task-creator

task-creator is a skill for Claude Code, Codex from arrase/ollama-agent. It costs 25 tokens per session (488 once invoked), scanned A, original, MIT.

A guide and schema for creating saved automated tasks. A saved task is a self-contained prompt and configuration that can be run later on demand.

In plain words
What is it for?
Use it to define recurring or on-demand tasks with a title, detailed prompt, optional model, and reasoning effort, saved as YAML configuration.
Why use it?
It ensures an autonomous task contains the context, instructions, model choice, reasoning setting, and success criteria it needs without relying on the original conversation.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/arrase/ollama-agent/task-creator
Any agent
npx skills add arrase/ollama-agent --skill task-creator
Clone the repo
git clone --depth 1 https://github.com/arrase/ollama-agent

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for task-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/arrase/ollama-agent/task-creator.svg)](https://agentmods.dev/skills/arrase/ollama-agent/task-creator)
Your own site
<a href="https://agentmods.dev/skills/arrase/ollama-agent/task-creator"><img src="https://agentmods.dev/badge/skills/arrase/ollama-agent/task-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 488 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.00488
Opus 5 $0.00013 $0.00244
Sonnet 5 $0.00005 $0.00098
Haiku 4.5 $0.00003 $0.00049

Measured 4d ago against content hash eddbe1234ad0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-creator 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 4d 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.

ollama_agent/skills/builtin/task-creator/SKILL.md · 37 lines

What it actually says

Task Creator

A saved task is a pre-configured, self-contained prompt and configuration that can be executed autonomously on demand via /task run <task_id> or ollama-agent task run <task_id>. Tasks reside in /tasks/<task_id>.yaml (persisted in ~/.ollama-agent/tasks/<task_id>.yaml).

Task YAML Schema

Each task is saved as a single YAML file: /tasks/<task_id>.yaml.

title: "Clear, descriptive title of the task"
prompt: "Comprehensive, fully self-contained prompt that describes the exact objective, context, requirements, constraints, and success criteria for the agent to execute."
model: "" # Optional specific model name, or empty string to use the active model
reasoning_effort: "medium" # Reasoning effort level: low, medium, high, default

Fields Specification

  • title (string, required): Short descriptive title for display in /task list.
  • prompt (string, required): Self-contained prompt. Because tasks run autonomously, the prompt should provide all necessary context, step-by-step instructions, and expected deliverables.
  • model (string, optional): Specific Ollama model name, or "" to use the session's active model.
  • reasoning_effort (string, optional): Reasoning effort (low, medium, high, default).

Task ID Rules

  • Must contain only letters, numbers, underscores, and hyphens (e.g. code-review, generate-changelog, db_migration_check).

Interactive Creation Workflow for the Agent

When helping a user create a task:

  1. Clarify Objective: Understand what repeatable task or workflow the user wants to automate.
  2. Formulate Prompt: Draft a high-quality, comprehensive prompt ensuring it includes clear goals, constraints, and output expectations.
  3. Write File: Use write_file to write the YAML file to /tasks/<task_id>.yaml.
  4. Confirm: Display the task summary and instruct the user on how to run it with /task run <task_id>.
Changes

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.

  1. 4d ago First seen · 37 lines · 25 tokens per session scan A eddbe1234ad0

Subscribe to this mod's changes

task-creator is a skill published in the GitHub repository arrase/ollama-agent (20 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 488 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 2026-08-30.