Agent skill

Worker Agents

by grandamenium in grandamenium/cortextos

Install Worker Agents

skills CLI

$ npx skills add grandamenium/cortextos --skill worker-agents -a claude-code

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

GitHub CLI

$ gh skill install grandamenium/cortextos worker-agents --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/grandamenium/cortextos.git skills-src && mkdir -p .claude/skills && cp -r skills-src/community/skills/worker-agents .claude/skills/worker-agents && 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 "worker-agents" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/skills/worker-agents into .claude/skills/worker-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "worker-agents", 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/grandamenium/cortextos/tree/main/community/skills/worker-agents

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 grandamenium/cortextos --skill worker-agents -a codex

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

GitHub CLI

$ gh skill install grandamenium/cortextos worker-agents --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/grandamenium/cortextos.git skills-src && mkdir -p .agents/skills && cp -r skills-src/community/skills/worker-agents .agents/skills/worker-agents && 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 "worker-agents" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/skills/worker-agents into .agents/skills/worker-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "worker-agents", 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 grandamenium/cortextos --skill worker-agents -a cursor

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

GitHub CLI

$ gh skill install grandamenium/cortextos worker-agents --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/grandamenium/cortextos.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/community/skills/worker-agents .cursor/skills/worker-agents && 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 "worker-agents" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/skills/worker-agents into .cursor/skills/worker-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "worker-agents", 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/grandamenium/cortextos.git --path community/skills/worker-agents

--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 grandamenium/cortextos --skill worker-agents -a gemini-cli

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

GitHub CLI

$ gh skill install grandamenium/cortextos worker-agents --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/grandamenium/cortextos.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/community/skills/worker-agents .gemini/skills/worker-agents && 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 "worker-agents" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/skills/worker-agents into .gemini/skills/worker-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "worker-agents", 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 grandamenium/cortextos worker-agents

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 grandamenium/cortextos --skill worker-agents -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/grandamenium/cortextos.git skills-src && mkdir -p .github/skills && cp -r skills-src/community/skills/worker-agents .github/skills/worker-agents && 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 "worker-agents" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/skills/worker-agents into .github/skills/worker-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "worker-agents", 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 grandamenium/cortextos --skill worker-agents -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 grandamenium/cortextos worker-agents --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/grandamenium/cortextos.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/community/skills/worker-agents .opencode/skills/worker-agents && 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 "worker-agents" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/skills/worker-agents into .opencode/skills/worker-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "worker-agents", 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: worker-agents
GitHub stars: 101
Token cost: ~1.2k tokens
SKILL.md length: 414 words
Files: 1
Skills in repo: 55
Repo updated: Sep 23, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Works in 6 steps: Scope the Work → Spawn Worker Session → Inject Task Prompt → …
Tasks that involve Context engineering
SKILL.md covers When to Use, How Workers Differ from…, Workflow (Concepts —… and Scaling Rules
Calls git and claude

What it does

Worker Agents is an agent skill from grandamenium/cortextos. You have a task that would benefit from running in a separate isolated Claude Code session — either because it is long-running and you do not want it to consume your context window, or because you want multiple pieces of work running in parallel that each require a full Claude Code session with its own tools, memory, and context (not just a subagent call). You will spawn one or more ephemeral worker sessions, give each a focused task, monitor their progress via the bus, and collect their outputs when done.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Context engineering and Subagents. The licence is MIT.

When your agent uses it

Tasks that involve Context engineering
Tasks that involve Subagents

Example prompts

“/worker-agents”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

Scope the Work
Spawn Worker Session
Inject Task Prompt
Log the Spawn
Monitor
Cleanup

What it can do on your machine

Read from SKILL.md and the folder at commit 6f93838. 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:
- git
- claude
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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

Worker Agents loads about 1.2k tokens when it runs. Until then it costs about 131 tokens; SKILL.md has 414 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~131
When it runs · the whole SKILL.md, loaded when a task matches: ~1.2k

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 grandamenium/cortextos at commit 6f93838, republished under its MIT licence (© grandamenium). 414 words, ~1,233 tokens.

