Agent skill

Processes

by alsk1992 in alsk1992/CloddsBot

Background jobs, long-running processes, and task management

MITAuto-check passedProductivity & Automation

Install Processes

skills CLI
$ npx skills add alsk1992/CloddsBot --skill processes -a claude-code

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

GitHub CLI
$ gh skill install alsk1992/CloddsBot processes --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/alsk1992/CloddsBot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/skills/bundled/processes .claude/skills/processes && 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/

Facts

Skill name
processes
GitHub stars
2.9k
Token cost
~1.3k tokens
SKILL.md length
102 words
Files
2
Skills in repo
116
Repo updated
First seen
Licence
MIT

At a glance

Background jobs, long-running processes, and task management

  • Works in 5 steps: Name your jobs — Easier to identify → Set timeouts — Prevent runaway processes → Monitor memory — Prevent OOM kills → …
  • Tasks that involve Background jobs
  • SKILL.md covers Chat Commands, TypeScript API Reference, Job Status and Use Cases, plus 1 more section
  • Runs TypeScript scripts from its folder

What it does

Processes is an agent skill from alsk1992/CloddsBot. Background jobs, long-running processes, and task management

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `index.ts`).

It sits in Productivity & Automation, covering Background jobs and Task management. The repository describes itself as: Open Source AI trading agent that operates autonomously across 1000+ markets - Polymarket, Kalshi, Binance, Hyperliquid, Solana DEXs, 5 EVM chains. Scans for edge, executes… The licence is MIT.

When your agent uses it

  • Tasks that involve Background jobs
  • Tasks that involve Task management

Example prompts

  • “/processes”

Requirements

  • Python 3
  • Node.js

Workflow steps

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

  1. Name your jobs — Easier to identify
  2. Set timeouts — Prevent runaway processes
  3. Monitor memory — Prevent OOM kills
  4. Use restart sparingly — Debug failures first
  5. Check logs — Always review output

What it can do on your machine

Read from SKILL.md and the folder at commit c930628. 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

    Ships script files (TypeScript), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    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

Processes loads about 1.3k tokens when it runs. Until then it costs about 18 tokens; SKILL.md has 102 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~18
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 alsk1992/CloddsBot at commit c930628, republished under its MIT licence (© alsk1992). 102 words, ~1,314 tokens.

Download SKILL.mdSave it as .claude/skills/processes/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
processes
description
Background jobs, long-running processes, and task management
emoji
⚙️

Processes - Complete API Reference

Spawn and manage background processes, long-running jobs, and scheduled tasks.


Chat Commands

Spawn Jobs
/job spawn "npm run backtest"               Start background job
/job spawn "python train.py" --name ml      Named job
/job spawn "node bot.js" --restart          Auto-restart on exit
Manage Jobs
/jobs                                       List all jobs
/job status <id>                            Check job status
/job output <id>                            View job output
/job output <id> --follow                   Stream output
/job stop <id>                              Stop job
/job restart <id>                           Restart job
Logs
/job logs <id>                              View logs
/job logs <id> --tail 100                   Last 100 lines
/job logs <id> --since 1h                   Last hour

TypeScript API Reference

Create Process Manager
typescript
import { createProcessManager } from 'clodds/processes';

const processes = createProcessManager({
  // Working directory
  cwd: process.cwd(),

  // Environment
  env: process.env,

  // Limits
  maxProcesses: 10,
  maxMemoryMB: 1024,

  // Logging
  logDir: './logs/jobs',
  maxLogSizeMB: 100,

  // Storage
  storage: 'sqlite',
  dbPath: './jobs.db',
});
Spawn Process
typescript
// Simple spawn
const job = await processes.spawn({
  command: 'npm',
  args: ['run', 'backtest'],
  name: 'backtest-btc',
});

console.log(`Job ID: ${job.id}`);
console.log(`PID: ${job.pid}`);

// With options
const job = await processes.spawn({
  command: 'python',
  args: ['train.py', '--epochs', '100'],
  name: 'ml-training',

