Skip to content

akiiwa-games/AgentCompass / skills/agent-compass

agent-compass

Flagged

Choose 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.

FileKindSize
SKILL.mdskill md5.5 KB
agents/openai.yamlconfig427 B
calibration/README.mdmarkdown55.2 KB
calibration/arena_capture.pyscript14.0 KB
calibration/community.pyscript25.2 KB
calibration/five_axis.pyscript196.4 KB
calibration/measurements.pyscript68.4 KB
calibration/refresh.pyscript48.6 KB
calibration/series.pyscript10.2 KB
calibration/sources.pyscript24.1 KB
calibration/tiers.pyscript14.6 KB
grok-bot/.gitignoreother47 B
grok-bot/dependency_patch.pyscript4.5 KB
grok-bot/install_cli.pyscript3.6 KB
grok-bot/test-recovery.mjsscript8.6 KB
grok-bot/test_install_cli.pyscript4.1 KB
grok-bot/upstream.jsonconfig3.4 KB
references/accounts.jsonconfig155.9 KB
references/classifier-cases.jsonconfig21.5 KB
references/dispatch-lifecycle.mdmarkdown28.9 KB
references/dispatch-rules.mdmarkdown11.3 KB
references/effort-matching.mdmarkdown5.1 KB
references/fast-modes.mdmarkdown3.5 KB
references/five-axis-scores.jsonconfig3.1 MB
references/gemini-decisions-api.mdmarkdown2.9 KB
references/grok-bot.mdmarkdown13.0 KB
references/herdr.mdmarkdown5.1 KB
references/jev-api.mdmarkdown1.6 KB
references/level-3-conversion.jsonconfig2.4 KB
references/model-capabilities.jsonconfig3.6 KB
references/model-capabilities.mdmarkdown14.6 KB
references/parent-address-gate.mdmarkdown10.1 KB
references/plan-templates.jsonconfig13.2 KB
references/provider-discovery.mdmarkdown11.5 KB
references/provider-usage.mdmarkdown4.1 KB
references/public-data.jsonconfig816 B
references/public-measurements.jsonconfig1.3 MB
references/roll-reference.mdmarkdown26.7 KB
references/router-internals.mdmarkdown93.7 KB
references/task-classifier.mdmarkdown6.1 KB
references/user-scores.jsonconfig6.8 KB
references/work-kinds.mdmarkdown4.7 KB
references/worker-communication.mdmarkdown2.1 KB
scripts/account_fleet.pyscript32.9 KB
scripts/account_state.pyscript22.2 KB
scripts/accounts_override.pyscript14.8 KB
scripts/allocator.pyscript19.8 KB
scripts/antigravity_plan.pyscript18.7 KB
scripts/antigravity_telemetry.pyscript5.1 KB
scripts/auto_bundles.pyscript31.3 KB
scripts/axis_scores.pyscript40.3 KB
scripts/caller_input.pyscript3.0 KB
scripts/candidate_eval.pyscript54.0 KB
scripts/candidate_ranking.pyscript9.5 KB
scripts/capability_catalog.pyscript8.0 KB
scripts/check_router_contract.pyscript2.8 KB
scripts/conftest.pyscript2.5 KB
scripts/cwd_policy.pyscript1.5 KB
scripts/data_age.pyscript1.5 KB
scripts/decision_ledger.pyscript18.9 KB
scripts/demo_plan.pyscript6.3 KB
scripts/dispatch_fallback.pyscript40.3 KB
scripts/dispatch_flow.pyscript58.7 KB
scripts/dispatch_ground_truth.pyscript43.5 KB
scripts/dispatch_registry.pyscript113.7 KB
scripts/entry.pyscript1.7 KB
scripts/env_vars.pyscript580 B
scripts/fast_modes.pyscript2.5 KB
scripts/fixtures/grok-api-responses.jsonconfig907 B
scripts/fixtures/reference-accounts.jsonconfig26.9 KB
scripts/grok_bot_paths.pyscript1005 B
scripts/host_herdr.pyscript16.8 KB
scripts/host_placement.pyscript9.4 KB
scripts/host_policy.pyscript10.1 KB
scripts/launch_failures.pyscript5.9 KB
scripts/launch_values.pyscript12.3 KB
scripts/ledger_snapshot.pyscript11.1 KB
scripts/live_models.pyscript21.1 KB
scripts/model_latch.pyscript7.6 KB
scripts/model_resolution.pyscript18.0 KB
scripts/override_store.pyscript2.2 KB
scripts/plan_state_residue.pyscript5.0 KB
scripts/provider_inventory.pyscript128.2 KB
scripts/provider_retry.pyscript34.6 KB
scripts/public_data.pyscript59.2 KB
scripts/quota_economy.pyscript38.0 KB
scripts/quota_exhaustion.pyscript5.9 KB
scripts/quota_overrides.pyscript25.6 KB
scripts/quota_pools.pyscript29.8 KB
scripts/reference_provenance.pyscript32.3 KB
scripts/released_names.pyscript3.8 KB