Download SKILL.mdSave it as .claude/skills/worker-agents/SKILL.md (or your agent's skills folder).

name: worker-agents
description: You have a task that would benefit from running in a separate isolated Claude Code session — either because it is long-running and you do not want it to consume your context window, or because you want multiple pieces of work running in parallel that each require a full Claude Code session with its own tools, memory, and context (not just a subagent call). You will spawn one or more ephemeral worker sessions, give each a focused task, monitor their progress via the bus, and collect their outputs when done.
triggers: worker, parallelize, spawn worker, spin up, parallel work, background task, isolated session, separate session, long running task, run in background, parallel…

Worker Agents

Spawn ephemeral Claude Code sessions for parallelized long-running tasks. Workers get a scoped task, produce deliverables, and are cleaned up when done. Use when work requires a full independent Claude Code session — not just a subagent tool call.

Worker session spawn is fully implemented. Use cortextos spawn-worker to launch isolated Claude Code sessions for parallelized tasks.

When to Use

Good fit:

Independent work that does not touch files another agent is editing
Research or design docs in a new directory
Scaffolding a new feature in isolation
Any task > 5 minutes that can run while you do other work

Bad fit:

Editing files another agent or worker is actively touching (merge conflicts)
Tasks needing real-time back-and-forth (just do it yourself)
Very short tasks < 2 minutes (overhead not worth it)

How Workers Differ from Persistent Agents

	Persistent Agent	Worker Agent
Lifetime	24/7, survives restarts	Dies when task is done
Identity	IDENTITY.md, SOUL.md, GOALS.md	None — just a task prompt
Heartbeat	Updates every 4h	None
Crons	config.json scheduled tasks	None
Inbox	Bus messages via check-inbox	Bus messages (optional)
Telegram	Yes	No
Memory	Daily journals, MEMORY.md	None

Workflow (Concepts — Implementation TBD)

Step 1: Scope the Work

Before spawning, answer:

What specific deliverables should the worker produce?
Which files/directories will it create or modify?
Does this overlap with any active agent or worker? If yes, do NOT parallelize.
What context does the worker need?

Show full SKILL.md (180 more words)Show less

Step 2: Spawn Worker Session

bash

cortextos spawn-worker <worker-name> \
  --dir <absolute-path-to-project-dir> \
  --prompt "Read AGENTS.md for your task. Deliverables: <list>. When done: cortextos bus send-message $CTX_AGENT_NAME normal 'Done: <summary>'" \
  --parent $CTX_AGENT_NAME

The worker:

Runs claude --dangerously-skip-permissions in the given directory
Gets a bus identity (CTX_AGENT_NAME=<worker-name>) for two-way communication
Logs to ~/.cortextos/<instance>/logs/<worker-name>/stdout.log
Is tracked by the daemon — use cortextos list-workers to monitor status

Step 3: Inject Task Prompt

A good worker task prompt includes:

Exact deliverables (specific files or outputs to produce)
What NOT to touch (files other agents own)
Working directory scope
How to communicate back (cortextos bus send-message <parent> normal '<update>')
Completion signal ("when done, send me a summary")

Step 4: Log the Spawn

bash

cortextos bus log-event action worker_spawned info \
  --meta '{"worker":"<worker-name>","parent":"'$CTX_AGENT_NAME'","task":"<title>"}'

Step 5: Monitor

Workers communicate back via the bus. Check your inbox:

bash

cortextos bus check-inbox

Check all worker statuses:

bash

cortextos list-workers
# Output: worker-name  running (pid 12345) ← parent-agent  42s  /path/to/dir

Check git progress in the worker's directory:

bash

cd <work-dir> && git log --oneline | head -5

Nudge a stuck worker (equivalent of tmux send-keys):

bash

cortextos inject-worker <worker-name> "Continue with phase 3. What's blocking you?"

