@Voxyz_ai: Every time you let Opus 5.5 run a long task on its own, have it vibe-code a quick ๐๐ง๐ ๐ ๐ฑ๐ฎ๐๐ต๐ฏ๐ผ๐ฎ๐ฟ๐ฑ like thisโฆ
Summary
This article proposes a technique for using Opus 5.5 to automate the creation and updating of an HTML dashboard during lengthy coding sessions, by configuring a specialized subagent that builds dashboards tailored to user preferences.
View Cached Full Text
Cached at: 09/27/26, 05:16 AM
Whenever you let Opus 5.5 run a long task on its own, have it vibe-code a quick HTML dashboard like this first.
Then give it a subagent that only builds dashboards: โ Name it dashboard-builder, set its effort to medium, and preload a design skill โ The first time, it asks what style you like and saves it to memory. After that, every dashboard fits your taste and the task at hand โ Call it before every long task. It builds the dashboard in the background in about two minutes, and the main session keeps coding on high without stopping โ The dashboard shows four things: task progress, whatโs stuck, questions waiting on you, and what itโll do by default if you donโt answer
Send this prompt to Claude Code ๐
โSet up a subagent that only builds progress dashboards:
- Create dashboard-builder in ~/.claude/agents: model: opus, effort: medium, memory: user. Preload the design skills I have installed (for example impeccable). It can only read and write the .dashboard/ folder and its own memory.
- The first time, it asks me what style I like: dark or light, dense or airy, and one accent color. It saves my answer to memory and follows it every time. Pick the panels for the current task; donโt use a template.
- The dashboard is one HTML file showing tasks and their status, questions waiting for me with the default action, the latest deliverables, and anything stuck. Use the real clock for every time. It opens with a double-click and refreshes itself every 10 seconds.
- Add a rule to ~/.claude/CLAUDE.md: for any task with more than 5 steps or that should take longer than 30 minutes, have dashboard-builder set up the dashboard before starting; update it after every step; when you need a decision from me, add it to the questions list and keep going with the default.
Show me the contents of the files youโll create or change, then explain the whole flow in words a 10-year-old could follow. Donโt write anything until I confirm.โ
Similar Articles
@eng_khairallah1: Claude Coders: run this Opus 5.5 command NOW '/insights' opus 5.5 reads your last 200 sessions and writes you a report:โฆ
A tip-focused tweet urging Claude Code users to run the '/insights' command in Claude Opus 5.5, which analyzes the last 200 sessions to highlight work patterns, recurring blockers, and unused features, plus a quoted guide on building AI agent teams with the model.
@Av1dlive: i finally mastered how to maximise my opus 5.5 usage limits... the trick: let jev choose which subagent gets each task โฆ
A user shares a method to maximize Opus 5.5 AI model usage limits by using JEV to assign worker profiles and effort levels for task management.
@gauravsbuilding: I put Opus 5.5 on Ultracode mode and asked it to create the best motion design launch video it possibly could 12 hours โฆ
A user demonstrated the capabilities of the Opus 5.5 AI model by setting it to Ultracode mode to generate a motion design launch video after 12 hours of continuous running.
@bcherny: Seeing a number of benchmarks showing Opus is the best model for long-running work. Five tips for running Opus autonomoโฆ
Practical tips for running Anthropic's Claude Opus autonomously for hours or days, such as using auto mode, dynamic workflows, and self-verification; also references the SWE-Marathon benchmark for long-horizon software tasks.
Getting the most out of Opus 5.5 in Claude and Claude Code
Anthropic published a practical guide on getting the most out of Opus 5.5 in Claude and Claude Code, covering how to hand over whole tasks with clear finish lines, drop "think carefully" lines since the model always reasons before replying, and steer long autonomous coding runs.