Rich Tabor
@rich.blog
Writes about the future of WordPress, Blocks & Design ✴︎ Product
@automattic ✴︎ Making @WordPress
@automattic ✴︎ Making @WordPress
Copy my Linear product manager subagent to make great issues on the fly, without ever leaving Claude Code. Works great for when you want to record something to do later.
agents.foo/linear-prod...
agents.foo/linear-prod...
linear-product-manager | Agents.foo
Use this agent when you need to create, structure, or manage issues in Linear, or set up MCP Linear integration. This includes writing well-formatted issue descriptions, selecting appropriate projects and teams, setting priorities, adding labels, ensuring issues follow best practices for product management, and configuring MCP Linear for automated workflows. The agent understands Linear's data model, MCP (Model Context Protocol) integration capabilities, and can help with issue templates, epics, project organization, and MCP setup. Examples: User wants to create a new feature request in Linear - 'I need to create an issue for adding dark mode to our settings page' - I'll use the linear-product-manager agent to help create a well-structured issue for this feature request. User has just finished implementing a feature and wants to document a bug found during testing - 'I found a bug where the login button doesn't work on mobile Safari' - Let me use the linear-product-manager agent to cre
agents.foo
August 25, 2025 at 10:00 AM
Copy my Linear product manager subagent to make great issues on the fly, without ever leaving Claude Code. Works great for when you want to record something to do later.
agents.foo/linear-prod...
agents.foo/linear-prod...
I shared all my daily driver agents on agents[dot]foo and wrote about them.
Full post: rich.blog/agents-foo
Full post: rich.blog/agents-foo
August 21, 2025 at 10:15 AM
I shared all my daily driver agents on agents[dot]foo and wrote about them.
Full post: rich.blog/agents-foo
Full post: rich.blog/agents-foo
What’s surprising to me is that we’ve already distilled agentic programming down to simple markdown files.
No complex frameworks or orchestration layers.
Just clear instructions about what you want the agent to know and how you want it to help. This feels like how AI should actually work.
No complex frameworks or orchestration layers.
Just clear instructions about what you want the agent to know and how you want it to help. This feels like how AI should actually work.
August 21, 2025 at 10:15 AM
What’s surprising to me is that we’ve already distilled agentic programming down to simple markdown files.
No complex frameworks or orchestration layers.
Just clear instructions about what you want the agent to know and how you want it to help. This feels like how AI should actually work.
No complex frameworks or orchestration layers.
Just clear instructions about what you want the agent to know and how you want it to help. This feels like how AI should actually work.
My favorite: A Linear product manager agent that creates perfect issues when I find bugs but don't want to lose coding momentum.
It explores my codebase, finds relevant components, includes file paths, and writes issues that actually help.
Like having a technical triage guy sitting next to me.
It explores my codebase, finds relevant components, includes file paths, and writes issues that actually help.
Like having a technical triage guy sitting next to me.
August 21, 2025 at 10:15 AM
My favorite: A Linear product manager agent that creates perfect issues when I find bugs but don't want to lose coding momentum.
It explores my codebase, finds relevant components, includes file paths, and writes issues that actually help.
Like having a technical triage guy sitting next to me.
It explores my codebase, finds relevant components, includes file paths, and writes issues that actually help.
Like having a technical triage guy sitting next to me.
Read them for yourself:
docs.github.com/en/enterpri...
docs.github.com/en/enterpri...
Best practices for using GitHub Copilot to work on tasks - GitHub Enterprise Cloud Docs
Learn how to get the best results from Copilot coding agent.
docs-internal.github.com
August 20, 2025 at 11:56 AM
Read them for yourself:
docs.github.com/en/enterpri...
docs.github.com/en/enterpri...
Download Kanso for yourself:
rich.blog/kanso/
rich.blog/kanso/
Meet Kanso, my best blogging theme yet
Since my latest design refresh, many folks have been asking about the WordPress theme I’m using and how to get it. So, same as before, I’ve made my blog's…
rich.blog
August 19, 2025 at 12:02 PM
Download Kanso for yourself:
rich.blog/kanso/
rich.blog/kanso/
I baked in a couple color/font variations too. One-click vibes.
August 19, 2025 at 12:02 PM
I baked in a couple color/font variations too. One-click vibes.
August 19, 2025 at 10:16 AM
Less debugging/more thinking.
The best developers are better at prompting, better product leaders, better strategic thinkers, and better at tracking what changed in their codebase.
The good news: those skills transfer whether you’re working with AI or humans.
The best developers are better at prompting, better product leaders, better strategic thinkers, and better at tracking what changed in their codebase.
The good news: those skills transfer whether you’re working with AI or humans.
August 19, 2025 at 10:16 AM
Less debugging/more thinking.
The best developers are better at prompting, better product leaders, better strategic thinkers, and better at tracking what changed in their codebase.
The good news: those skills transfer whether you’re working with AI or humans.
The best developers are better at prompting, better product leaders, better strategic thinkers, and better at tracking what changed in their codebase.
The good news: those skills transfer whether you’re working with AI or humans.
I typically scope ideas with Claude Code, log the issues I don't want to do asap with my Linear PM agent, then tackle implementation.
When it’s time for a pull request, I have another AI pair programmer (usually @Copilot) handle the initial review.
I'm more of the technical lead making the calls.
When it’s time for a pull request, I have another AI pair programmer (usually @Copilot) handle the initial review.
I'm more of the technical lead making the calls.
August 19, 2025 at 10:16 AM
I typically scope ideas with Claude Code, log the issues I don't want to do asap with my Linear PM agent, then tackle implementation.
When it’s time for a pull request, I have another AI pair programmer (usually @Copilot) handle the initial review.
I'm more of the technical lead making the calls.
When it’s time for a pull request, I have another AI pair programmer (usually @Copilot) handle the initial review.
I'm more of the technical lead making the calls.
I don’t need to understand every technical implementation detail, but I need to understand how to prompt these systems effectively.
And how to distinguish good output from garbage.
And how to distinguish good output from garbage.
August 19, 2025 at 10:16 AM
I don’t need to understand every technical implementation detail, but I need to understand how to prompt these systems effectively.
And how to distinguish good output from garbage.
And how to distinguish good output from garbage.
The difference is partnership vs just getting code generated.
Vibe coding = blind trust.
AI-augmented coding = guidance. Will this scale? Is the architecture sound? Does it handle edge cases?
Vibe coding = blind trust.
AI-augmented coding = guidance. Will this scale? Is the architecture sound? Does it handle edge cases?
August 19, 2025 at 10:16 AM
The difference is partnership vs just getting code generated.
Vibe coding = blind trust.
AI-augmented coding = guidance. Will this scale? Is the architecture sound? Does it handle edge cases?
Vibe coding = blind trust.
AI-augmented coding = guidance. Will this scale? Is the architecture sound? Does it handle edge cases?