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_usage_core_magpie_pool.py

View on GitHub
"""A Magpie pool shows its largest plan: N such accounts read as one window set worth N accounts (×N)."""
import copy
import json
import unittest
from datetime import datetime, timedelta, timezone
from pathlib import Path
from tempfile import TemporaryDirectory
from unittest.mock import patch

import usage_magpie as magpie_usage
import usage_core as usage


class MagpiePoolTests(unittest.TestCase):
    def setUp(self):
        self.now = datetime.now(timezone.utc)
        self.source = magpie_usage.Source('https://example.com', 'test-key', '*')
        self.a = self.account('a', 100, 50, 1)
        self.b = self.account('b', 0, 0, 3)

    def account(self, name, short, week, reset_hours):
        return {'provider': 'claude', 'kind': 'subscription', 'user': name,
                'plan': 'pro', 'readAt': self.now.isoformat(), 'windows': [
                    {'name': '5 hours', 'used': short,
                     'resetsAt': (self.now + timedelta(hours=reset_hours)).isoformat()},
                    {'name': '7 days', 'used': week,
                     'resetsAt': (self.now + timedelta(days=reset_hours)).isoformat()}]}

    def parse(self, *rows):
        return magpie_usage.parse_quota({'data': list(rows)}, self.source)

    def test_same_plan_accounts_add_up(self):
        quota, windows = self.parse(self.a, self.b)
        self.assertEqual([w['used_pct'] for w in windows], [25, 50])  # mean; the window holds two accounts' worth
        self.assertEqual([w['accounts'] for w in windows], [2, 2])
        self.assertEqual([w['label'] for w in windows], ['7d×2', '5h×2'])
        self.assertEqual(windows[1]['resets_at'], self.b['windows'][0]['resetsAt'])  # the last account to refill
        self.assertEqual(quota['plan'], 'pro ×2')
        details = quota['usage_details']
        self.assertEqual((details['account_count'], details['plan_count'], details['aggregation']), (2, 2, 'plan_sum'))
        self.assertNotIn('test-key', json.dumps(quota))
        self.assertNotIn('user', details['members'][0])
        shown = usage.UsageWindow(**windows[0])
        self.assertEqual(usage._provider_from_dict(usage._provider_to_dict(usage.ProviderUsage(
            provider_id='claude-2', display_name='claude-2', windows=[shown]))).windows[0].accounts, 2)

    def fable_week(self, row, used):
        row['windows'].append({'name': '7 days · Fable', 'used': used,
                               'resetsAt': (self.now + timedelta(days=2)).isoformat()})
        return row

    def test_model_scoped_week_is_pooled_as_the_fable_row(self):
        quota, windows = self.parse(self.fable_week(self.a, 40), self.fable_week(self.b, 10))
        fable = next(w for w in windows if w['id'] == 'weekly_fable')
        self.assertEqual((fable['label'], fable['used_pct'], fable['accounts'], fable['models']),
                         ('fable 7d×2', 25, 2, ['Fable']))
        self.assertEqual([w['id'] for w in windows], ['seven_day', 'five_hour', 'weekly_fable'])
        shown = usage.UsageWindow(**fable)
        self.assertEqual(shown.models, ['Fable'])
        single, alone = magpie_usage.parse_quota({'data': [self.a]}, magpie_usage.Source('https://example.com', 'test-key', 'a'))
        self.assertIn(('weekly_fable', 'fable 7d', 40.0), [(w['id'], w['label'], w['used_pct']) for w in alone])

    def test_scoped_week_one_account_lacks_is_left_out_not_an_error(self):
        _, windows = self.parse(self.fable_week(self.a, 40), self.b)
        self.assertEqual([w['id'] for w in windows], ['seven_day', 'five_hour'])

    def test_largest_plan_wins_over_smaller_plans(self):
        self.a['plan'] = 'max'
        quota, windows = self.parse(self.a, self.b, self.account('c', 0, 0, 2))
        self.assertEqual([w['used_pct'] for w in windows], [50, 100])
        self.assertEqual([w['label'] for w in windows], ['7d', '5h'])
        self.assertEqual([w['accounts'] for w in windows], [1, 1])
        self.assertEqual(quota['plan'], 'max')
        self.assertEqual(quota['usage_details']['account_count'], 3)
        self.assertGreater(magpie_usage.plan_rank('Max 20x'), magpie_usage.plan_rank('max'))
        self.assertGreater(magpie_usage.plan_rank('pro'), magpie_usage.plan_rank('plus'))

    def test_without_a_configured_account_every_subscription_is_read(self):
        source = magpie_usage.Source('https://example.com', 'test-key', '')
        quota, windows = magpie_usage.parse_quota({'data': [self.a, self.b]}, source)
        self.assertEqual(quota['plan'], 'pro ×2')
        single, _ = magpie_usage.parse_quota({'data': [self.a]}, source)
        self.assertNotIn('usage_details', single)

    def test_only_selected_provider_subscriptions(self):
        foreign = dict(self.b, provider='codex')
        wallet = dict(self.b, kind='api')
        _, windows = self.parse(self.a, foreign, wallet)
        self.assertEqual([w['used_pct'] for w in windows], [50, 100])

