oil-oil/codex-team-mode / skills/team-mode
team-mode
VerifiedUse when a task may benefit from a bounded subagent for implementation, large-codebase discovery at task start, independent review, requested or pre-commit code simplification, or expert work on complex decisions, modeling, automation, or repeated failures. The main agent chooses whether to delegate and accepts the result. Do not use for simple questions or short work with no meaningful review or delegation.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 1.8 KB |
| SKILL.md | skill md | 5.2 KB |
| agents/openai.yaml | config | 410 B |
| references/custom-agents.md | markdown | 4.1 KB |
| references/evaluation.md | markdown | 2.3 KB |
| references/explore.md | markdown | 654 B |
| references/interactive-testing.md | markdown | 1.4 KB |
| references/simplify.md | markdown | 2.9 KB |
| scripts/current_model.pyexecutable | script | 3.4 KB |
| scripts/usage_by_model.pyexecutable | script | 36.0 KB |
scripts/current_model.py
View on GitHub#!/usr/bin/env python3
"""Best-effort lookup of the current task model from local Codex traces."""
from __future__ import annotations
import json
import os
import sys
from datetime import datetime, timezone
from pathlib import Path
from typing import Any
def codex_home() -> Path:
configured = os.environ.get("CODEX_HOME")
return Path(configured).expanduser() if configured else Path.home() / ".codex"
def parse_time(value: Any) -> datetime | None:
if not isinstance(value, str) or not value:
return None
try:
parsed = datetime.fromisoformat(value.replace("Z", "+00:00"))
return parsed.replace(tzinfo=timezone.utc) if parsed.tzinfo is None else parsed
except ValueError:
return None
def emit_unknown(reason: str) -> int:
print(json.dumps({"status": "unknown", "reason": reason}, ensure_ascii=False))
return 2
def main() -> int:
task_id = os.environ.get("CODEX_THREAD_ID")
if not task_id:
return emit_unknown("CODEX_THREAD_ID is not set")
home = codex_home()
active_root = home / "sessions"
archived_root = home / "archived_sessions"
roots = [root for root in (active_root, archived_root) if root.is_dir()]
candidates: list[tuple[datetime, str, str | None]] = []
# Match the task ID in filenames before reading traces. Trace formats are internal,
# so return unknown on failure instead of inferring the runtime model from config.
for root in roots:
for path in root.rglob(f"*{task_id}*.jsonl"):
meta_id: str | None = None
contexts: list[tuple[datetime, str, str | None]] = []
try:
with path.open("r", encoding="utf-8") as trace:
for line in trace:
try:
event = json.loads(line)
except json.JSONDecodeError:
continue
if not isinstance(event, dict):
continue
payload = event.get("payload") or {}
if not isinstance(payload, dict):
continue
if event.get("type") == "session_meta":
meta_id = payload.get("id") or payload.get("session_id")
elif event.get("type") == "turn_context":
model = payload.get("model")
timestamp = parse_time(event.get("timestamp") or payload.get("timestamp"))
if isinstance(model, str) and model and timestamp:
effort = payload.get("effort")
contexts.append((timestamp, model, effort if isinstance(effort, str) else None))
except OSError:
continue
# Exclude subagents whose filename contains the root task ID.
if meta_id != task_id:
continue
candidates.extend(contexts)
if not candidates:
return emit_unknown("No model record for the current task was found in local traces")
observed_at, model, effort = max(candidates, key=lambda item: item[0])
print(json.dumps({
"status": "ok",
"task_id": task_id,
"model": model,
"effort": effort,
"observed_at": observed_at.isoformat(),
"source": "local_codex_session_trace",
}, ensure_ascii=False))
return 0
if __name__ == "__main__":
sys.exit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |