Bil0000/Hill-Climb
AI skill
Can I trust it?
No red flags in our checks.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change 3 days ago.
Licence OK
MIT: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
A Claude Code and Codex skill with a single Python script that makes a coding agent work in small steps against a locked command or test score. A step is committed only if the score improves and the guard checks still pass; otherwise the tree is reset. Locked test files are…
Who it's for
Developers using Claude Code or Codex who want an agent's changes verified by tests or benchmarks
How to use it
Install
/plugin install hill-climb@hill-climbFrom its README. Check it there before running it.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up Bil0000/Hill-Climb in my project. Follow its README: https://github.com/Bil0000/Hill-Climb. Explain each step and check it is safe before running anything.
Star curve
Get alerts for repos like this
We'll email you when something in AI agents starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/Bil0000/Hill-Climb?ref=badge)Similar repos
- sno-ai/sno-station-skills
A set of 31 tested skills that add team working habits to Claude Code and Codex. It provides cross-vendor peer review, automatic handoff when an agent's quota runs low, a one-page morning brief, work
- aicodeking/leanrea
A single 8 KB agent skill file that gives AI coding agents routing rules and ready-to-run plain CLI commands for reverse engineering binaries, Electron apps and bundles, instead of an MCP server. It r
- richardedens/crissp
A Python framework for an agentic software development lifecycle with Claude Code. AI colleagues plan, build and review work, scripted guards check every change with tests and coverage gates, and the
- mari8711/agent-runtime-kit
A typed, async Python runtime layer that runs coding-agent tasks through the Claude Agent SDK, OpenAI Codex SDK, or Google Antigravity SDK behind one shared task and result API. It reports unsupported
- collinzrj/claude-code-auto-safeguard-prompt
A system prompt and rule set for a security monitor that evaluates the latest action of autonomous AI coding agents and decides whether to block it. It defines hard and soft block categories covering
- alexyc9381/court-skill
A Claude Code skill that stages a mock trial of your idea. A prosecutor and a defense argue the case, then 12 juror personas vote GUILTY or NOT GUILTY independently, and a judge lists the conditions t