An upgrade agent for NCC, a tool called nextjs-claude-code. It detects whether NCC was installed as a project plugin or through npx, then follows the matching update process.

Use it to check the installed NCC version, fetch and apply updates, and refresh project skills when the installation supports that workflow.

It removes the need to remember different upgrade commands for different installation methods and checks whether the tool is installed before proceeding.

ncc-upgrade — Agent for Claude Code by ByeongminLee: An upgrade agent for NCC, a tool called nextjs-claude-code.

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/byeongminlee/nextjs-claude-code/ncc-upgrade

Clone the repo

git clone --depth 1 https://github.com/ByeongminLee/nextjs-claude-code

Made for: Claude Code.

Or install nextjs-claude-code, the plugin that ships this one along with the rest of its 9 skills, 49 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/byeongminlee/nextjs-claude-code/ncc-upgrade.svg)](https://agentmods.dev/agents/byeongminlee/nextjs-claude-code/ncc-upgrade)

Your own site

<a href="https://agentmods.dev/agents/byeongminlee/nextjs-claude-code/ncc-upgrade"><img src="https://agentmods.dev/badge/agents/byeongminlee/nextjs-claude-code/ncc-upgrade.svg" alt="Measured on agentmods" height="20"></a>

Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 672 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.

Model	Per session	Once invoked
Fable 5	$0.00049	$0.00672
Opus 5	$0.00024	$0.00336
Sonnet 5	$0.00010	$0.00134
Haiku 4.5	$0.00005	$0.00067

Measured 3d ago against content hash 748649e29043, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ncc-upgrade 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 3d 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.

template/.claude/agents/ncc-upgrade.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the NCC upgrade agent. Your job is to upgrade the nextjs-claude-code installation to the latest version.

Step 1 — Detect installation mode

Determine how NCC was installed by checking the CLAUDE_PLUGIN_ROOT environment variable:

echo "CLAUDE_PLUGIN_ROOT=${CLAUDE_PLUGIN_ROOT:-not_set}"

If CLAUDE_PLUGIN_ROOT is set → Plugin mode
If not set but .claude/agents/ exists in the project → npx mode
If neither → NCC is not installed. Tell the user to run npx nextjs-claude-code first and stop.

Plugin mode (CLAUDE_PLUGIN_ROOT is set)

The plugin's agents, skills, hooks, and scripts are served directly from the plugin repository directory. To upgrade, pull the latest from git.

Check current state

cd "$CLAUDE_PLUGIN_ROOT" && git rev-parse --short HEAD

Fetch and check for updates

cd "$CLAUDE_PLUGIN_ROOT" && git fetch origin && git rev-list --count HEAD..origin/main

If behind, pull latest

cd "$CLAUDE_PLUGIN_ROOT" && git pull origin main

Update skills in the project (on-demand skills are copied to the project)
```
npx nextjs-claude-code@latest skill-update
```
Verify
```
npx nextjs-claude-code doctor
```
Report: Show before/after commit ref, and doctor results.

npx mode (files copied into project)

Run the upgrade CLI command
```
npx nextjs-claude-code@latest upgrade
```
This will:
- Check the latest version on npm
- Download and install the latest NCC package
- Overwrite system files: agents, scripts, hooks, rules
- Merge settings.json (adds new hooks without removing existing ones)
- Update the CLAUDE.md NCC block
- Update all installed skills
Verify
```
npx nextjs-claude-code doctor
```
Report: Show version before/after, and doctor results.

Hard constraints

NEVER modify files in spec/feature/ — these are user-owned
NEVER delete or overwrite spec/STATE.md
NEVER modify the user's custom content in CLAUDE.md (only the NCC block between  and  markers is managed)
If an upgrade fails, show the error and suggest manual steps
Always run doctor after upgrade to verify health

Read the full file on GitHub · 86 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.

3d ago First seen · 86 lines · 49 tokens per session scan A 748649e29043

Subscribe to this mod's changes

ncc-upgrade is an agent published in the GitHub repository ByeongminLee/nextjs-claude-code (3 stars, last pushed 5mo ago), licensed MIT. It adds 49 tokens to every session and 672 once invoked, about $0.0002 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.

ai-agents claude claude-code-plugin nextjs

stitch-kit

Use this agent for anything Stitch-related: ideating designs through conversation, generating UI screens from text, editing/iterating designs, generating design variants, managing Stitch Design Systems, converting designs to production code, extracting design tokens, and running the full design-to-ship pipeline.…

gabelul/stitch-kit · 237 tokens

fe-a11y-auditor

Specialized accessibility (a11y) audit — semantic HTML, ARIA, keyboard navigation, color contrast, focus management. More precise than fe-reviewer's a11y axis. READ-ONLY. With --live, also measures via Chrome DevTools MCP (Lighthouse a11y score, real accessibility tree, runtime console); falls back to static analysis…

sh5623/fe-rail · 85 tokens

fe-perf-auditor

In-depth React performance audit — bundle size, data fetching, image optimization, dynamic import, Suspense. Supports both Next.js (RSC, next/image) and Vite SPA (bundle analysis, fetchpriority). More precise than fe-reviewer's performance axis. READ-ONLY. With --live, also measures via Chrome DevTools MCP…

sh5623/fe-rail · 92 tokens

fe-git-operator

Dedicated git operations — splitting commits, safe staging, and writing Conventional Commits bodies (fix = symptom/cause/fix, feat = addition/core/impact). fe-pr-author owns PRs; this agent owns commits. Destructive commands forbidden.

sh5623/fe-rail · 55 tokens

fe-reviewer

4-axis frontend code review — type safety, performance, a11y, code quality. READ-ONLY, no direct edits. Delegate after fe-build completes, before the PR stage.

sh5623/fe-rail · 41 tokens

fe-vision

Precisely extracts layout, components, color, and typography from a single screen in Figma, screenshots, UI mockups, design drafts, or PDF/PPT (via conversion) — extraction mode. Or compares an implementation screenshot against a reference and judges visual fidelity as JSON — comparison mode (visual-verdict).…

sh5623/fe-rail · 90 tokens