Step 6: Cleanup

bash

# Terminate a running worker
cortextos terminate-worker <worker-name>

# Log completion
cortextos bus log-event action worker_completed info \
  --meta '{"worker":"<worker-name>","deliverables":"<summary>"}'

Scaling Rules

Workers	Risk	Notes
1-2	Low	Safe for most tasks
3-4	Medium	Ensure zero file overlap
5+	High	Resource contention, monitor closely

Hard rules:

NEVER spawn workers for overlapping file sets
NEVER let workers modify files you or other agents are editing
ALWAYS log spawns and completions
Workers should NOT spawn their own workers (no worker-ception)

Files

Just SKILL.md in community/skills/worker-agents of grandamenium/cortextos.

Open the folder on GitHubat commit 6f93838

Compare with similar skills

Worker Agents 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.

Worker Agents compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Worker Agents this skillgrandamenium/cortextos	101	—	~1.2k	Automated safety check: Pass	MIT	17 days ago
Claude Statusbarleeguooooo/claude-code-usage-bar	378	—	~2.6k	Automated safety check: Pass	MIT	yesterday
Badstephenleo/bmad-autonomous-development	107	—	~7.7k	Automated safety check: Pass	MIT	5 mo ago
Analyze Trajectoryyologdev/yoyo-evolve	1.9k	—	~3.6k	Automated safety check: Pass	MIT	today
Code Context Slicingtrailofbits/skills	7.5k	—	~2.1k	Automated safety check: Pass	CC-BY-SA-4.0	today
MoAI Foundation Coremodu-ai/moai-adk	1.2k	—	~5k	Automated safety check: Pass	Apache-2.0	yesterday

Similar skills

Claude Statusbar
leeguooooo/claude-code-usage-bar
Manage cs (claude-statusbar) — switch theme/style/density, override severity colors, preview combinations, run doctor, reset config, install, upgrade (cs upgrade — the only supported upgrade path)…
378 GitHub stars~2.6k tokensUpdated yesterday
Agent WorkflowsAuto-check passed
Bad
stephenleo/bmad-autonomous-development
BMad Autonomous Development — orchestrates parallel story implementation pipelines.
107 GitHub stars~7.7k tokensUpdated 5 mo ago
Agent WorkflowsAuto-check passed
Analyze Trajectory
yologdev/yoyo-evolve
Diagnoses a recurring failure such as a stuck task, repeated CI error or frequent reverts by sending sub-agents through the logs and returning one root-cause diagnosis.
1.9k GitHub stars~3.6k tokensUpdated today
Agent WorkflowsAuto-check passed
Code Context Slicing
trailofbits/skills
Official
Picks a small, graph-based slice of source with Trailmark and hands a focused code task to a smaller or local model without exposing the whole repository.
7.5k GitHub stars~2.1k tokensUpdated today
Agent WorkflowsAuto-check passed
MoAI Foundation Core
modu-ai/moai-adk
Reference for MoAI-ADK's core development principles: TRUST 5 quality gates, SPEC-first domain-driven workflow, agent delegation and token budgeting.
1.2k GitHub stars~5k tokensUpdated yesterday
Agent WorkflowsAuto-check passed
Cc Dev Agent
sangrokjung/claude-forge
A skill your agent uses when starting Claude Code projects, writing CLAUDE.md/spec.md, dispatching subagents, or requesting Agent Teams parallel development.
852 GitHub stars~771 tokensUpdated 1 mo ago
Agent WorkflowsAuto-check passed

