Agent skill

Monitor With Haoleme

Selectively monitor important long-running or resource-intensive commands with Haoleme by prefixing them with hao, so status, output, and completion notifications sync to the mobile app.

AGPL-3.0Auto-check passedData & Analytics

Install Monitor With Haoleme

skills CLI

$ npx skills add HaolemeApp/Haoleme --skill monitor-with-haoleme -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install HaolemeApp/Haoleme monitor-with-haoleme --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/HaolemeApp/Haoleme.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/monitor-with-haoleme .claude/skills/monitor-with-haoleme && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "monitor-with-haoleme" agent skill from https://github.com/HaolemeApp/Haoleme/tree/main/skills/monitor-with-haoleme into .claude/skills/monitor-with-haoleme/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "monitor-with-haoleme", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/HaolemeApp/Haoleme/tree/main/skills/monitor-with-haoleme

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add HaolemeApp/Haoleme --skill monitor-with-haoleme -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install HaolemeApp/Haoleme monitor-with-haoleme --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HaolemeApp/Haoleme.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/monitor-with-haoleme .agents/skills/monitor-with-haoleme && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "monitor-with-haoleme" agent skill from https://github.com/HaolemeApp/Haoleme/tree/main/skills/monitor-with-haoleme into .agents/skills/monitor-with-haoleme/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "monitor-with-haoleme", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add HaolemeApp/Haoleme --skill monitor-with-haoleme -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install HaolemeApp/Haoleme monitor-with-haoleme --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HaolemeApp/Haoleme.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/monitor-with-haoleme .cursor/skills/monitor-with-haoleme && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "monitor-with-haoleme" agent skill from https://github.com/HaolemeApp/Haoleme/tree/main/skills/monitor-with-haoleme into .cursor/skills/monitor-with-haoleme/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "monitor-with-haoleme", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/HaolemeApp/Haoleme.git --path skills/monitor-with-haoleme

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add HaolemeApp/Haoleme --skill monitor-with-haoleme -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install HaolemeApp/Haoleme monitor-with-haoleme --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HaolemeApp/Haoleme.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/monitor-with-haoleme .gemini/skills/monitor-with-haoleme && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "monitor-with-haoleme" agent skill from https://github.com/HaolemeApp/Haoleme/tree/main/skills/monitor-with-haoleme into .gemini/skills/monitor-with-haoleme/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "monitor-with-haoleme", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install HaolemeApp/Haoleme monitor-with-haoleme

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add HaolemeApp/Haoleme --skill monitor-with-haoleme -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/HaolemeApp/Haoleme.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/monitor-with-haoleme .github/skills/monitor-with-haoleme && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "monitor-with-haoleme" agent skill from https://github.com/HaolemeApp/Haoleme/tree/main/skills/monitor-with-haoleme into .github/skills/monitor-with-haoleme/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "monitor-with-haoleme", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add HaolemeApp/Haoleme --skill monitor-with-haoleme -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install HaolemeApp/Haoleme monitor-with-haoleme --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HaolemeApp/Haoleme.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/monitor-with-haoleme .opencode/skills/monitor-with-haoleme && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "monitor-with-haoleme" agent skill from https://github.com/HaolemeApp/Haoleme/tree/main/skills/monitor-with-haoleme into .opencode/skills/monitor-with-haoleme/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "monitor-with-haoleme", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: monitor-with-haoleme
GitHub stars: 157
Token cost: ~1.3k tokens
SKILL.md length: 582 words
Files: 3
Skills in repo: 1
Repo updated: Aug 14, 2026
First seen: Oct 7, 2026
Licence: AGPL-3.0

At a glance

Selectively monitor important long-running or resource-intensive commands with Haoleme by prefixing them with hao, so status, output, and completion notifications sync to the mobile app.

