0xwilliamortiz
Featured
openclaude-improved
OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It addresses a common productivity struggle by embedding behavioral accountability directly into the AI agent's workflow, using the agent's natural context to detect and interrupt counterproductive patterns in real time.
Who it is for
- Developers who use Claude Code, Codex, or OpenCode as their primary coding assistant
- People with ADHD tendencies who struggle with distraction and task completion
- Solopreneurs or freelancers managing multiple projects and priorities
- Anyone who wants to align daily work with long-term goals but finds it hard to maintain focus
Use cases
- Setting up a personal profile of goals and anti-patterns, then receiving automatic reminders when the agent detects you're falling into a known trap
- Getting a prioritized, goal-aligned task list instead of an overwhelming todo dump
- Receiving a verbal nudge when you've been stuck on a non-essential task for too long
- Using the alignment check on demand to refocus after a distraction
Strengths
- Proactive awareness: the mentor scans your ongoing activity and speaks up when you violate your own don't-let-me list, without needing manual check-ins
- Privacy-first: all data stored as local plain markdown files, nothing sent externally, and uninstall leaves only two user-owned files
- Cross-agent portability: works with Claude Code, Codex, and OpenCode using the same shared profile, so your mentor follows you across tools
- Honest self-reflection: the interview process forces you to articulate your anti-patterns while you're still objective, making the nudges later more impactful
Considerations
- Effectiveness varies by underlying model; the README notes the nudges land better with Claude than with Codex or OpenCode
- Setup requires a one-time ten-minute interview, which may feel heavy for someone who just wants a quick productivity boost
- Only works within supported agent environments (Claude Code, Codex, OpenCode); not a standalone app or browser extension
README quick start
mentor
Turn your agent into a mentor. It knows what you're working toward, and how you get in your own way.
Install
Claude Code
claude plugin marketplace add hcsum/dont-let-me
claude plugin install mentor@dont-let-me
Then run /mentor:init to set up your profile, and /mentor:check any time you
want the alignment check on demand.
Codex
codex plugin marketplace add hcsum/dont-let-me --ref main
codex plugin add mentor@dont-let-me
Then run $mentor-init to set up your profile, and $mentor-check any time you
want the alignment check on demand.
Codex makes you trust a hook before it runs: open /hooks, review the
SessionStart entry, trust it. Until you do, the profile never loads.
OpenCode
OpenCode has no plugin marketplace for this, so clone it and point the config at the two pieces:
git clone https://github.com/hcsum/dont-let-me.git ~/.mentor/plugin
// ~/.config/opencode/opencode.json
{
"instructions": ["~/.mentor/plugin/stance.md", "~/.mentor/profile.md"],
"skills": { "paths": ["~/.mentor/plugin/skills"] }
}
Then run /mentor-init to set up your profile, and /mentor-check any time you
want the alignment check on demand.
In my own use, Claude Code is where this works best. Codex and OpenCode both run it, but how well the nudges land depends on the model behind them, and I've had better results with Claude.
1. It interviews you
Setup asks you questions, one at a time, for about ten minutes. Run /mentor:init
in Claude Code, $mentor-init in Codex, /mentor-init in OpenCode. Two things
come out of it.
Your long-term goals. What you're actually working toward. It pushes back if you answer vaguely.
Your anti-patterns. The ways you reliably get in your own way, written down while you're still honest about them, so it can hold you to them later when you're not:
- [ship] don't let me build in private forever, waiting for it to be ready
- [explore] don't let me keep opening new threads while nothing is finished
You do this once and rarely touch it again.
2. Then you just talk to it
mentor, what's on my plate today?
Ask what's on your plate and it won't read you the whole todo list. It picks the few that serve your main goals and names the first move on one, small enough to start now.
add "ship the landing page" to my todos
P
Description
Turn your agent into a mentor. It knows what you're working toward, and how you get in your own way.
Related repositories
Similar projects matched by category, topics, and programming language.
jamesob
Featured
local-llm
A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.
mereyabdenbekuly-ctrl
Featured
clodex-ide
Clodex is an open-source, local-first agentic IDE that combines persistent AI tasks, code, terminal, browser, Git, models, memory, and governed execution in one Electron workspace, currently in technical preview.