aios-long-running-harness — ai-agent aios-long-running-harness, rex-cli, community, ai-agent, ide skills, browser-automation, claude-code, codex-cli, contextdb, gemini-cli, Claude Code

v1.0.0

このスキルについて

UIのドリフトやモデル変動性の下で安定性を維持するための堅牢な長時間実行タスク管理が必要なAIエージェントに最適です。 Use when running multi-step or long-running agent jobs in aios that require checkpointing, retries, evidence capture, and safe human handoff.

# Core Topics

rexleimo rexleimo
[11]
[1]
Updated: 3/11/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 7/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution
Review Score
7/11
Quality Score
32
Canonical Locale
en
Detected Body Locale
en

UIのドリフトやモデル変動性の下で安定性を維持するための堅牢な長時間実行タスク管理が必要なAIエージェントに最適です。 Use when running multi-step or long-running agent jobs in aios that require checkpointing, retries, evidence capture, and safe human handoff.

このスキルを使用する理由

Playwright Browser MCPとContextDBを使用して、エージェントが長時間のタスクを信頼性高く実行できるようにし、安定性を確保し、ツールの出力をキャプチャし、冪等的なステップと明示的な成功/失敗の証拠を使用します。Codex CLI、Claude Code、Gemini CLI、OpenCodeと共同作業する開発者に最適です。

おすすめ

UIのドリフトやモデル変動性の下で安定性を維持するための堅牢な長時間実行タスク管理が必要なAIエージェントに最適です。

実現可能なユースケース for aios-long-running-harness

UIのドリフトやモデル変動性の下で長時間実行タスクを安定させる
冪等的なステップと明示的な成功/失敗の証拠を使用して、タスクを信頼性高く完了する
デバッグと検証の目的でツールの出力をキャプチャする

! セキュリティと制限

  • Playwright Browser MCPとContextDBの設定が必要
  • ローカルファーストのAIエージェントブートストラップ用に設計
  • 部分的な故障や予算の制約に対応するための調整が必要になる可能性がある

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.

Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is aios-long-running-harness?

UIのドリフトやモデル変動性の下で安定性を維持するための堅牢な長時間実行タスク管理が必要なAIエージェントに最適です。 Use when running multi-step or long-running agent jobs in aios that require checkpointing, retries, evidence capture, and safe human handoff.

How do I install aios-long-running-harness?

Run the command: npx killer-skills add rexleimo/rex-cli/aios-long-running-harness. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for aios-long-running-harness?

Key use cases include: UIのドリフトやモデル変動性の下で長時間実行タスクを安定させる, 冪等的なステップと明示的な成功/失敗の証拠を使用して、タスクを信頼性高く完了する, デバッグと検証の目的でツールの出力をキャプチャする.

Which IDEs are compatible with aios-long-running-harness?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for aios-long-running-harness?

Playwright Browser MCPとContextDBの設定が必要. ローカルファーストのAIエージェントブートストラップ用に設計. 部分的な故障や予算の制約に対応するための調整が必要になる可能性がある.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add rexleimo/rex-cli/aios-long-running-harness. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use aios-long-running-harness immediately in the current project.

! Reference-Only Mode

This page remains useful for installation and reference, but Killer-Skills no longer treats it as a primary indexable landing page. Read the review above before relying on the upstream repository instructions.

Imported Repository Instructions

The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.

Supporting Evidence

aios-long-running-harness

Install aios-long-running-harness, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command...

SKILL.md
Readonly
Imported Repository Instructions
The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.
Supporting Evidence

AIOS Long-Running Harness

Overview

Use this harness to keep long tasks stable under UI drift, model variability, and partial failures. It maps Anthropic's long-running-agent harness ideas into this repository's file-based workflow.

Harness Loop

  1. Preflight: lock objective, stop conditions, budgets, and required artifacts.
  2. Plan: split into idempotent steps with explicit success/failure evidence.
  3. Execute: run one step at a time with tool output capture.
  4. Verify: assert completion from page evidence, not assumptions.
  5. Checkpoint: persist current state, artifacts, and next action.
  6. Recover: on failure, classify and retry only with a changed hypothesis.
  7. Complete: run final verification and write summary doc.

Pairing with Superpowers Skills

  • Plan step should be produced through superpowers:writing-plans (or superpowers:brainstorming first when scope is unclear).
  • For 2+ independent domains, use superpowers:dispatching-parallel-agents; for coupled domains, run sequentially.
  • If the runtime has no true subagent tool, emulate dispatch with explicit per-domain task queues and only parallelize safe independent reads/checks.
  • Always finish with superpowers:verification-before-completion before claiming run success.

Orchestrate Live Notes

  • When running aios orchestrate --execute live with AIOS_SUBAGENT_CLIENT=codex-cli, Codex CLI v0.114+ supports structured exec outputs (--output-schema, --output-last-message, stdin). AIOS uses them when available and falls back to stdout parsing for older versions.

Required Controls

  • Time budget per step and per run.
  • Retry budget per failure class.
  • Human-gate checkpoints for login, payment, or policy-sensitive actions.
  • Structured logs for every major transition.

Failure Classes

  • Selector/UI drift.
  • Authentication/session loss.
  • Policy rejection/content moderation.
  • Network/transient failures.
  • Tool/runtime errors.

Completion Gate

Declare success only when all are true:

  • Target action succeeded.
  • Expected artifact exists.
  • Evidence snapshot/log exists.
  • Updated runbook reflects newly observed drift.

Resources

  • references/harness-checklist.md: operational checklist template.
  • references/anthropic-mapping.md: principle-to-project mapping.

関連スキル

Looking for an alternative to aios-long-running-harness or another community skill for your workflow? Explore these related open-source skills.

すべて表示

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

カスタマイズ可能なウィジェットプラグインをprompts.chatのフィードシステム用に生成する

149.6k
0
AI

flags

Logo of vercel
vercel

React フレームワーク

138.4k
0
ブラウザ

pr-review

Logo of pytorch
pytorch

Pythonにおけるテンソルと動的ニューラルネットワーク(強力なGPUアクセラレーション)

98.6k
0
開発者