Borrowing it
Nothing to install: this file belongs to hazelcast/hive. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hazelcast/hive/master/.claude/commands/migrate-to-v4.mdgit clone --depth 1 https://github.com/hazelcast/hiveWrote 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/commands/hazelcast/hive/migrate-to-v4)<a href="https://agentmods.dev/commands/hazelcast/hive/migrate-to-v4"><img src="https://agentmods.dev/badge/commands/hazelcast/hive/migrate-to-v4/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/commands/hazelcast/hive/migrate-to-v4"><img src="https://agentmods.dev/badge/commands/hazelcast/hive/migrate-to-v4.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 | $0.00000 | $0.00913 |
| Opus 5.5 | $0.00000 | $0.00365 |
| Sonnet 5.5 | $0.00000 | $0.00183 |
| Haiku 4.5 | $0.00000 | $0.00091 |
Grade A, and why
migrate-to-v4 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hive v4 Migration Assistant
You are helping a client app: mc (../management-center) or cloud (../hazelcast-cloud-frontend) migrate its @hazelcast/ui dependency from v3 to v4.
Key concept: gradual migration via /old
v4 ships with a @hazelcast/ui/old subpath that re-exports all v3 components that have changed or been removed from the main entry point. This means clients do not need to migrate everything at once.
The strategy is:
- Upgrade the package to v4
- For each component with a breaking change: either migrate now or temporarily redirect the import to
@hazelcast/ui/old - Migrate components from
/oldto the new API at your own pace - Once all
/oldimports are gone, you're fully on v4
@hazelcast/ui/old components will be removed in v5 — they are a migration aid, not a permanent API.
Step-by-step process
1. Upgrade the package
npm install @hazelcast/ui@4
Run the test suite immediately after. Failures indicate where breaking changes are.
2. Load the migration guide
Ask the user for the path to docs/migration-v4.md from the hive repo, or read it if already available. This is the source of truth for all breaking changes.
3. Inventory all hive imports
Search the client codebase:
grep -r "@hazelcast/ui" src --include="*.tsx" --include="*.ts" -l
For each file, note which components are imported.
4. Triage each component
For every component that has a breaking change in the migration guide, decide with the user:
- Migrate now — apply the new API immediately
- Use
/oldtemporarily — redirect the import, migrate later
For components with no breaking changes — nothing to do.
5. Apply the chosen strategy
Option A: Migrate now
Apply the prop/behavior/CSS changes from docs/migration-v4.md at every usage site.
Option B: Redirect to /old
Change the import in each affected file:
// Before
import { Tooltip } from '@hazelcast/ui'
// After (temporary — migrate before v5)
import { Tooltip } from '@hazelcast/ui/old'
// TODO: migrate to @hazelcast/ui v4 Tooltip
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.
- 2mo ago First seen · 134 lines · 0 tokens per session scan A f54f0ebb9635
migrate-to-v4 is a command published in the GitHub repository hazelcast/hive (19 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 913 tokens. 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.
migrate-to-v4 compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| migrate-to-v4hazelcast/hive | Command | 19 | yesterday | Apache-2.0 | A | 0 | Claude Code |
| dev-react-headlessdaangn/seed-design | Command | 1.2k | today | Apache-2.0 | A | 7 | Claude Code |
| write-react-component-docsdaangn/seed-design | Command | 1.2k | today | Apache-2.0 | A | 13 | Claude Code |
| seed-componentdaangn/seed-design | Command | 1.2k | today | Apache-2.0 | A | 12 | Claude Code |
| gen-videoAdityaraj0421/naksha-studio | Command | 353 | 19d ago | MIT | A | 56 | Claude Code |
| plan-featureHoangNguyen0403/agent-skills-standard | Command | 583 | yesterday | MIT | A | 0 | Claude Code |
| responsive-design-specialistimsaif/design-with-claude | Command | 11 | yesterday | MIT | A | 36 | Claude Code |