Agent skill

Human Tasks

by grandamenium in grandamenium/cortextos

You have hit a blocker that is not a permission issue — it is a capability issue.

MITAuto-check: notes

Install Human Tasks

skills CLI

$ npx skills add grandamenium/cortextos --skill human-tasks -a claude-code

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

GitHub CLI

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

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 human-tasks -a codex

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

GitHub CLI

$ gh skill install grandamenium/cortextos human-tasks --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/human-tasks .agents/skills/human-tasks && 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 "human-tasks" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/skills/human-tasks into .agents/skills/human-tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "human-tasks", 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 human-tasks -a cursor

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

GitHub CLI

$ gh skill install grandamenium/cortextos human-tasks --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/human-tasks .cursor/skills/human-tasks && 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 "human-tasks" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/skills/human-tasks into .cursor/skills/human-tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "human-tasks", 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/human-tasks

--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 human-tasks -a gemini-cli

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

GitHub CLI

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

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 human-tasks -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/human-tasks .github/skills/human-tasks && 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 "human-tasks" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/skills/human-tasks into .github/skills/human-tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "human-tasks", 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 human-tasks -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 human-tasks --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/human-tasks .opencode/skills/human-tasks && 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 "human-tasks" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/skills/human-tasks into .opencode/skills/human-tasks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "human-tasks", 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: human-tasks
GitHub stars: 101
Token cost: ~865 tokens
SKILL.md length: 198 words
Files: 1
Skills in repo: 55
Repo updated: Sep 23, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

You have hit a blocker that is not a permission issue — it is a capability issue.

Works in 3 steps: Title must start with [HUMAN] → assignee human → project human-tasks
SKILL.md covers Creating a Human Task, When Human Completes the Task, Writing Good Human Task… and Consequence
Needs OPENAI_API_KEY

What it does

Human Tasks is an agent skill from grandamenium/cortextos. You have hit a blocker that is not a permission issue — it is a capability issue. You genuinely cannot complete the next step because it requires a human: making a payment, entering credentials for a service you cannot access, physical action, a decision that only the user can make, or anything else outside your capabilities. You need to create a clear [HUMAN] task with step-by-step instructions, block your own work on it, and notify the orchestrator so this surfaces in the next briefing.

Its SKILL.md is about 870 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The licence is MIT.

Example prompts

“/human-tasks”

Requirements

A credential in OPENAI_API_KEY

Workflow steps

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

Title must start with [HUMAN]
assignee human
project human-tasks

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
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
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 these keys or tokens, usually read from environment variables:
- OPENAI_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Human Tasks loads about 865 tokens when it runs. Until then it costs about 126 tokens; SKILL.md has 198 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~126
When it runs · the whole SKILL.md, loaded when a task matches: ~865

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NoteMentions a .env fileSKILL.md:72

EY=<your-key>' >> ~/cortextos/orgs/myorg/.env"

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). 198 words, ~865 tokens.

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

name: human-tasks
description: You have hit a blocker that is not a permission issue — it is a capability issue. You genuinely cannot complete the next step because it requires a human: making a payment, entering credentials for a service you cannot access, physical action, a decision that only the user can make, or anything else outside your capabilities. You need to create a clear [HUMAN] task with step-by-step instructions, block your own work on it, and notify the orchestrator so this surfaces in the next briefing.
triggers: human task, need human, can't do this myself, requires human, needs you to, blocked by human, human input needed, waiting for human, human only, physical…

Human Tasks

A human task is for when you CANNOT do something — it requires human capability. This is different from an approval (where you can do it but need permission).

Situation	Use
"I can do this but need sign-off"	Approval (see approvals skill)
"I cannot do this at all — needs a human"	Human task (this skill)

Creating a Human Task

Three signals tell the dashboard to route this to "Your Tasks" — all three are required:

Title must start with [HUMAN]
--assignee human
--project human-tasks

bash

# 1. Create the human task with clear step-by-step instructions
HUMAN_TASK_ID=$(cortextos bus create-task \
  "[HUMAN] <what needs to be done>" \
  --desc "<step-by-step instructions — be specific enough for the human to complete without asking you>" \
  --assignee human \
  --priority normal \
  --project human-tasks)

echo "HUMAN_TASK_ID=$HUMAN_TASK_ID"

# 2. Block your own task on it
cortextos bus update-task "$YOUR_TASK_ID" blocked
cortextos bus log-event task task_blocked info --meta "{\"task_id\":\"$YOUR_TASK_ID\",\"blocked_by\":\"$HUMAN_TASK_ID\",\"reason\":\"human dependency\"}"

# 3. Notify orchestrator to surface in next briefing
cortextos bus send-message "$CTX_ORCHESTRATOR_AGENT" normal \
  "Human task created: [HUMAN] <title> — needed before I can proceed with <your task title>"

# 4. Notify user directly if urgent
cortextos bus send-telegram "$CTX_TELEGRAM_CHAT_ID" \
  "I need your help: [HUMAN] <title> — I've created a task with instructions. Check dashboard."