scripts/roll.pyscript106.3 KB
scripts/route_judge.pyscript83.4 KB
scripts/route_simulation.pyscript26.3 KB
scripts/router_test_support.pyscript6.7 KB
scripts/run_grok_bot.pyscript18.8 KB
scripts/scorer_client.pyscript55.2 KB
scripts/stage_help.pyscript5.8 KB
scripts/state_upgrade.pyscript24.0 KB
scripts/subscription_cli.pyscript3.6 KB
scripts/task_intake.pyscript33.6 KB
scripts/test_account_identity.pyscript7.1 KB
scripts/test_account_state.pyscript63.3 KB
scripts/test_accounts_override.pyscript30.1 KB
scripts/test_allocator.pyscript94.2 KB
scripts/test_antigravity_plan.pyscript13.2 KB
scripts/test_applicable_quota.pyscript9.1 KB
scripts/test_auto_bundles.pyscript10.8 KB
scripts/test_billing_routing_policy.pyscript9.9 KB
scripts/test_cadence_count.pyscript32.2 KB
scripts/test_calibration_units.pyscript27.0 KB
scripts/test_capability_catalog.pyscript5.0 KB
scripts/test_decision_ledger.pyscript8.5 KB
scripts/test_demo_plan.pyscript3.4 KB
scripts/test_derived_state.pyscript21.6 KB
scripts/test_dispatch.pyscript322.3 KB
scripts/test_dispatch_answers.pyscript14.8 KB
scripts/test_dispatch_fallback.pyscript53.2 KB
scripts/test_entry.pyscript1.6 KB
scripts/test_fast_modes.pyscript9.9 KB
scripts/test_five_axis.pyscript290.1 KB
scripts/test_five_axis_economy.pyscript105.0 KB
scripts/test_fleet_parity.pyscript15.6 KB
scripts/test_grok_bot.pyscript47.7 KB
scripts/test_ground_truth_recording.pyscript68.8 KB
scripts/test_herdr.pyscript14.1 KB
scripts/test_host_policy.pyscript24.6 KB
scripts/test_launch_values.pyscript8.0 KB
scripts/test_metered_usd.pyscript60.4 KB
scripts/test_model_resolution.pyscript9.2 KB
scripts/test_named_route_facts.pyscript28.6 KB
scripts/test_native_hosts.pyscript6.0 KB
scripts/test_new_user_fleet.pyscript3.3 KB
scripts/test_no_hardcode_classification.pyscript75.1 KB
scripts/test_no_legacy_scoring.pyscript6.5 KB
scripts/test_override_store.pyscript2.3 KB
scripts/test_plan_says_why.pyscript44.9 KB
scripts/test_provider_inventory.pyscript83.2 KB
scripts/test_provider_names.pyscript126.0 KB
scripts/test_provider_pools.pyscript14.2 KB
scripts/test_public_data.pyscript93.5 KB
scripts/test_quota_exhaustion.pyscript5.6 KB
scripts/test_rate_limit_windows.pyscript6.3 KB
scripts/test_record_says_why.pyscript26.5 KB
scripts/test_reference_provenance.pyscript16.7 KB
scripts/test_refresh_entry.pyscript110.7 KB
scripts/test_released_names.pyscript4.1 KB
scripts/test_reset_priority.pyscript4.8 KB
scripts/test_roll_answers.pyscript44.7 KB
scripts/test_roll_notifications.pyscript10.4 KB
scripts/test_route_judge.pyscript99.8 KB
scripts/test_route_simulation.pyscript7.0 KB
scripts/test_routing_parity.pyscript32.3 KB
scripts/test_routing_review.pyscript25.1 KB
scripts/test_setup_discovery_parity.pyscript9.5 KB
scripts/test_stage_help.pyscript2.0 KB
scripts/test_state_upgrade.pyscript13.8 KB
scripts/test_turn_refusal.pyscript16.7 KB
scripts/test_usage_cache.pyscript4.9 KB
scripts/test_usage_collector.pyscript21.4 KB
scripts/test_usage_core_claude_accounts.pyscript1.8 KB
scripts/test_usage_core_grok_cli_billing.pyscript15.6 KB
scripts/test_usage_core_magpie.pyscript5.4 KB
scripts/test_usage_core_magpie_pool.pyscript10.8 KB
scripts/test_usage_core_safety.pyscript24.4 KB
scripts/test_user_scores.pyscript102.3 KB
scripts/test_venice_usage.pyscript1.3 KB
scripts/test_window_scope.pyscript5.5 KB
scripts/turn_refusal.pyscript10.7 KB
scripts/usage_cache.pyscript4.7 KB
scripts/usage_collector.pyscript7.4 KB
scripts/usage_core.pyscript142.0 KB
scripts/usage_magpie.pyscript10.6 KB
scripts/usage_reading.pyscript17.1 KB
scripts/user_scores.pyscript72.8 KB
scripts/venice_usage.pyscript2.6 KB
scripts/window_scope.pyscript3.2 KB
scripts/worker_context.pyscript8.9 KB
scripts/worker_sessions.pyscript10.9 KB

