hashgraph-online/awesome-codex-plugins / plugins/beastlabai/multi-llm-plugin/skills/multi-llm
multi-llm
FlaggedOrchestrate plan reviews, task generation, implementation and code reviews across several LLM CLIs in parallel, or ask every model one free-text question about a plan. Use when the user says: review my plan, multi-llm, run a code review, generate tasks from a plan, implement this plan, ask the models about my plan.
finalize_tracking.py
View on GitHub#!/usr/bin/env python3
"""Finalize file tracking after implementation completes.
Usage:
uv run --project "{SKILL_DIR}" -- python "{SKILL_DIR}/multi_llm.py" util finalize-tracking --state-file <path_to_state.json>
The census itself is ``utils/tracking.py``; this script is its command. Every
name of ``utils.tracking`` reads through this module too, for reading only: the
code that uses a name reads it in ``utils.tracking``, so patch it there, never
here (docs/development/dispatcher.md#import-layers).
"""
import sys
from pathlib import Path
from typing import Any, List
# Add parent to path for imports
sys.path.insert(0, str(Path(__file__).parent))
from utils import tracking as _tracking # noqa: E402
from utils.stream_bootstrap import bootstrap_streams # noqa: E402
from utils.tracking import main # noqa: E402
def __getattr__(name: str) -> Any:
"""Any other name of ``utils.tracking``, read from its owner at each access."""
try:
return getattr(_tracking, name)
except AttributeError:
raise AttributeError(f"module {__name__!r} has no attribute {name!r}") from None
def __dir__() -> List[str]:
return sorted({*globals(), *dir(_tracking)})
if __name__ == "__main__":
bootstrap_streams() # every script entry bootstraps its streams; main does it again
sys.exit(main(sys.argv[1:]))
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |