Super-Prompt Patterns
SkillAI & modelsUse when drafting, executing, or reviewing Codex super-prompts for this repository.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Super-Prompt Patterns skill
What this skill tells your AI
The instructions your AI receives, as published by nebius/nebius-physical-ai in skills/atomic/super-prompt-patterns/SKILL.md and read by ahel’s review.
Dirty Tree
Use RELAXED_DIRTY_TREE_MODE: halt only when dirty files overlap with the run's target paths. Pre-existing dirty files in unrelated paths never halt the run.
Budgets
Do not add time, cost, or job-count limits unless the operator explicitly specifies them. Strip per-phase time budgets, wall-clock caps, and GPU spend limits from prompts.
Phase Shape
Standard phase flow:
- Phase 0: state check, read-only.
- Phase A: design.
- Phase B-G: implementation.
- Phase L: final report.
NOVEL_ISSUE Protocol
Log novel issues to /tmp/<run-id>/novel-issues.md. Use log/skip/continue for non-blocking issues and halt only for true blockers.
Commit Lock
Acquire /tmp/npa-commit-lock/<scope> during commit phases for parallel runs that share files.
Broken CLI Workflow
If the npa CLI is broken during a run, document the breakage as a structured prompt, run Codex to fix it, then use the fixed CLI.
Autonomous Run Rhythm
Use separate agents by phase: Build with Codex, verify with Codex in read-only mode, review with Claude Code for architecture, then cleanup with Codex in a scoped pass.
Trigger a Claude Code review after 3 or more commits land. The CC agent must differ from the building agent.
Root AGENTS.md is a lightweight index; details belong in skill files.
Signals
- GitHub stars
- 28
- Forks
- 15
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
super-prompt-patterns- Source
- github.com/nebius/nebius-physical-ai