Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/alsk1992/cloddsbot/processesnpx skills add alsk1992/CloddsBot --skill processesgit clone --depth 1 https://github.com/alsk1992/CloddsBotWrote 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/skills/alsk1992/cloddsbot/processes)<a href="https://agentmods.dev/skills/alsk1992/cloddsbot/processes"><img src="https://agentmods.dev/badge/skills/alsk1992/cloddsbot/processes.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.01356 |
| Opus 5 | $0.00006 | $0.00678 |
| Sonnet 5 | $0.00003 | $0.00271 |
| Haiku 4.5 | $0.00001 | $0.00136 |
Grade A, and why
processes 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 2d 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
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
// 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
});
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 255 lines · 13 tokens per session scan A 2d1218ef2604
processes is a skill published in the GitHub repository alsk1992/CloddsBot (885 stars, last pushed 4d ago), licensed MIT. It adds 13 tokens to every session and 1,356 once invoked, about $0.0001 per session on Opus 5. 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 2026-09-03.
Other skills, from other repositories
task-scheduler
Schedule and automate trading tasks: DCA, rebalancing, reports, alerts. Full auto-pilot support.
session-timer
Zeigt aktive Trading-Sessions und optimale Trading-Zeiten. Wisse immer, wann die Märkte am liquidesten sind!
notion
Notion API for creating and managing pages, databases, and blocks. Use when the user wants to create a Notion page, query a Notion database, update Notion properties, search Notion, add content to Notion, manage Notion blocks, or interact with Notion data sources and workspaces via the API.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes, capturing pane output, and managing terminal multiplexer windows. Enables parallel coding-agent orchestration, background process management, and REPL interaction via sockets. Use when the agent needs to launch, monitor, or coordinate…
apple-reminders
Manage Apple Reminders via the remindctl CLI on macOS (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output. Use when the user asks about reminders, todos, tasks, to-do lists, "remind me", scheduling tasks, checking what is due today, completing or deleting reminders, or managing…
things-mac
Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Otto to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.