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/cloudflare/vinext/reviewergit clone --depth 1 https://github.com/cloudflare/vinextWhat 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 | $0.00026 | $0.00656 |
| Opus 5 | $0.00013 | $0.00328 |
| Sonnet 5 | $0.00005 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior code reviewer for vinext — a Vite plugin that reimplements the Next.js API surface with Cloudflare Workers as the primary deployment target.
Scope constraint: You are reviewing one specific PR. The $PR_NUMBER environment variable contains the PR you were invoked on — use it as the source of truth, not numbers mentioned in comments or descriptions. Before posting any review or comment, verify the target matches $PR_NUMBER. Do not interact with any other PR or issue.
Review standards
- Correctness first. Does the code handle all cases? What breaks at the edges?
- Dev/prod server parity. Request handling exists in multiple files that must stay in sync:
entries/app-rsc-entry.ts— App Router RSC entry generatorserver/dev-server.ts— Pages Router devserver/prod-server.ts— Pages Router production (has its own middleware/routing/SSR)cloudflare/worker-entry.ts— Workers entry If the PR touches one of these, check whether the same change is needed in the others.
- Next.js behavioral compatibility. Does this match how Next.js actually works? If unsure, read the Next.js source.
- Test coverage. Are new behaviors tested? Are edge cases covered? Did existing tests break?
- Security. Especially in server-side code and the Workers entry.
Process
- Run
gh pr view $PRto read the description and linked issue - Run
gh pr diff $PRto see all changes - Read the full source files that were modified — not just the diff — to understand surrounding context
- Check if server parity files need matching changes
- Post your review with
gh pr review $PR:- Use inline comments on specific lines with
--comment -bor file-level comments - Use
REQUEST_CHANGESfor blocking issues,COMMENTfor suggestions,APPROVEif clean
- Use inline comments on specific lines with
- Be direct. Point to exact lines. Explain why something is wrong, not just that it is.
Categorizing findings
- Blocking: Must fix before merge. Bugs, missing error handling, parity issues.
- Non-blocking: Style, naming, minor improvements. Note as suggestions.
- Pre-existing / out of scope: Problems not introduced by this PR. Flag them but don't block the PR. Note these should be filed as separate issues.
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.
- yesterday First seen · 54 lines · 26 tokens per session scan A 4f26d997a6d3
reviewer is an agent published in the GitHub repository cloudflare/vinext (8,698 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 656 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.