Works in 4 steps: Check availability with command -v hao… → If hao is missing, do not silently… → If monitoring fails because the device… → …
Environment installation
SKILL.md covers Decide Before Running, Prepare Haoleme, Run The Command and Handle Mixed Workflows, plus 1 more section
Calls pip, python and uv

What it does

Monitor With Haoleme is an agent skill from HaolemeApp/Haoleme. Selectively monitor important long-running or resource-intensive commands with Haoleme by prefixing them with hao, so status, output, and completion notifications sync to the mobile app. Use while running training, fine-tuning, full evaluations, benchmarks, simulations, large builds, data pipelines, batch jobs, crawlers, deployments, migrations, or other consequential commands likely to take minutes. Do not trigger for dependency or environment installation, quick smoke tests, formatting or linting, simple…

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `SKILL_CN.md` and `agents/openai.yaml`).

It sits in Data & Analytics, covering Linting and formatting, Background jobs and QA and bug reports. It works with Git, Python and Android. The repository describes itself as: Monitor commands running on your computers and servers from your phone, with live output and finish notifications via the hao CLI. The licence is AGPL-3.0.

When your agent uses it

Environment installation
Quick smoke tests
Commands that expose secrets

Example prompts

“/monitor-with-haoleme”

Requirements

Python 3
Node.js

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

Check availability with command -v hao on POSIX systems or Get-Command hao in PowerShell.
If hao is missing, do not silently replace or delay the user's task. Explain that the user can run pip install -U haoleme, then retry.
If monitoring fails because the device is not paired, ask the user to run hao login. Do not wrap either installation or login with hao.
Use hao doctor only to diagnose an actual Haoleme failure, not before every command.

What it can do on your machine

Read from SKILL.md and the folder at commit 5b9b470. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- pip
- python
- uv
- conda
- npm
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- img.shields.io
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Monitor With Haoleme loads about 1.3k tokens when it runs. Until then it costs about 152 tokens; SKILL.md has 582 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~152
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HaolemeApp/Haoleme at commit 5b9b470, republished under its AGPL-3.0 licence (© HaolemeApp). 582 words, ~1,262 tokens.

Download SKILL.mdSave it as .claude/skills/monitor-with-haoleme/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.

name: monitor-with-haoleme
description: Selectively monitor important long-running or resource-intensive commands with Haoleme by prefixing them with `hao`, so status, output, and completion notifications sync to the mobile app. Use while running training, fine-tuning, full evaluations, benchmarks, simulations, large builds, data pipelines, batch jobs, crawlers, deployments, migrations, or other consequential commands likely to take minutes. Do not trigger for dependency or environment installation, quick smoke tests, formatting or linting, simple probes, ordinary file or Git commands, or commands that expose secrets.

<p align="center">
  <a href="SKILL.md"><img src="https://img.shields.io/badge/English-Primary-2563EB?style=flat-square&amp;logo=googletranslate&amp;logoColor=white" alt="English skill guide"></a>
  <a href="SKILL_CN.md"><img src="https://img.shields.io/badge/简体中文-中文文档-E85D75?style=flat-square&amp;logo=googletranslate&amp;logoColor=white" alt="简体中文 Skill 指南"></a>
</p>

Monitor With Haoleme

Use hao only for commands worth following from the Haoleme mobile app. Keep routine development commands local.

Decide Before Running

Apply exclusions first. Never monitor a command when any of these conditions holds:

It installs or configures an environment, such as pip install, uv sync, conda install, npm install, apt, brew, or login/setup commands.
It is a quick probe, smoke test, tiny prediction test, formatter, linter, type check, health check, file operation, search, or ordinary Git command that is expected to finish quickly.
It is interactive infrastructure such as a shell, REPL, editor, password prompt, or authentication flow.
Its command line or expected output exposes passwords, API keys, tokens, private keys, full environment dumps, credentials, or other secrets.
It is already prefixed with hao.
The user explicitly says not to monitor or sync it.

Monitor the command when at least one strong signal applies:

The user explicitly asks to monitor it, receive a notification, or follow it in Haoleme.
It trains or fine-tunes a model, runs a full evaluation or benchmark, performs a simulation, or processes a large dataset.
It is an expensive GPU, CPU, memory, or remote-server job whose failure or completion matters.
It is a consequential batch job, crawl, deployment, migration, large build, or long-running script.
It is expected to run for about two minutes or longer and produces a result the user will care about.

