BitTide
Menu
中文 Sign in

custom-agent

Tag

Cards List
#custom-agent

@Saccc_c: How to give your Codex unlimited bullets? Set the subagent to luna-max. Use sol for complex task design and luna-max for parallel execution. Specific setup: Enter the following prompt in the Codex conversation: In ~/.codex/agents/luna-worke…

X AI KOLs Following ↗ · 2026-08-01 Cached

Shares a method for customizing a Codex subagent (luna-max) and configuring it as luna-worker, allowing complex tasks to use sol for design and luna-max for parallel execution, resulting in stronger execution capability.

0 favorites 0 likes
#custom-agent

@seclink: Mimofan Today's Update (2026-07-30) Core Capabilities - [x] Active Task Notification -- Automatically notifies the model upon background task completion, no manual polling needed - [x] Custom Agent -- Define domain-specific agents via Markdown + YAML frontmatter - [x] Parallel Sub-agent Execution -- Read-only tools execute concurrently, doubling analysis speed for large codebases - [x] /fast Speed Mode -- One-click switch to low-cost model + reduced reasoning, quickly completes simple tasks - [x] Automatic Retry on Empty Response -- Automatically retries when LLM returns empty response, improving stability

X AI KOLs Timeline ↗ · 2026-07-30 Cached

Mimofan's today's update introduces several core capability improvements, including active task notification, custom agents, parallel sub-agent execution, fast mode, etc., while optimizing infrastructure and user experience.

0 favorites 0 likes
#custom-agent

@sydneyrunkle: https://x.com/sydneyrunkle/status/2062217190724579673

X AI KOLs Timeline ↗ · 2026-06-03 Cached

A guide on building custom agent harnesses using LangChain's create_agent, focusing on middleware for customization.

0 favorites 0 likes
← Back to home

Submit Feedback