When Human Completes the Task

You receive an inbox message automatically when the human task is marked complete. On receiving it:

bash

# Unblock immediately — don't wait
cortextos bus update-task "$YOUR_TASK_ID" in_progress \
  "Human task completed — resuming"

# Resume work

Writing Good Human Task Instructions

The instructions field should be complete enough that the human can execute without coming back to ask you questions.

Bad: "Set up the API key"

Good: "1. Go to openai.com/account/api-keys. 2. Click 'Create new secret key'. 3. Name it 'cortextos-myorg'. 4. Copy the key (starts with sk-...). 5. Open Terminal and run: echo 'OPENAI_API_KEY=<your-key>' >> ~/cortextos/orgs/myorg/.env"

Consequence

Leaving work undone without creating a human task = invisible blocker. The system stalls silently. Create the human task within 1 heartbeat of discovering you're blocked by a human dependency.

Files

Just SKILL.md in community/skills/human-tasks of grandamenium/cortextos.

Open the folder on GitHubat commit 6f93838

Compare with similar skills

Human Tasks 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.

Human Tasks compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Human Tasks this skillgrandamenium/cortextos	101	—	~865	Automated safety check: Notes	MIT	17 days ago
Permission Managersickn33/agentic-awesome-skills	47k	1 repos	~595	Automated safety check: Pass	MIT	yesterday
Cognee Permissionstopoteretes/cognee	32k	—	~3.6k	Automated safety check: Pass	Apache-2.0	today
Fewer Permission Promptsasgeirtj/system_prompts_leaks	69k	—	~1.9k	Automated safety check: Pass	CC0-1.0	today
Permissions Policythedaviddias/Front-End-Checklist	74k	—	~565	Automated safety check: Pass	MIT	4 days ago
Auditing GCP Iam Permissionsmukul975/Anthropic-Cybersecurity-Skills	34k	—	~3.2k	Automated safety check: Pass	Apache-2.0	1 mo ago

Similar skills

Permission Manager
sickn33/agentic-awesome-skills
Manage opencode permissions: review always-allow lists, suggest safe read-only commands, configure permission patterns
47k GitHub starsUsed in 1 repo~595 tokens
DevelopmentAuto-check passed
Cognee Permissions
topoteretes/cognee
A skill your agent uses when working with cognee's users, permissions, and multi-tenancy — creating users, tenants and roles, sharing datasets (read/write/delete/share grants), acting as a specific…
32k GitHub stars~3.6k tokensUpdated today
Backend & APIsAuto-check passed
Fewer Permission Prompts
asgeirtj/system_prompts_leaks
Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.
69k GitHub stars~1.9k tokensUpdated today
Agent WorkflowsAuto-check passed
Permissions Policy
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing HTTP response headers for defense-in-depth security hardening on any web application.
74k GitHub stars~565 tokensUpdated 4 days ago
SecurityAuto-check passed
Auditing GCP Iam Permissions
mukul975/Anthropic-Cybersecurity-Skills
Auditing Google Cloud Platform IAM permissions to identify overly permissive bindings, primitive role usage, service account key proliferation, and cross-project access risks using gcloud CLI…
34k GitHub stars~3.2k tokensUpdated 1 mo ago
SecurityAuto-check passed
Add Permission
fullstackhero/dotnet-starter-kit
Add a new permission end-to-end — server constant + endpoint gate, and (admin app) mirror it into the permissions catalog + route guard.
6.8k GitHub stars~849 tokensUpdated yesterday
Backend & APIsAuto-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 Human Tasks

What does Human Tasks do?

You have hit a blocker that is not a permission issue — it is a capability issue. Human Tasks is an agent skill from grandamenium/cortextos. You have hit a blocker that is not a permission issue — it is a capability issue.

How do I install Human Tasks in Claude Code?

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

How do I install Human Tasks in Codex?

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

Can I use Human Tasks 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 human-tasks -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/human-tasks, .gemini/skills/human-tasks, .github/skills/human-tasks and .opencode/skills/human-tasks in your project.

What does Human Tasks need to run?

Going by SKILL.md and its folder, Human Tasks needs credentials named OPENAI_API_KEY. Our summary lists: A credential in OPENAI_API_KEY.

Does Human Tasks 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 Human Tasks safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Human Tasks use?

Human Tasks 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 Human Tasks use?

About 865 tokens (SKILL.md is roughly 3.5k 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 Human Tasks?

Skills that share tags, products or a category with Human Tasks: Permission Manager (sickn33/agentic-awesome-skills, 47k stars), Cognee Permissions (topoteretes/cognee, 32k stars), Fewer Permission Prompts (asgeirtj/system_prompts_leaks, 69k stars) and Permissions Policy (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Human Tasks?

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 Human Tasks

Facts

At a glance

What it does

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Human Tasks

Creating a Human Task

When Human Completes the Task

Writing Good Human Task Instructions

Consequence

Files

Compare with similar skills

Similar skills

More from grandamenium/cortextos

Questions about Human Tasks