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 skills add YuDefine/nuxt-supabase-starter --skill version-upgradegit clone --depth 1 https://github.com/YuDefine/nuxt-supabase-starterWrote 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.
[](https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/version-upgrade)<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.
<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>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 | $0.00026 | $0.06170 |
| Opus 5 | $0.00013 | $0.03085 |
| Sonnet 5 | $0.00005 | $0.01234 |
| Haiku 4.5 | $0.00003 | $0.00617 |
Grade C, and why
version-upgrade scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
``` PHASE_RESULT: SUCCESS COMMIT: <sha> FILES_CHANGED: package.json, <lockfile> VERIFICATION: <依驗證步驟回報> ``` 失敗： ``` PHASE_RESULT: FAILURE STAGE_FAILED: <install | typecheck | build | test> ERROR_TAIL: <≤ 30 行 error How it starts
The opening of the file, as written. The whole thing — 382 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
四種升級需求一個 skill 涵蓋：
- Outdated batch：一個 consumer 累積很久沒升、
pnpm outdated一坨要批升 - Fleet sweep：看到 upstream release、想跨 consumer 跟上同一個版本
- Skills：
npx skills裝進來的第三方 skill 落後上游，或上游新增了我們還沒裝的 skill - Machine：本機裝的東西落後——mise 管的工具、全域 npm（含 agent runtime 自己）、 手裝 binary（rtk）、MCP server（codebase-memory-mcp）
skill 開頭依輸入分流，不要記四個 skill 名。
名字為什麼不是 dep-upgrade（2026-09-10 改名）
管的對象從第一天起就不只是 dependency——actions 與 skills 都不是——加上 Machine mode 之後更不是。三個候選被否決的理由值得留著，因為它們各自對應一個真實的邊界：
| 候選 | 否決理由 |
|---|---|
env-upgrade |
clade 全域「env」一致指 deploy environment（rules/core/deploy-env-identity.md、db-preview-env.md），也就是本 skill 明確不做的 C 軸。用它命名等於用唯一不做的事替 skill 命名 |
裸 upgrade |
撞 Claude Code 內建 /upgrade（訂閱升級） |
version-sweep |
「sweep」暗示 fleet，對 single-consumer 的 Outdated batch 與單機的 Machine mode 都不貼 |
三個軸（決定哪些事不在這支 skill 裡）
| 軸 | 版本宣告在哪 | git 載體 | 落點 |
|---|---|---|---|
| A. Repo-declared | package.json / lockfile / workflow yaml / .nvmrc |
✅ commit | Outdated / Fleet / Skills mode |
| B. Machine-installed | mise config / 全域 npm / ~/.local/bin / .mcp.json |
❌ | Machine mode |
| C. Remote-deployed | LXC / VM 上實際跑的版本 | ❌ | 不在本 skill：scripts/audit-remote-env-version-drift.ts 出訊號，落地 relay 給該 consumer 的 session |
C 軸刻意留在外面：升遠端 staging / prod 的 runtime 是 consumer 的 production 動作，clade 主線
替它動手正是 .claude/rules/local/clade-role-and-todo-discipline.md § 反模式 逐字禁止的那件事。
NEVER 因為「使用者問的是版本、本 skill 就叫 version-upgrade」把 C 軸吸進來。
Step 0 — Mode dispatcher（最先讀）
依輸入跟 cwd 分流：
| 觸發 | cwd 預期 | Mode | 跳到 |
|---|---|---|---|
純命令 /version-upgrade（無參數） |
consumer root（有 package.json + lockfile 或 .github/workflows/） |
Outdated batch | § Outdated · Step O.1 |
/version-upgrade actions |
consumer root（有 .github/workflows/） |
Outdated batch（only actions） | § Outdated · Step O.1（skip O.1-npm） |
給 GitHub release URL（https://github.com/.../releases/tag/v<ver>） |
clade home | Fleet | § Fleet · Step F.1 |
給 <pkg>@<ver> / <pkg> v<ver> / <pkg> <ver> |
clade home | Fleet | § Fleet · Step F.1 |
| 給純 pkg name（「升 @nuxt/ui」、「無腦升 X」） | clade home | Fleet + Discovery | § Fleet · Step F.1 |
| 給 package manager / runtime 本身（「升 pnpm」、「fleet packageManager 統一」、「Node 版本統一」） | clade home | Fleet · Toolchain | § Fleet · Step F.1，再讀 fleet-mode.md § Toolchain sweep 分支 |
/version-upgrade skills，或提到 skill 上游 / 落後 / 新增（「supabase skill 上游更新了我們有跟嗎」「掃一下 skill 有沒有落後」） |
clade home | Skills | § Skills · Step S.1 |
/version-upgrade machine，或提到本機裝的東西落後（「supabase cli 該升了嗎」「rtk / codebase-memory-mcp 有新版嗎」「mise 那堆工具掃一下」「全域 npm / claude-code 自己的版本」） |
任意（本機唯一） | Machine | § Machine · Step M.1 |
| 無參數但 cwd = clade home | — | STOP + 問意圖 | 見下方 § Disambiguation |
What ships with it
4 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.
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 · 382 lines · 26 tokens per session scan C 6dbc5d3ebc0c
version-upgrade is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 6,170 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-11.
Other skills, from other repositories
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…
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
create-milestone
Create a GitHub milestone for an upcoming release. Suggests the next version based on the latest release, gathers all merged PRs and closed issues since that release, presents a draft with two tables (Issues and PRs) for user approval, then creates the milestone and assigns all approved items.
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.
nw-finalize
Archives a completed feature to docs/evolution/, migrates lasting artifacts to permanent directories, and cleans up the temporary workspace. Use after all implementation steps pass and mutation testing completes.
team-release
Orchestrate the release team: coordinates release-manager, qa-lead, devops-engineer, and producer to execute a release from candidate to deployment.