nextjs

An orchestration entry point for Next.js and React frontend work. Next.js is a framework for building web applications, including pages that run on the server or in the browser.

In plain words
What is it for?
Use it for Next.js or React interfaces, including App Router, server components, TypeScript, and semantic CSS tasks.
Why use it?
It routes the task through specialist agents and separate planning, implementation, standards, and verification stages. It is intended for frontend work rather than general coding.

Command

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 commands/adilkalam/orca/nextjs
Clone the repo
git clone --depth 1 https://github.com/adilkalam/orca
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,051 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 $0.00014 $0.09051
Opus 5 $0.00007 $0.04526
Sonnet 5 $0.00003 $0.01810
Haiku 4.5 $0.00001 $0.00905

Measured 2d ago against content hash 057c4ddf9b4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nextjs 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.

commands/nextjs.md · 886 lines

How it starts

The opening of the file, as written. The whole thing — 886 lines — stays where its author put it; the contents beside it link to each section on GitHub.

STOP - DELEGATION ONLY

Before you do ANYTHING else, read this.

This slash command EXISTS to delegate work to agents. Not to do work directly.

NEVER acceptable:

  • "This is simple, I'll just do it directly"
  • "Let me quickly fix this"
  • "I can handle this without agents"
  • Using Edit/Write tools to make changes yourself

ALWAYS required:

  1. Parse the arguments
  2. Determine routing (--tweak, default, --complex)
  3. Spawn specialists single-level via the Agent tool (you are the orchestrator, in the main thread — no orchestrator subagent; OS 7.1)

Even --tweak delegates to a builder. It skips gates, not agents.

If you are about to Edit/Write, STOP. Delegate instead.


/nextjs - Next.js Lane Orchestrator (OS 7.1)

Use this command for Next.js / React frontend UI work (App Router, RSC, TypeScript, semantic CSS).

Flat pattern: this command runs in the main thread and IS the orchestrator. It spawns the 8 real nextjs agents single-level via Agent(): nextjs-architect (planning / analysis), nextjs-builder (implementation — owns CSS / layout / tokens), nextjs-standards-enforcer (standards gate), nextjs-verification-agent (verification), and the specialists nextjs-typescript-specialist, nextjs-performance-specialist, nextjs-accessibility-specialist, nextjs-seo-specialist. Design adjudication for UI-affecting tasks is the shared web design lane floor (design-validator + the designcheck detector, docs/reference/design-lane.md) — there are no CSS / layout / design-review specialist agents; that work is owned by the builder + the design floor. See docs/pipelines/nextjs-pipeline.md and docs/reference/phase-configs/nextjs-phase-config.yaml.

Usage

/nextjs "update the pricing page layout"           # Default: light path + gates
/nextjs --tweak "fix button spacing"                # Fast: light path, no gates
/nextjs --complex "multi-page feature"             # Full: architect + builder + all gates
/nextjs "implement requirement 2025-11-25-0930-dashboard"  # Full path with spec

Read the full file on GitHub · 886 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. 2d ago First seen · 886 lines · 14 tokens per session scan A 057c4ddf9b4b

Subscribe to this mod's changes

nextjs is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 9,051 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 2026-08-31.