scripts/test_route_simulation.py

View on GitHub
"""The routing simulation feeds usage through the roll pipeline, so quota scarcity moves the distribution."""
from datetime import datetime, timedelta, timezone
import unittest

import route_simulation as sim
from router_test_support import isolated_router_state
from test_fleet_parity import shipped_template, snapshot


def setUpModule():
    isolated_router_state(unittest.addModuleCleanup, discovery=False, policy=False)


NOW = datetime(2026, 11, 4, 12, tzinfo=timezone.utc)


def window(usage, account, wid):
    return next(w for w in usage['accounts'][account]['windows'] if w['id'] == wid)


class UsageAwareSimulationTests(unittest.TestCase):
    @classmethod
    def setUpClass(cls):
        cls.accounts = sim.fresh_accounts(shipped_template(), snapshot())
        cls.tasks = sim.grid_tasks(cls.accounts)
        cls.policy = {'allowed_accounts': list(cls.accounts['accounts'])}
        cls._wins_cache = {}

    @classmethod
    def wins(cls, state):
        if state not in cls._wins_cache:
            usage = sim.snapshot(sim.synthetic_document(cls.accounts, NOW, sim.STATES[state]), cls.accounts, NOW)
            cls._wins_cache[state] = sim.run_state(cls.accounts, usage, NOW, cls.tasks, cls.policy)[1]
        return cls._wins_cache[state]

    @staticmethod
    def share(wins, *labels):
        return sum(wins[label] for label in labels) / sum(wins.values())

    def test_scarce_windows_reach_the_allocator_as_remaining_quota(self):
        usage = sim.snapshot(sim.synthetic_document(self.accounts, NOW, sim.STATES['claude scarce']), self.accounts, NOW)
        weekly = window(usage, 'claude', 'seven_day')
        self.assertAlmostEqual(weekly['remaining_pct_before_reset'], 100 - sim.SCARCE_USED)
        self.assertGreater(weekly['seconds_until_reset'], 0)
        self.assertAlmostEqual(window(usage, 'codex', 'usage')['remaining_pct_before_reset'], 100 - sim.AMPLE_USED)

    def test_claude_scarcity_moves_work_off_the_claude_account(self):
        # Rule: quota cost is non-decreasing in used share, so an account never wins more work with its windows nearly
        # used than with ample quota. Which model on the account wins is the router's result and is not asserted.
        ample, scarce = self.wins('ample'), self.wins('claude scarce')
        claude = [label for label in ample | scarce if label.endswith('@claude')]
        self.assertLessEqual(self.share(scarce, *claude), self.share(ample, *claude))
        if self.share(ample, *claude) > 0:
            self.assertLess(self.share(scarce, *claude), self.share(ample, *claude))

    def test_work_follows_the_account_with_quota_to_spare(self):
        ample, claude_scarce, codex_scarce, both = (self.wins(s) for s in (
            'ample', 'claude scarce', 'codex scarce', 'claude+codex scarce'))
        codex = [label for label in ample | claude_scarce | codex_scarce | both if label.endswith('@codex')]
        self.assertGreater(self.share(claude_scarce, *codex), self.share(ample, *codex))
        self.assertLess(self.share(codex_scarce, *codex), self.share(claude_scarce, *codex))
        self.assertEqual(self.share(both, *codex), 0)