  // Environment
  env: {
    ...process.env,
    CUDA_VISIBLE_DEVICES: '0',
  },

  // Working directory
  cwd: '/path/to/ml-project',

  // Auto-restart
  restart: true,
  maxRestarts: 3,
  restartDelayMs: 5000,

  // Resource limits
  maxMemoryMB: 4096,
  timeoutMs: 3600000,  // 1 hour
});
List Jobs
typescript
const jobs = await processes.list();

for (const job of jobs) {
  console.log(`${job.id}: ${job.name}`);
  console.log(`  Status: ${job.status}`);  // 'running' | 'stopped' | 'failed' | 'completed'
  console.log(`  PID: ${job.pid}`);
  console.log(`  Started: ${job.startedAt}`);
  console.log(`  Memory: ${job.memoryMB}MB`);
  console.log(`  CPU: ${job.cpuPercent}%`);
}
Get Status
typescript
const status = await processes.getStatus(jobId);

console.log(`Status: ${status.status}`);
console.log(`Exit code: ${status.exitCode}`);
console.log(`Runtime: ${status.runtimeMs}ms`);
console.log(`Restarts: ${status.restarts}`);
console.log(`Memory: ${status.memoryMB}MB`);
console.log(`CPU: ${status.cpuPercent}%`);
Get Output
typescript
// Get all output
const output = await processes.getOutput(jobId);
console.log(output.stdout);
console.log(output.stderr);

// Get last N lines
const output = await processes.getOutput(jobId, { tail: 100 });

// Stream output
const stream = processes.streamOutput(jobId);
stream.on('stdout', (data) => console.log(data));
stream.on('stderr', (data) => console.error(data));
stream.on('exit', (code) => console.log(`Exit: ${code}`));
Stop Job
typescript
// Graceful stop (SIGTERM)
await processes.stop(jobId);

// Force kill (SIGKILL)
await processes.stop(jobId, { force: true });

// Stop all
await processes.stopAll();
Restart Job
typescript
await processes.restart(jobId);
Event Handlers
typescript
processes.on('started', (job) => {
  console.log(`Job started: ${job.name}`);
});

processes.on('stopped', (job) => {
  console.log(`Job stopped: ${job.name} (code: ${job.exitCode})`);
});

processes.on('failed', (job, error) => {
  console.error(`Job failed: ${job.name}`, error);
});

processes.on('output', (job, type, data) => {
  console.log(`[${job.name}] ${type}: ${data}`);
});

Job Status

StatusDescription
runningCurrently executing
stoppedStopped by user
completedFinished successfully
failedExited with error
restartingAuto-restarting

Use Cases

Run Backtest
typescript
const job = await processes.spawn({
  command: 'npm',
  args: ['run', 'backtest', '--', '--strategy', 'momentum'],
  name: 'backtest-momentum',
});

// Wait for completion
const result = await processes.wait(job.id);
console.log(`Backtest complete: ${result.exitCode === 0 ? 'success' : 'failed'}`);
Train ML Model
typescript
const job = await processes.spawn({
  command: 'python',
  args: ['train.py'],
  name: 'ml-training',
  cwd: './ml',
  maxMemoryMB: 8192,
  timeoutMs: 86400000,  // 24 hours
});

// Monitor progress
processes.streamOutput(job.id).on('stdout', (line) => {
  if (line.includes('Epoch')) {
    console.log(line);
  }
});

Best Practices

  1. Name your jobs — Easier to identify
  2. Set timeouts — Prevent runaway processes
  3. Monitor memory — Prevent OOM kills
  4. Use restart sparingly — Debug failures first
  5. Check logs — Always review output

© alsk1992, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in src/skills/bundled/processes of alsk1992/CloddsBot.

  • SKILL.md
  • index.ts

Open the folder on GitHubat commit c930628

Compare with similar skills

Processes 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.

Processes compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Processes this skillalsk1992/CloddsBot2.9k—~1.3kAutomated safety check: PassMIT
Minimal Web Baas DemoTencentCloudBase/CloudBase-AI-Toolkit1.1k1 repos~2.2kAutomated safety check: PassMIT
DexCraftOS-dev/CraftBot3921 repos~322Automated safety check: PassMIT
Worker DevelopmentChatbotXIO/ChatbotX879—~2.7kAutomated safety check: NotesCustom licence
Frappe Impl SchedulerImpertio-Studio/Frappe_Claude_Skill_Package187—~2.4kAutomated safety check: PassMIT
Frappe Impl UI ComponentsImpertio-Studio/Frappe_Claude_Skill_Package187—~4.2kAutomated safety check: PassMIT

Similar skills

  • Minimal Web Baas Demo

    TencentCloudBase/CloudBase-AI-Toolkit

    Fast path for a minimal CloudBase Web + database demo (最小前后端 / 最小可用 fullstack / Lovable-like BaaS).

    1.1k GitHub starsUsed in 1 repo~2.2k tokens
    Productivity & AutomationAuto-check passed
  • Dex

    CraftOS-dev/CraftBot

    Task tracking for async/multi-step work. An agent skill from CraftOS-dev/CraftBot.

