Hot Updater Agent
Apps & Automationhot-updater-agentHot Updater Agent is an Agent Skill for apps & automation published in the gronxb/hot-updater repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Use when an AI agent needs to run, monitor, diagnose, or iterate HotUpdater E2E jobs through the local `hot-updater-agent` dashboard CLI instead of running device flows directly.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/gronxb/hot-updater/blob/HEAD/.agents/skills/hot-updater-agent/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/hot-updater-agent, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
HotUpdater Agent
Use this skill from the HotUpdater repository root when E2E should run through the dashboard queue.
The CLI infers the current PR with gh pr view; there is no -pr flag.
Profiles
Valid profiles:
standalone-s3standalone-drizzlestandalone-prismastandalone-kyselystandalone-mongodbsupabasecloudflarefirebaseaws
Use the user-mentioned profile. If none is mentioned, use standalone-s3.
Commands
Queue and wait for the normal AI verification loop:
hot-updater-agent verify -platform <full|ios|android> -profile <profile> -env-target examples/v0.85.0/.env.hotupdater
Queue without waiting:
hot-updater-agent e2e -platform <full|ios|android> -profile <profile> -env-target examples/v0.85.0/.env.hotupdater
Inspect current PR jobs:
hot-updater-agent status -limit 5
Inspect recent successful baselines by profile:
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:
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:
hot-updater-agent timeline <profile|task-id> -limit 10
hot-updater-agent -json timeline <profile|task-id> -limit 10
Workflow
- Check existing work:
hot-updater-agent status -limit 5. - For performance or provider diagnosis, read
hot-updater-agent -json timeline <profile> -limit 10. - For a failed exact job, read
hot-updater-agent reason <task-id> -tail 240. - Patch this repo based on the observed failure.
- Re-run the same
verifycommand until the dashboard job succeeds or the blocker is clearly outside repo 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.