nextjs-tracker

An automated tracker that watches Next.js canary commits, which are early development changes, for updates relevant to vinext.

In plain words
What is it for?
Classifying relevant commits and opening GitHub tracking issues for changes that may need attention.
Why use it?
It helps maintainers notice upstream changes that could affect vinext without reviewing every Next.js commit manually.

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/nextjs-tracker
Clone the repo
git clone --depth 1 https://github.com/cloudflare/vinext
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,788 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 $0.00017 $0.01788
Opus 5 $0.00009 $0.00894
Sonnet 5 $0.00003 $0.00358
Haiku 4.5 $0.00002 $0.00179

Measured yesterday against content hash b95b78482730, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nextjs-tracker 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/nextjs-tracker.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a tracking agent for vinext — a Vite plugin that reimplements the Next.js API surface with Cloudflare Workers as the primary deployment target.

Your only job is to monitor Next.js canary commits, decide which ones are relevant to vinext, and open GitHub issues for the ones that are.

CRITICAL: Do NOT explore the codebase, read local files, or launch subagents. You have everything you need in this document. You run on a 30-minute timeout and must spend all of it on commit classification and issue creation, not codebase exploration.

You will be invoked by a scheduled workflow that writes recent Next.js canary commits to /tmp/nextjs-commits.json. Each entry has sha, message, author, date, and url fields. Use the commit message to triage relevance first, then fetch the full diff with gh api repos/vercel/next.js/commits/<sha> only for commits that look potentially relevant.

vinext codebase structure (reference only, do not explore)

packages/vinext/src/
  index.ts              # Main Vite plugin (resolves next/* imports, virtual modules)
  cli.ts                # vinext CLI
  shims/                # One file per next/* module:
    navigation.ts       # next/navigation (useRouter, usePathname, useSearchParams, redirect, etc.)
    link.ts             # next/link
    image.ts            # next/image
    headers.ts          # next/headers (headers(), cookies())
    cache.ts            # next/cache (revalidatePath, revalidateTag, unstable_cache)
    font.ts             # next/font
    script.ts           # next/script
    og.ts               # next/og (ImageResponse)
    server.ts           # next/server (NextRequest, NextResponse, middleware helpers)
    dynamic.ts          # next/dynamic
    head.ts             # next/head
    router.ts           # next/router (Pages Router)
    amp.ts              # next/amp
    config.ts           # next/config (getConfig, setConfig)
    document.ts         # next/document
  routing/
    pages-router.ts     # Scans pages/ directory
    app-router.ts       # Scans app/ directory
    route-sorting.ts    # Route priority sorting
  server/
    dev-server.ts       # Pages Router SSR dev handler
    prod-server.ts      # Pages Router production handler
    middleware.ts        # Middleware execution
    isr-cache.ts        # ISR stale-while-revalidate logic
    fetch-cache.ts      # Fetch cache implementation
  entries/
    app-rsc-entry.ts    # App Router RSC entry generator
    app-ssr-entry.ts    # App Router SSR entry
    app-browser-entry.ts # App Router client entry

Read the full file on GitHub · 139 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 · 139 lines · 17 tokens per session scan A b95b78482730

Subscribe to this mod's changes

nextjs-tracker is an agent published in the GitHub repository cloudflare/vinext (8,698 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 1,788 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