More from grandamenium/cortextos

All 55 skills in this repo

Cortext Self Diagnosis
grandamenium/cortextos
Diagnose cortextOS itself when the framework misbehaves — an agent has gone silent or wedged, agents are crash-looping, Telegram or agent-to-agent messages are not arriving, crons did not fire, an…
101 GitHub stars~3.7k tokensUpdated 17 days ago
Auto-check passed
Activity Channel
grandamenium/cortextos
You have completed something significant and want the whole org — all agents and the user — to know about it.
101 GitHub stars~624 tokensUpdated 17 days ago
Auto-check passed
Agentcard Purchase
grandamenium/cortextos
You need to make a purchase on behalf of the user — buy a SaaS subscription, pay for an API, purchase a domain, or any transaction requiring a credit card.
101 GitHub stars~1.1k tokensUpdated 17 days ago
Auto-check passed
Claude To Codex Migration
grandamenium/cortextos
Migrate ANY cortextOS agent from the claude-code runtime to the live codex-app-server runtime.
101 GitHub stars~12k tokensUpdated 17 days ago
Auto-check: warnings
Bus Reference
grandamenium/cortextos
Complete cortextos bus CLI reference - all available commands with examples.
101 GitHub stars~3.8k tokensUpdated 17 days ago
Auto-check passed
Business News Monitor
grandamenium/cortextos
Daily cron-driven scan of news/forums/social in a domain to surface market shifts, new competitors, regulatory changes, and net-new opportunities.
101 GitHub stars~1.3k tokensUpdated 17 days ago
Auto-check passed

Questions about Worker Agents

What does Worker Agents do?

You have a task that would benefit from running in a separate isolated Claude Code session — either because it is long-running and you do not want it to consume your context window, or because you…. Worker Agents is an agent skill from grandamenium/cortextos. You have a task that would benefit from running in a separate isolated Claude Code session — either because it is long-running and you do not want it to consume your context window, or because you want multiple pieces of work running in parallel that each require a full Claude Code session with its own tools, memory, and context (not just a subagent call).

When should I use Worker Agents?

Worker Agents fits situations like: tasks that involve Context engineering; tasks that involve Subagents.

How do I install Worker Agents in Claude Code?

Run `npx skills add grandamenium/cortextos --skill worker-agents -a claude-code`. Or copy the skill folder (community/skills/worker-agents in grandamenium/cortextos) into .claude/skills/worker-agents in your project. Claude Code loads it when a task matches its description.

How do I install Worker Agents in Codex?

Run `npx skills add grandamenium/cortextos --skill worker-agents -a codex`. Or copy the skill folder (community/skills/worker-agents in grandamenium/cortextos) into .agents/skills/worker-agents in your project. Codex loads it when a task matches its description.

Can I use Worker Agents 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 grandamenium/cortextos --skill worker-agents -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/worker-agents, .gemini/skills/worker-agents, .github/skills/worker-agents and .opencode/skills/worker-agents in your project.

What does Worker Agents need to run?

Going by SKILL.md and its folder, Worker Agents needs the command-line tools its instructions call (git and claude).

Does Worker Agents access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Worker Agents 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 Worker Agents use?

Worker Agents 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 Worker Agents use?

About 1.2k tokens (SKILL.md is roughly 4.9k 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 Worker Agents?

Skills that share tags, products or a category with Worker Agents: Claude Statusbar (leeguooooo/claude-code-usage-bar, 378 stars), Bad (stephenleo/bmad-autonomous-development, 107 stars), Analyze Trajectory (yologdev/yoyo-evolve, 1.9k stars) and Code Context Slicing (trailofbits/skills, 7.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Worker Agents?

grandamenium (a GitHub user) maintains it in grandamenium/cortextos, which has 101 GitHub stars. The repository holds 55 skills in this directory. The repository was last updated on September 23, 2026.

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

Install Worker Agents

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Worker Agents

When to Use

How Workers Differ from Persistent Agents

Workflow (Concepts — Implementation TBD)

Step 1: Scope the Work

Step 2: Spawn Worker Session

Step 3: Inject Task Prompt

Step 4: Log the Spawn

Step 5: Monitor

Step 6: Cleanup

Scaling Rules

Files

Compare with similar skills

Similar skills

More from grandamenium/cortextos

Related

Questions about Worker Agents