Hot Updater Agent

CommunityPopular

gronxb

hot-updater-agent

Use when an AI agent needs to run or inspect full HotUpdater E2E jobs, or prepare and lease a profile-scoped manual QA environment through the local `hot-updater-agent` CLI.

Overview

Publisher	gronxb
Repository	`hot-updater`
Skill name	`hot-updater-agent`
Stars	1.8K
Forks	179
Bundled files	1
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by gronxb on GitHub. Read the source before you install it.

Installation

Install the Hot Updater Agent AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/gronxb/hot-updater/tree/main/.agents/skills/hot-updater-agent
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/gronxb/hot-updater.git /tmp/hot-updater
mkdir -p .claude/skills
cp -r /tmp/hot-updater/.agents/skills/hot-updater-agent .claude/skills/hot-updater-agent

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hot Updater Agent in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Hot Updater Agent on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Hot Updater Agent is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

HotUpdater Agent

Use this skill from the HotUpdater repository root when E2E should run through the dashboard queue or manual QA needs prepared provider infrastructure.

The CLI infers the current PR with gh pr view; there is no -pr flag.

Profiles

Valid profiles:

standalone-dynamodb
standalone-drizzle
standalone-prisma
standalone-kysely
standalone-mongodb
supabase
cloudflare
firebase
aws

Use the user-mentioned profile. If none is mentioned, use standalone-kysely.

Commands

Queue and wait for the normal AI verification loop:

bash
hot-updater-agent verify -platform <full|ios|android> -profile <profile> -env-target examples/v0.85.0/.env.hotupdater

Queue without waiting:

bash
hot-updater-agent e2e -platform <full|ios|android> -profile <profile> -env-target examples/v0.85.0/.env.hotupdater

Inspect current PR jobs:

bash
hot-updater-agent status -limit 5

Inspect recent successful baselines by profile:

bash
hot-updater-agent status -latest-success-by-profile -limit 20
hot-updater-agent -json status -latest-success-by-profile -limit 20

Inspect an exact job:

bash
hot-updater-agent wait <task-id> -tail 240
hot-updater-agent reason <task-id> -tail 240
hot-updater-agent log <task-id> -tail 240

Inspect provider and stage bottlenecks. Prefer profile lookup for provider diagnosis because it resolves to the latest successful job for that profile:

bash
hot-updater-agent timeline <profile|task-id> -limit 10
hot-updater-agent -json timeline <profile|task-id> -limit 10

Prepare one platform for agent-device-led manual QA:

bash
hot-updater-agent manual start <profile> \
  -platform <ios|android> \
  -ref "$(git rev-parse HEAD)" \
  -env-target examples/v0.85.0/.env.hotupdater \
  -ttl 2h

manual start waits until the profile service, native release artifact, and control server are ready. Human output returns all handoff fields and exact agent-device commands. Prefer structured output when another agent consumes the handoff:

bash
hot-updater-agent -json manual start <profile> -platform ios -ref "$(git rev-parse HEAD)"

The JSON session contains id, status/expiry/ref/log metadata, and handoff.worktreePath, scenarioRoot, envTargetPath, controlBaseUrl, runtimeConfigUrl, appBaseUrl, cleanupCommand, plus handoff.agentDevice with session, platform, device ID, app ID, binary path, and exact boot/install/open/snapshot/close commands.

Inspect or release the lease:

bash
hot-updater-agent manual status [session-id] [-limit 20]
hot-updater-agent manual stop <session-id>
hot-updater-agent manual --help

Only one manual session may be active. It blocks dashboard E2E execution until manual stop or TTL expiry. Always stop it in a finally-style cleanup path; iOS and Android manual sessions must run sequentially.

Workflow

Choose full E2E (verify) or prepared manual QA (manual start).
Check existing work: hot-updater-agent status -limit 5 and, for manual work, hot-updater-agent manual status -limit 5.
For provider diagnosis, read hot-updater-agent -json timeline <profile> -limit 10.
For a failed exact E2E job, read hot-updater-agent reason <task-id> -tail 240.
For manual QA, consume only the returned handoff and always stop the lease.
Re-run the same path until it succeeds or the blocker is clearly outside repository code.

Use timeline data to distinguish setup, deploy, service boot, app reload, and E2E command execution bottlenecks. Compare providerBottlenecks[*].totalMs, providerBottlenecks[*].slowestStage, and global bottlenecks.

Default suite contract

Full-platform verify reads e2e/scenario-names.json from the exact checked-out PR commit. Adding a scenario to that manifest automatically includes it in every full-platform verification profile. A missing, empty, malformed, or duplicate manifest is a verification failure; do not replace it with an agent-side fallback list.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

agents/openai.yaml1 KB

Frequently asked questions

What does the Hot Updater Agent AI skill do?

Use when an AI agent needs to run or inspect full HotUpdater E2E jobs, or prepare and lease a profile-scoped manual QA environment through the local `hot-updater-agent` CLI.

Why use Hot Updater Agent on TypingMind?

Because you install it once and use it with any model. Hot Updater Agent is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Hot Updater Agent in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/gronxb/hot-updater/tree/main/.agents/skills/hot-updater-agent. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Hot Updater Agent?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Hot Updater Agent?

As many as you like. As long as a model supports skills, you can use Hot Updater Agent with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Hot Updater Agent AI skill free?

It is published on GitHub by gronxb. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Land And Deploy

garrytan

CommunityPopular

Land and deploy workflow. (gstack)

Clawsweeper

Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions…

Openclaw Ci Limits

Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe…

Openclaw Testing

Choose proportional OpenClaw tests and checks, diagnose failures, and route environment-sensitive or release proof to its owner.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

HotUpdater Agent

Profiles

Commands

Workflow

Default suite contract

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now