When duration is uncertain, monitor work that is expensive or consequential. Do not monitor work merely because it invokes Python, a test runner, or a build tool.

Prepare Haoleme

Before the first command selected for monitoring in an environment:

Check availability with command -v hao on POSIX systems or Get-Command hao in PowerShell.
If hao is missing, do not silently replace or delay the user's task. Explain that the user can run pip install -U haoleme, then retry.
If monitoring fails because the device is not paired, ask the user to run hao login. Do not wrap either installation or login with hao.
Use hao doctor only to diagnose an actual Haoleme failure, not before every command.

Show full SKILL.md (215 more words)Show less

Run The Command

Prefix the original executable and arguments with hao. Preserve the working directory, arguments, quoting, and environment assignments.

bash

hao python train.py --epochs 100
hao CUDA_VISIBLE_DEVICES=0 python train.py
hao bash scripts/full-evaluation.sh
hao make -j8 release

For a compound shell program that depends on pipes, redirects, variable expansion, or multiple commands, monitor one explicit shell invocation:

bash

hao bash -lc 'python evaluate.py 2>&1 | tee evaluation.log'

Prefer the execution tool's working-directory option over embedding cd in the command. Do not edit a script solely to add Haoleme.

Keep hao in the foreground so it can record the real exit status. If the user needs tmux, screen, a scheduler, or another supervisor, place the complete hao ... command inside that supervisor.

Handle Mixed Workflows

Monitor only the important final or full-scale step. For example:

bash

pip install -r requirements.txt        # local only
python train.py --epochs 1 --smoke     # local only
hao python train.py --epochs 100        # monitor

If a workflow launches several independent important experiments, prefix each experiment separately so every run has its own status and output. Do not wrap the entire setup pipeline in one hao bash -lc command.

Report The Result

After execution, report the normal command result and exit status. Mention Haoleme only when it adds useful context, such as confirming that the run is visible in the app or explaining why monitoring was skipped.

Never claim that a command synced successfully unless hao actually started the run. If Haoleme fails before the underlying command starts, surface the error and let the user choose whether to retry with monitoring or run locally.

Files

SKILL.md and 2 other files in skills/monitor-with-haoleme of HaolemeApp/Haoleme.

SKILL.md
SKILL_CN.md
agents/openai.yaml

Open the folder on GitHubat commit 5b9b470

Compare with similar skills

Monitor With Haoleme next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Monitor With Haoleme compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Monitor With Haoleme this skillHaolemeApp/Haoleme	157	—	~1.3k	Automated safety check: Pass	AGPL-3.0	1 mo ago
Upgrading Mwaa Environmentsaws/agent-toolkit-for-aws	2.8k	—	~7.3k	Automated safety check: Pass	Apache-2.0	yesterday
Crawl4AI Web Scrapingsmallnest/goclaw	599	1 repos	~2.5k	Automated safety check: Pass	MIT	6 mo ago
Adk Setupgoogle/adk-python	22k	—	~993	Automated safety check: Notes	Apache-2.0	today
Authoritative Data Harvesteryushui2022/MathModel-Skill	454	1 repos	~1.1k	Automated safety check: Pass	MIT	4 days ago
Anti Detect Browserantibrow/anti-detect-browser-skills	17	—	~9.8k	Automated safety check: Warn	MIT	1 mo ago

