brendon_gorelik's Corner of the Web

Tag: software

  • # Agents|software
    • Make commits atomic. git commit -m "<scoped message>" -- path/to/file1 path/to/file2 skips git add and commits just specific already tracked files. Use git restore --staged :/ && git add "path/to/file1" "path/to/file2" && git commit -m "<scoped message>" -- path/to/file1 path/to/file2 for untracked files (which have to be added first). Now you can trust agents to use git (agent file).
    • Terminal grid, parallel agents, same folders, gpt-5-codex mid.
    • Beware of the prompts Blast Radius (time and file-span)

      • If something takes longer than I anticipated, I just hit escape and ask “what’s the status” to get a status update

    • Tab in Codex to queue next prompt. Can use for related features
    • 50% of prompts contain a screenshot and uses Wisp Flow
    • Cli > MCP: less context, can concatenate calls, tools more local.
      • does use chrome-devtools-mcp
    • On Spec-driven development:

      • My current approach is usually that I start a discussion with codex, I paste in some websites, some ideas, ask it to read code, and we flesh out a new feature together. If it’s something tricky, I ask it to write everything into a spec, give that to GPT-5-Pro for review (via chatgpt.com) to see if it has better ideas (surprisingly often, this greatly improves my plan!) and then paste back what I think is useful into the main context to update the file.

    • Ask the model to write tests after each feature/fix is done. Use the same context. This will lead to far better tests, and likely uncover a bug in your implementation.

    • My Agent file is currently ~800 lines long and feels like a collection of organizational scar tissue. I didn’t write it, codex did, and anytime sth happens I ask it to make a concise note in there.

  • # software

    My Notes on the Pragmatic Programmer 2nd Edition.

  • # Agents|software
    • Make commits atomic. git commit -m "<scoped message>" -- path/to/file1 path/to/file2 skips git add and commits just specific already tracked files. Use git restore --staged :/ && git add "path/to/file1" "path/to/file2" && git commit -m "<scoped message>" -- path/to/file1 path/to/file2 for untracked files (which have to be added first). Now you can trust agents to use git (agent file).
    • Terminal grid, parallel agents, same folders, gpt-5-codex mid.
    • Beware of the prompts Blast Radius (time and file-span)

      • If something takes longer than I anticipated, I just hit escape and ask “what’s the status” to get a status update

    • Tab in Codex to queue next prompt. Can use for related features
    • 50% of prompts contain a screenshot and uses Wisp Flow
    • Cli > MCP: less context, can concatenate calls, tools more local.
      • does use chrome-devtools-mcp
    • On Spec-driven development:

      • My current approach is usually that I start a discussion with codex, I paste in some websites, some ideas, ask it to read code, and we flesh out a new feature together. If it’s something tricky, I ask it to write everything into a spec, give that to GPT-5-Pro for review (via chatgpt.com) to see if it has better ideas (surprisingly often, this greatly improves my plan!) and then paste back what I think is useful into the main context to update the file.

    • Ask the model to write tests after each feature/fix is done. Use the same context. This will lead to far better tests, and likely uncover a bug in your implementation.

    • My Agent file is currently ~800 lines long and feels like a collection of organizational scar tissue. I didn’t write it, codex did, and anytime sth happens I ask it to make a concise note in there.