system-upgrade

system-upgrade is a command for coding agents from notque/vexjoy-agent. It costs 33 tokens per session (606 once invoked), scanned A, original, MIT.

A six-phase workflow for updating coding agents, skills, and hooks when software changes, goals shift, or lessons from past work need to be incorporated. It covers reviewing the change, auditing affected parts, planning, implementation, validation, and deployment.

In plain words
What is it for?
Use it after a Claude Code release, a change in technical focus, or a retrospective to audit the system, approve updates, validate them, and create a pull request.
Why use it?
It helps keep an agent setup aligned with new tools, technologies, workflows, and accumulated lessons. Proposed changes are reviewed before files are modified.

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/notque/vexjoy-agent/system-upgrade
Clone the repo
git clone --depth 1 https://github.com/notque/vexjoy-agent

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.

agentmods badge for system-upgrade

README.md
[![agentmods](https://agentmods.dev/badge/commands/notque/vexjoy-agent/system-upgrade.svg)](https://agentmods.dev/commands/notque/vexjoy-agent/system-upgrade)
Your own site
<a href="https://agentmods.dev/commands/notque/vexjoy-agent/system-upgrade"><img src="https://agentmods.dev/badge/commands/notque/vexjoy-agent/system-upgrade.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 606 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 $0.00033 $0.00606
Opus 5 $0.00016 $0.00303
Sonnet 5 $0.00007 $0.00121
Haiku 4.5 $0.00003 $0.00061

Measured 4d ago against content hash eeb7e25872e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

system-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 4d 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/system-upgrade.md · 82 lines

What it actually says

/system-upgrade

Entry point for the System Upgrade Pipeline.

Usage

/do upgrade the system — claude just shipped [feature]
/do system upgrade — I'm now working with [new domain]
/do apply retro learnings to upgrade the system

What It Does

6-Phase Pipeline:

  1. CHANGELOG — Parse the trigger, extract actionable change signals
  2. AUDIT — Scan agents/skills/hooks for affected components
  3. PLAN — Rank changes (Critical/Important/Minor), present to user for approval
  4. IMPLEMENT — Dispatch domain specialists in parallel for approved changes
  5. VALIDATE — Score modified components before/after with agent-evaluation
  6. DEPLOY — Commit, sync to ~/.claude, create PR

Three Trigger Types

Type When Input
claude-release Claude Code ships new version "Claude added Notification hook event"
goal-change Your workflow/focus shifts "I'm now working with Rust"
retro-driven Retro learnings ready to embed "Apply retro" or "/retro graduate" output

Key Behavior

Phase 3 always gates on your approval. The pipeline shows you a ranked table of proposed changes with effort estimates before touching any files. You can approve all, pick specific items, or stop.

Examples

/do upgrade the system — Claude Code shipped structured output support for tools
/do system upgrade — I want to add Rust support to the agent system
/do apply retro learnings to upgrade the system
/do claude update — new hook event Notification was added
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. 4d ago First seen · 82 lines · 33 tokens per session scan A eeb7e25872e6

Subscribe to this mod's changes

system-upgrade is a command published in the GitHub repository notque/vexjoy-agent (419 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 606 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 2026-08-30.