    392 GitHub starsUsed in 1 repo~322 tokens
    Backend & APIsAuto-check passed
  • Worker Development

    ChatbotXIO/ChatbotX

    Create and manage background workers, BullMQ queues, and scheduled jobs.

    879 GitHub stars~2.7k tokensUpdated today
    Productivity & AutomationAuto-check: notes
  • Frappe Impl Scheduler

    Impertio-Studio/Frappe_Claude_Skill_Package

    A skill your agent uses when implementing scheduled tasks and background jobs in Frappe v14/v15/v16.

    187 GitHub stars~2.4k tokensUpdated 21 days ago
    Productivity & AutomationAuto-check passed
  • Frappe Impl UI Components

    Impertio-Studio/Frappe_Claude_Skill_Package

    A skill your agent uses when building custom dialogs, extending List View, creating Page controllers, or adding Kanban/Calendar views and realtime updates.

    187 GitHub stars~4.2k tokensUpdated 21 days ago
    Productivity & AutomationAuto-check passed
  • Clickup

    sundial-org/awesome-openclaw-skills

    Interact with ClickUp project management platform via REST API.

    663 GitHub stars~1.6k tokensUpdated 7 mo ago
    Productivity & AutomationAuto-check passed

More from alsk1992/CloddsBot

All 116 skills in this repo
  • Qmd

    alsk1992/CloddsBot

    Local hybrid search for markdown notes and docs. An agent skill from alsk1992/CloddsBot.

    2.9k GitHub starsUsed in 3 repos~1.2k tokens
    Auto-check passed
  • Drift SDK

    alsk1992/CloddsBot

    Drift Protocol perpetual futures trading on Solana (direct SDK)

    2.9k GitHub starsUsed in 1 repo~625 tokens
    Auto-check passed
  • Edge

    alsk1992/CloddsBot

    Find mispriced markets by comparing to external models and data sources

    2.9k GitHub starsUsed in 1 repo~472 tokens
    Auto-check passed
  • Embeddings

    alsk1992/CloddsBot

    Vector embeddings configuration and semantic search. An agent skill from alsk1992/CloddsBot.

    2.9k GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed
  • News

    alsk1992/CloddsBot

    Monitor news and correlate with prediction market movements. An agent skill from alsk1992/CloddsBot.

    2.9k GitHub starsUsed in 1 repo~462 tokens
    Auto-check passed
  • Opportunity

    alsk1992/CloddsBot

    Find and execute cross-platform arbitrage opportunities across prediction markets

    2.9k GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed

Questions about Processes

What does Processes do?

Background jobs, long-running processes, and task management. Processes is an agent skill from alsk1992/CloddsBot.

When should I use Processes?

Processes fits situations like: tasks that involve Background jobs; tasks that involve Task management.

How do I install Processes in Claude Code?

Run `npx skills add alsk1992/CloddsBot --skill processes -a claude-code`. Or copy the skill folder (src/skills/bundled/processes in alsk1992/CloddsBot) into .claude/skills/processes in your project. Claude Code loads it when a task matches its description.

How do I install Processes in Codex?

Run `npx skills add alsk1992/CloddsBot --skill processes -a codex`. Or copy the skill folder (src/skills/bundled/processes in alsk1992/CloddsBot) into .agents/skills/processes in your project. Codex loads it when a task matches its description.

Can I use Processes 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 alsk1992/CloddsBot --skill processes -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/processes, .gemini/skills/processes, .github/skills/processes and .opencode/skills/processes in your project.

What does Processes need to run?

Going by SKILL.md and its folder, Processes needs TypeScript for the scripts in its folder. Our summary lists: Python 3; Node.js.

Does Processes access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Processes 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 Processes use?

Processes is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Processes use?

About 1.3k tokens (SKILL.md is roughly 5.3k 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 Processes?

Skills that share tags, products or a category with Processes: Minimal Web Baas Demo (TencentCloudBase/CloudBase-AI-Toolkit, 1.1k stars), Dex (CraftOS-dev/CraftBot, 392 stars), Worker Development (ChatbotXIO/ChatbotX, 879 stars) and Frappe Impl Scheduler (Impertio-Studio/Frappe_Claude_Skill_Package, 187 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Processes?

alsk1992 (a GitHub user) maintains it in alsk1992/CloddsBot, which has 2,903 GitHub stars. The repository holds 116 skills in this directory. The repository was last updated on October 2, 2026.

Source: alsk1992/CloddsBot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.