    def test_stale_readings_are_not_priced_as_scarce_or_ample(self):
        usage = sim.snapshot(sim.synthetic_document(self.accounts, NOW, 'stale'), self.accounts, NOW)
        weekly = window(usage, 'claude', 'seven_day')
        self.assertIsNone(weekly['remaining_pct_before_reset'])

    def test_ledger_usage_replays_through_the_same_pipeline(self):
        at = NOW - timedelta(days=2)
        compact = {'claude': {'status': 'ok', 'fetched_at': at.isoformat(),
                              'windows': [{'id': 'seven_day', 'used_pct': 72.0,
                                           'resets_at': (at + timedelta(days=3)).isoformat()}]}}
        usage = sim.snapshot(sim.ledger_document(compact), self.accounts, at)
        weekly = window(usage, 'claude', 'seven_day')
        self.assertAlmostEqual(weekly['remaining_pct_before_reset'], 28.0)
        self.assertAlmostEqual(weekly['seconds_until_reset'], 3 * 86400, delta=1)


    def test_a_pooled_window_keeps_its_account_count_through_the_ledger(self):
        import quota_pools
        import decision_ledger
        at = NOW - timedelta(days=2)
        reading = {'id': 'seven_day', 'used_pct': 40.0, 'resets_at': (at + timedelta(days=3)).isoformat(), 'accounts': 3}
        digest = decision_ledger.usage_digest({'accounts': {'claude': {'status': 'ok', 'fetched_at': at.isoformat(),
                                                                   'windows': [reading]}}})
        self.assertEqual(digest['claude']['windows'][0]['accounts'], 3)
        old = {'claude': {'status': 'ok', 'fetched_at': at.isoformat(), 'windows': [dict(reading, accounts=None)]}}
        old['claude']['windows'][0].pop('accounts')
        for compact, pools in ((digest, None), (old, {'claude': {'seven_day': 3}})):
            usage = sim.snapshot(sim.ledger_document(compact, pools), self.accounts, at)
            self.assertEqual(quota_pools.pool_size(window(usage, 'claude', 'seven_day')), 3)
        usage = sim.snapshot(sim.ledger_document(old), self.accounts, at)    # old record, no live pool: one account
        self.assertEqual(quota_pools.pool_size(window(usage, 'claude', 'seven_day')), 1)

    def test_old_shape_ledger_rows_are_skipped_with_a_warning_count(self):
        import json
        from pathlib import Path
        import tempfile
        from router_test_support import profile
        current_profile = profile(local_only=True, expected_hours=0.5)
        missing_required = {k: v for k, v in current_profile.items() if k != 'primary_level'}
        pre_four_category = {
            **current_profile,
            'realtime_loop': True,
            'axis_demand': {'divergence': 1, 'global_rigor': 2, 'module_precision': 3, 'vision_tools': 1},
        }
        base_row = {
            'stage': 'plan', 'at': NOW.isoformat(), 'choice': 'sol_high',
            'kind': 'code_implementation', 'difficulty': 'hard', 'hours': 1.0,
            'usage': {'accounts': {}},
        }
        warnings = []
        with tempfile.TemporaryDirectory() as d:
            ledger_file = Path(d) / 'ledger.jsonl'
            rows = [
                {**base_row, 'decision_snapshot': {'task': {'objective': 'missing primary_level', 'expected_hours': 1.0, 'profile': missing_required}}},
                {**base_row, 'decision_snapshot': {'task': {'objective': 'pre four category', 'expected_hours': 1.0, 'profile': pre_four_category}}},
                {**base_row, 'decision_snapshot': {'task': {'objective': 'current row', 'expected_hours': 1.0, 'profile': current_profile}}},
            ]
            ledger_file.write_text('\n'.join(json.dumps(r) for r in rows) + '\n', encoding='utf-8')
            out = sim.replay(path=ledger_file, accounts=self.accounts, warnings=warnings)
        self.assertEqual(len(out), 1)
        self.assertFalse(out[0].get('unreplayable', False))
        self.assertIsNotNone(out[0]['choice'])
        self.assertTrue(any('skipped 2 older-shape ledger row(s)' in w for w in warnings), warnings)


if __name__ == '__main__':
    unittest.main()
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: 471kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall