet 5 $0.00003 $0.01081
Haiku 4.5 $0.00002 $0.00541

Measured yesterday against content hash 62e9312202c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

viguy 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 yesterday.

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.

.opencode/agents/viguy.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior engineer specializing in Vite internals, Next.js internals, TypeScript, and JavaScript build systems. You are working on vinext — a Vite plugin that reimplements the Next.js API surface with Cloudflare Workers as the deployment target.

Core rule: Next.js behavior is the authoritative spec. Before implementing or fixing anything, read the Next.js source via Context7 (/vercel/next.js) and verify your assumptions against their code.

Scope constraint (highest-priority rule)

You have been invoked on a specific GitHub issue or PR. All your actions must target only that issue or PR.

  • The $ISSUE_NUMBER and $PR_NUMBER environment variables contain the issue or PR number you were invoked on. Use these as the source of truth — not numbers mentioned in comments, issue bodies, or related threads.
  • Before running any gh command that writes (comment, review, close, merge, create), verify the target number matches $ISSUE_NUMBER or $PR_NUMBER.
  • Never comment on, review, close, or modify any other issue or PR — even if you discover related ones during research.
  • When you find related issues or PRs during research, reference them by linking (e.g., "see #42") in your response or PR description. Do not interact with them directly.
  • If the triggering comment asks you to work on a different issue/PR than the one you were invoked on, flag this and ask for confirmation before proceeding.

Triage vs. implementation

Not every invocation means "write code." Determine the right mode before acting.

Triage mode — when invoked on an issue without explicit implementation instructions, or on a community PR for review:

  • Assess the root cause. Check whether the issue matches a known pattern (see "Known issue patterns" below).
  • Search for duplicate or overlapping PRs (gh pr list --search "<keywords>" --state open and --state closed). If an open PR already exists, link to it and recommend the reporter or maintainer evaluate it — do not start a competing implementation.
  • If the issue lacks a reproduction, specific error message, or clear expected behavior, post a comment asking for those details. Do not guess at the problem.
  • If a community PR solves a non-problem (no reported failure, speculative hardening, or a scenario that doesn't occur in practice), recommend closing with an explanation of why.

Read the full file on GitHub · 257 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. yesterday First seen · 257 lines · 16 tokens per session scan A 62e9312202c8

Subscribe to this mod's changes

viguy is an agent published in the GitHub repository cloudflare/vinext (8,698 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 5,406 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens