neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
Vibecoding harness: structured planning → checklist execution → multi-lens self-review. Works with Cursor, Claude Code, Codex, and more.
Developer toolsTypeScript · JavaScriptGitHub @mt2007Self-installOwner unconfirmed
Paste into Claude or ChatGPT for installation instructions suited to your environment.
Have you tried it? One tap is enough. No sign-in needed.
Loading the full README. The saved excerpt is shown below.
autopilot-harness — a vibecoding harness that turns open-ended agent chat into structured planning → checklist execution → multi-lens self-review. (中文说明) Vibe coding is fast until scope drifts, acceptance stays implicit, and “looks done” skips hard review angles. Autopilot keeps the agent on a durable track: 1. Grill the plan before writing product code 2. Execute against a checklist (artifacts.plans_dir/ /, new-init default docs/autopilot/plans) 3. Self-review under rotating lenses before an item is marked doneRead the full README ↗
The full README is unavailable right now. Read it at the original link. The saved excerpt is shown below.
autopilot-harness — a vibecoding harness that turns open-ended agent chat into structured planning → checklist execution → multi-lens self-review. (中文说明) Vibe coding is fast until scope drifts, acceptance stays implicit, and “looks done” skips hard review angles. Autopilot keeps the agent on a durable track: 1. Grill the plan before writing product code 2. Execute against a checklist (artifacts.plans_dir/ /, new-init default docs/autopilot/plans) 3. Self-review under rotating lenses before an item is marked doneRead the full README ↗