Which AI tools does this work with?

Any current model. It was seen with in the sources.

Where did this come from?

OpenAI Developers Blog (OpenAI Developers Blog). Subvolts collected, normalized and credited it; the link above opens the original.

Checklist Agents and automationExpert · 30 min

Checklist for building long-horizon agents with skills and shell

Key considerations for building robust, long-running agents using skills, hosted shell, and server-side compaction.

Any modelParaphrased

Items

Open in ChatGPT Open in Claude

Define skills with clear descriptions, including 'use when' and 'don't use when' clauses.
Incorporate negative examples and edge cases into skill descriptions for improved routing.
Embed templates and worked examples within skills, not the system prompt.
Plan for continuity by chaining prompts or using techniques that maintain state across turns.
Consider explicit skill invocation for deterministic production workflows.
Implement strict network allowlists and secure credential handling if using networking.
Use `/mnt/data` as the standard directory for agent outputs.
Leverage server-side compaction to manage context window limits for long runs.

Define skills with clear descriptions, including 'use when' and 'don't use when' clauses.
Incorporate negative examples and edge cases into skill descriptions for improved routing.
Embed templates and worked examples within skills, not the system prompt.
Plan for continuity by chaining prompts or using techniques that maintain state across turns.
Consider explicit skill invocation for deterministic production workflows.
Implement strict network allowlists and secure credential handling if using networking.
Use `/mnt/data` as the standard directory for agent outputs.
Leverage server-side compaction to manage context window limits for long runs.

Before or after

before

Context

Building long-running agents that perform complex tasks.

What it does and when to use it

A checklist for developing long-horizon agents. It covers defining skills with clear routing logic, embedding examples within skills, planning for continuity, securing network access, managing outputs, and using compaction for long runs.

Why it works

Following these steps helps ensure agents are reliable, efficient, and secure by addressing common failure modes and best practices for complex, multi-step tasks.

Sources and credit

Shell + Skills + Compaction: Tips for long-running agents that do real work ↗OpenAI Developers Blog · OpenAI Developers Blog · Sep 3, 2026 · paraphrased

First seen on Subvolts Sep 3, 2026. Updated Sep 11, 2026. Spotted a problem? Tell us.

Where it shows up

Shell + Skills + Compaction: Tips for long-running agents that do real workOpenAI · OpenAI Developers Blog · Sep 3, 2026

Related in the PlaybookPlaybook →

The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.

TemplateEvals CSV prompt list for agent skillsA CSV file template for listing prompts used in evaluating agent skills. · 20 min
ChecklistAX Practitioner Playbook Evaluation Quality ChecklistReview your AI agent evaluation process before running it to ensure its quality and trustworthiness. · 30 min
Skill or agent configJoplin agent for automated note filing and retrievalAutomate note organization and retrieval in Joplin using a custom agent and Python scripts. · 60 min
HeuristicUse reasoning models for improved reliability on complex tasksEmploy reasoning models like o1, o3, and o4-mini for dramatically improved reliability on complex, multi-step work. · 5 min
Setting tipStore AI agent traces and evaluation data with projectKeep traces, evaluation datasets, and results with your project for repeatable testing. · 5 min
WorkflowBuild and test an AI agent using Microsoft Foundry ToolkitCreate, configure, test, and evaluate an AI agent within VS Code. · 60 min

Questions people ask

Which AI tools does this work with?: Any current model. It was seen with in the sources.
Where did this come from?: OpenAI Developers Blog (OpenAI Developers Blog). Subvolts collected, normalized and credited it; the link above opens the original.

Checklist for building long-horizon agents with skills and shell

Questions people ask

OpenAI (ChatGPT)

Google (Gemini)

Anthropic (Claude)

Microsoft (Copilot)

Meta (Meta AI)

xAI (Grok)

Across the six

Subvolts