What is version-upgrade?

A workflow for upgrading versions across project dependencies, automation actions, installed tools, and agent skills. It first identifies what kind of upgrade is being requested and whether the change belongs in the repository or only on a machine.

It helps batch-update dependencies, bring several consumers to an upstream release, update installed skills, and refresh locally installed tools and servers.

Version changes do not all affect the same files or need the same checks. This separates repository updates from local machine updates and from software already deployed elsewhere.

version-upgrade — Skill for Claude Code by YuDefine

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.

Any agent

npx skills add YuDefine/nuxt-supabase-starter --skill version-upgrade

Clone the repo

git clone --depth 1 https://github.com/YuDefine/nuxt-supabase-starter

Made for: Claude Code.

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/skills/yudefine/nuxt-supabase-starter/version-upgrade/github.svg)](https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/version-upgrade)

Your own site

<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/version-upgrade"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/version-upgrade/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/version-upgrade"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/version-upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,471 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00115	$0.01471
Opus 5.5	$0.00046	$0.00588
Sonnet 5.5	$0.00023	$0.00294
Haiku 4.5	$0.00012	$0.00147

Measured yesterday against content hash 23ed3e906fc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

version-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 yesterday.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/inventory.py, scripts/mode_route.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/version-upgrade/SKILL.md · 54 lines

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.

version-upgrade — 統一版本升級入口

Step 0 算出 route=<理由>.<範圍> 再跳 Phase。每一步只讀該步命中的檔，NEVER 一次讀完 rules/、phases/。

Phase 0 — 入口

Step 0（Route）. READ 若啟動本 skill，讀取 rules/mode分流判準.md，執行 uv run <skill 根目錄>/scripts/mode_route.py [--plan <計畫檔>] -- <參數>，依 route=／phase= 分流。判不出 MUST 等 user 拍板；有上一輪計畫檔才帶 --plan，NEVER 因 cwd 是 worktree 就當續跑。
Step 0.1. READ 若範圍是 consumer，或 cwd_kind=consumer（含在 consumer 內觸發的 machine），進 Phase 之前每一次跑 node ~/offline/clade/scripts/consumer-policy-upgrade-prompt.ts --json，讀取 rules/更新政策詢問判準.md，依 ask: true／ask: false／exit 1／exit 2 處置。
Step 0.2（目標刷新）. READ 若 Phase 是 P、M 或 T，進 Phase 前每一次跑 node ~/offline/clade/scripts/audit-ci-toolchain-parity.ts --refresh-targets，讀取 rules/跨環境版本對齊判準.md Rule 7。
Step 0.3（計畫檔）. 若 Phase 是 B、C、F、F-routine 或 K，讀取 templates/upgrade-plan.md：resume 續用 --plan 那份，否則在 B.4（F 在 F.5）開新檔，落點 clade home 是承載 plan package（specs/plans/<work-id>）下的 upgrade-<YYYY-MM-DD>.md，consumer 是它自己的 plan package。
Step 0.4（Worktree gate）. READ 若 Phase 是 B、C、D、F、F-routine、K 或 T（會動 package.json／lockfile／workflow 或計畫檔），讀取 rules/A軸共用紀律判準.md，跑 node ~/offline/clade/vendor/scripts/wt-gate.ts --for version-upgrade，exit 0 才可改檔或 commit。Phase S、M、P 不跑這一步——S 的隔離紀律在 phases/skills.md 自帶。
Step 0.5（進 Phase）. MUST 先完整讀 rules/mode分流判準.md Rule 4 指向的 Phase 檔。READ 若進 Phase F 或要動 .mcp.json 的 chrome-devtools-mcp，讀取 rules/fleet准入與釘版判準.md。

Phase F-routine — 全 fleet 例行補落後（`routine.fleet`、`deprecated.fleet`、`security.fleet`）

clade 不替 consumer 升版，只彙總。

Step FR.1. 讀 registry/consumers.json＋consumers.local 列出 consumer；paused 標 skipped、非 Node 標 out.non-node，都不派。
Step FR.2. 開計畫檔（fleet 段），每個 consumer 一列 pending。
Step FR.3. 逐一 relay 給該 consumer 的 session（[[clade-role-and-todo-discipline]] § Consumer 工作命中時 MUST relay），brief 只寫 /version-upgrade --reason <理由> --scope consumer（mode_route.py 吃這兩個旗標直接判 route，不落 judge）＋「計畫檔路徑回報 clade」。NEVER 在 clade 主線改 consumer。
Step FR.4. 回報到就更新該列；全部結案才算完成。

Read the full file on GitHub · 54 lines

Files

What ships with it

29 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

yesterday Changed · +1 lines · +51 tokens per session 23ed3e906fc8
4d ago Changed · +20 lines · +38 tokens per session d8eccb24844c
21d ago Changed · -389 lines scan C → A f81da521b8c9
22d ago Changed · -1 lines 2cd25a094deb
27d ago Changed · +2 lines e68a7d70f09a
28d ago Changed 9a2559430e97
29d ago Changed · +15 lines 154415fda920
1mo ago Changed 499eefc185cb
1mo ago Changed ad6315d42e1a
1mo ago First seen · 406 lines · 26 tokens per session scan C 519edcfd1c32

Subscribe to this mod's changes

version-upgrade is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (44 stars, last pushed today), licensed MIT. It adds 115 tokens to every session and 1,471 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-11.

Claude Code Git and workflow Project management Releases TDD ai-assisted nuxt supabase template

capture-lessons

Ship and capture lessons workflow. Creates the PR, updates lessons learned, updates documentation, generates the sprint retrospective, and updates the backlog. Use at the end of a sprint cycle, or when the user says "ship", "capture", "lessons", "retro", "retrospective", "wrap up", or "done with this sprint". Also use…

rbah31/claude-code-workflow · 100 tokens

team-release

Orchestrate the release team — release-manager, qa-lead, devops-engineer, producer — to execute a release from candidate to deployment.

Donchitos/Claude-Code-Game-Studios · 33 tokens

close-task-commit-push-pr

Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.

devoxx/DevoxxGenieIDEAPlugin · 64 tokens

prd-v08-changelog-as-marketing

Design the changelog as a distribution surface bridging engineering releases (DEP-/FEA-) to marketing channels (GTM-) during PRD v0.8 Deployment & Ops. Triggers on requests to set up a changelog system, publish releases, or when user asks "how should we publish releases?", "changelog as marketing", "release notes"…

mattgierhart/PRD-driven-context-engineering · 114 tokens

apm-customization

Guide changes to an APM source repository, including templates, builds and custom releases.

sdi2200262/agentic-project-management · 22 tokens

story-pr-orchestrator

WHEN delivering an approved multi-story feature or several specs as dependency-gated pull requests; NOT for a single story, product discovery, or generic task delegation; coordinates one isolated task, worktree, branch, and PR per ready story.

mintuz/skills · 53 tokens