Skip to content
View sdi2200262's full-sized avatar
👨‍💻
Discord: cobuter_man
👨‍💻
Discord: cobuter_man

Highlights

  • Pro

Block or report sdi2200262

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
sdi2200262/README.md

"Should we read the code?"

It depends.

As a counterexample: would you be comfortable if Linux kernel maintainers stopped reviewing code and let autonomous agents commit directly? At least as of October 2026, I am not.

When building agentic software and developer utilities, I prioritize human agency while trying to get the most out of LLMs. Personal favorite projects are pinned below.

Pinned Loading

  1. agentic-project-management agentic-project-management Public template

    A framework for managing complex projects with spec-driven multi-agent workflows.

    JavaScript 2.4k 230

  2. elements-of-style-for-agents elements-of-style-for-agents Public

    A compact plain-English writing standard for clear, concise agent communication and authored prose.

    20

  3. cc-context-awareness cc-context-awareness Public

    Tell Claude what to do based on how much context it has used. Set thresholds, inject custom instructions, and trigger workflows based on live context usage.

    Shell 35 3

  4. cc-get-my-context cc-get-my-context Public

    A Claude Code skill that enables Claude to get it's context window usage at any time.

    Shell 5

  5. focus-shell focus-shell Public

    Minimal bash script to block distracting sites for macOS and Linux.

    Shell 1