akiiwa-games/AgentCompass / skills/agent-compass
agent-compass
FlaggedChoose owner, model and effort, outbound authorization, advisor use, and continuation for delegated work. Reads local usage and effective account policy, profiles the task with the configured System-One scorer, then allocates a compatible worker. Use for independent worker or advisor work; ordinary local execution needs no routing.
scripts/conftest.py
View on GitHub"""Autouse isolation fixtures for the agent-compass scripts suite."""
import pytest
@pytest.fixture(autouse=True)
def disabled_score_cache(monkeypatch):
"""Tests never touch the machine's real score cache and count scorer calls; cache tests opt back in."""
monkeypatch.setenv('ROUTER_SCORE_CACHE', 'off')
@pytest.fixture(autouse=True)
def offline_lookups(monkeypatch):
"""Tests never look up the Antigravity tier or the published reference data over the network, and read the shipped
references; antigravity_plan and public_data tests pass their own environment."""
monkeypatch.setenv('AGENTCOMPASS_ANTIGRAVITY_PLAN', 'off')
monkeypatch.setenv('AGENTCOMPASS_PUBLIC_DATA', 'off')
@pytest.fixture(autouse=True)
def isolated_launch_failures(monkeypatch):
"""Tests never read or write the machine's launch-failure cooldowns; test_launch_failures opts back in."""
monkeypatch.setenv('ROUTER_LAUNCH_FAILURES', 'off')
@pytest.fixture(autouse=True)
def isolated_model_latches(monkeypatch):
"""Tests never read or write the machine's latched models; model-latch tests point it at their own file."""
monkeypatch.setenv('ROUTER_MODEL_LATCH', 'off')
@pytest.fixture(autouse=True)
def isolated_provider_retries(monkeypatch):
"""Tests never read or write the machine's provider-retry holds; provider-retry tests point it at their own file."""
monkeypatch.setenv('ROUTER_PROVIDER_RETRY', 'off')
@pytest.fixture(autouse=True)
def isolated_live_models(monkeypatch):
"""Tests never read or write the machine's live-model cache; live-model tests point it at their own file."""
monkeypatch.setenv('AGENTCOMPASS_LIVE_MODELS', 'off')
@pytest.fixture(autouse=True)
def bare_tasks_get_a_profile(monkeypatch):
"""The router plans only a task with a classifier profile (its category demands). Most tests write a task with a few
fields; this gives such a task the profile `router_test_support.profile_for` derives. A test of the missing-profile
error calls `task_intake.normalize_task.__wrapped__` or `validate_profile` and is untouched."""
import task_intake
import router_test_support
real = task_intake.normalize_task
def normalize(raw, *args, **kwargs):
task = dict(raw or {})
if task.get('profile') is None:
task['profile'] = router_test_support.profile_for(task)
return real(task, *args, **kwargs)
normalize.__wrapped__ = real
monkeypatch.setattr(task_intake, 'normalize_task', normalize)
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 |