Similar skills

Upgrading Mwaa Environments
aws/agent-toolkit-for-aws
Official
Upgrades an MWAA environment to a newer Airflow version — within 2.x, within 3.x, or across the 2.x-to-3.x boundary.
2.8k GitHub stars~7.3k tokensUpdated yesterday
Data & AnalyticsAuto-check passed
Crawl4AI Web Scraping
smallnest/goclaw
Scrapes sites, handles JavaScript-heavy pages and extracts structured data with Crawl4AI, through its crwl CLI or Python SDK, including schema-based extraction without an LLM.
599 GitHub starsUsed in 1 repo~2.5k tokens
Data & AnalyticsAuto-check passed
Adk Setup
google/adk-python
Official
Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test…
22k GitHub stars~993 tokensUpdated today
DevelopmentAuto-check: notes
Authoritative Data Harvester
yushui2022/MathModel-Skill
Finds authoritative public data sources for modeling tasks, prefers official APIs and bulk downloads, and outputs a reproducible fetch and cleaning plan with citations.
454 GitHub starsUsed in 1 repo~1.1k tokens
Data & AnalyticsAuto-check passed
Anti Detect Browser
antibrow/anti-detect-browser-skills
Drive Chromium from standard Playwright APIs with a real-device fingerprint applied in the kernel, one persistent isolated profile per identity, and a per-profile proxy whose exit IP sets timezone…
17 GitHub stars~9.8k tokensUpdated 1 mo ago
Testing & QAAuto-check: warnings
Quantized Export
wshobson/agents
Export a promoted fine-tuned model in the right deployment format — merged safetensors, LoRA-only, GGUF with imatrix, or FP8.
40k GitHub stars~2k tokensUpdated 6 days ago
AI & LLM EngineeringAuto-check passed

Works with

Questions about Monitor With Haoleme

What does Monitor With Haoleme do?

Selectively monitor important long-running or resource-intensive commands with Haoleme by prefixing them with hao, so status, output, and completion notifications sync to the mobile app. Monitor With Haoleme is an agent skill from HaolemeApp/Haoleme. Selectively monitor important long-running or resource-intensive commands with Haoleme by prefixing them with hao, so status, output, and completion notifications sync to the mobile app.

When should I use Monitor With Haoleme?

Monitor With Haoleme fits situations like: environment installation; quick smoke tests; commands that expose secrets.

How do I install Monitor With Haoleme in Claude Code?

Run `npx skills add HaolemeApp/Haoleme --skill monitor-with-haoleme -a claude-code`. Or copy the skill folder (skills/monitor-with-haoleme in HaolemeApp/Haoleme) into .claude/skills/monitor-with-haoleme in your project. Claude Code loads it when a task matches its description.

How do I install Monitor With Haoleme in Codex?

Run `npx skills add HaolemeApp/Haoleme --skill monitor-with-haoleme -a codex`. Or copy the skill folder (skills/monitor-with-haoleme in HaolemeApp/Haoleme) into .agents/skills/monitor-with-haoleme in your project. Codex loads it when a task matches its description.

Can I use Monitor With Haoleme in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HaolemeApp/Haoleme --skill monitor-with-haoleme -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/monitor-with-haoleme, .gemini/skills/monitor-with-haoleme, .github/skills/monitor-with-haoleme and .opencode/skills/monitor-with-haoleme in your project.

What does Monitor With Haoleme need to run?

Going by SKILL.md and its folder, Monitor With Haoleme needs the command-line tools its instructions call (pip, python, uv, conda and npm). Our summary lists: Python 3; Node.js.

Does Monitor With Haoleme access the network?

SKILL.md names 1 domain. As links in the text: img.shields.io. This is read from the text; nothing was executed.

Is Monitor With Haoleme safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Monitor With Haoleme use?

Monitor With Haoleme is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Monitor With Haoleme use?

About 1.3k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Monitor With Haoleme?

Skills that share tags, products or a category with Monitor With Haoleme: Upgrading Mwaa Environments (aws/agent-toolkit-for-aws, 2.8k stars), Crawl4AI Web Scraping (smallnest/goclaw, 599 stars), Adk Setup (google/adk-python, 22k stars) and Authoritative Data Harvester (yushui2022/MathModel-Skill, 454 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Monitor With Haoleme?

HaolemeApp (a GitHub organization) maintains it in HaolemeApp/Haoleme, which has 157 GitHub stars. The repository was last updated on August 14, 2026.

Source: HaolemeApp/Haoleme on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Monitor With Haoleme

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Monitor With Haoleme

Decide Before Running

Prepare Haoleme

Run The Command

Handle Mixed Workflows

Report The Result

Files

Compare with similar skills

Similar skills

Upgrading Mwaa Environments

Crawl4AI Web Scraping

Adk Setup

Authoritative Data Harvester

Anti Detect Browser

Quantized Export

Related

Questions about Monitor With Haoleme