    def test_unread_account_is_skipped_and_bad_data_is_rejected(self):
        for changes in ({'error': 'offline'}, {'readAt': None}):
            with self.subTest(changes=changes):
                quota, windows = self.parse(self.a, dict(self.b, **changes))
                self.assertEqual([w['used_pct'] for w in windows], [50, 100])
                self.assertEqual(quota['plan'], 'pro')
        with self.assertRaises(ValueError):
            self.parse(dict(self.a, error='offline'), dict(self.b, error='offline'))
        for changes in ({'readAt': 'bad'}, {'windows': []}, {'user': None}):
            with self.subTest(changes=changes), self.assertRaises(ValueError):
                self.parse(self.a, dict(self.b, **changes))

    def test_duplicates_and_invalid_percentages_are_rejected(self):
        with self.assertRaises(ValueError):
            self.parse(self.a, self.a)
        for number in (-1, 101, True, float('nan')):
            bad = copy.deepcopy(self.b)
            bad['windows'][0]['used'] = number
            with self.subTest(number=number), self.assertRaises(ValueError):
                self.parse(self.a, bad)

    def test_order_does_not_change_pool_identity(self):
        left, _ = self.parse(self.a, self.b)
        right, _ = self.parse(self.b, self.a)
        self.assertEqual(left['usage_details']['pool_key'], right['usage_details']['pool_key'])

    def test_changed_membership_replaces_cache_even_with_older_vendor_time(self):
        with TemporaryDirectory() as folder:
            home = Path(folder)
            (home / 'settings.json').write_text(json.dumps({'env': {
                'ANTHROPIC_BASE_URL': self.source.url,
                'ANTHROPIC_AUTH_TOKEN': self.source.token}}), encoding='utf-8')
            (home / 'usage-float.json').write_text(json.dumps({
                'source': 'magpie', 'account': '*'}), encoding='utf-8')
            self.b['readAt'] = (self.now - timedelta(hours=1)).isoformat()
            with patch.object(usage, 'CLAUDE_HOME_2', home), \
                    patch.object(usage, 'CACHE_PATH', home / 'cache.json'), \
                    patch.object(usage, 'http_json') as request:
                request.return_value = (200, {'data': [self.a, self.b]})
                first = usage.fetch_claude_usage(provider_id='claude-2')
                self.assertTrue(first.stale)  # the older member reading (b, an hour ago) dates the pool
                self.assertEqual(first.fetched_at, self.b['readAt'])
                request.return_value = (200, {'data': [self.b]})
                usage.fetch_claude_usage(provider_id='claude-2')
                cached = usage.cache_get_provider('claude-2')
                self.assertFalse(cached.usage_details)  # one account left: a plain reading replaces the pool
                self.assertEqual([w.used_pct for w in cached.windows], [0, 0])
                self.assertEqual(cached.fetched_at, self.b['readAt'])


    def test_a_new_reading_rule_replaces_the_cached_pool_at_the_same_vendor_time(self):
        with TemporaryDirectory() as folder:
            home = Path(folder)
            (home / 'settings.json').write_text(json.dumps({'env': {
                'ANTHROPIC_BASE_URL': self.source.url,
                'ANTHROPIC_AUTH_TOKEN': self.source.token}}), encoding='utf-8')
            (home / 'usage-float.json').write_text(json.dumps({'source': 'magpie'}), encoding='utf-8')
            self.a['readAt'] = self.b['readAt'] = (self.now - timedelta(hours=6)).isoformat()  # stale, same time
            with patch.object(usage, 'CLAUDE_HOME_2', home),                     patch.object(usage, 'CACHE_PATH', home / 'cache.json'),                     patch.object(usage, 'http_json', return_value=(200, {'data': [self.a, self.b]})):
                usage.fetch_claude_usage(provider_id='claude-2')
                def as_mean(cache):
                    row = cache['providers']['claude-2']
                    row['usage_details']['aggregation'] = 'account_mean'
                    row['windows'][0]['label'] = '7d×2均'
                usage.update_usage_cache(as_mean)
                usage.fetch_claude_usage(provider_id='claude-2')
                cached = usage.cache_get_provider('claude-2')
                self.assertEqual(cached.usage_details['aggregation'], 'plan_sum')
                self.assertEqual(cached.windows[0].label, '7d×2')

    def test_old_readings_are_read_again_by_magpie(self):
        self.b['readAt'] = (self.now - timedelta(hours=5)).isoformat()
        now = self.now.timestamp()
        payload = {'data': [self.a, self.b]}
        self.assertEqual(magpie_usage.reread_targets(payload, self.source, now, 600), [('claude', 'b')])
        self.assertEqual(magpie_usage.reread_targets(payload, self.source, now, 600, force=True),
                         [('claude', 'a'), ('claude', 'b')])
        self.assertEqual(magpie_usage.reread_targets({'error': 'x'}, self.source, now, 600), [])
        quota, _ = self.parse(self.a, self.b)
        self.assertEqual([m['label'] for m in quota['usage_details']['members']], ['a***', 'b***'])
        self.assertTrue(all(m['counted'] for m in quota['usage_details']['members']))

    def test_auto_discovered_gateway_passes_force_to_magpie_refresh(self):
        with TemporaryDirectory() as folder:
            home = Path(folder)
            (home / 'settings.json').write_text(json.dumps({'env': {
                'ANTHROPIC_BASE_URL': self.source.url,
                'ANTHROPIC_AUTH_TOKEN': self.source.token}}), encoding='utf-8')
            calls = []
            def fake_http(url, *, method='GET', **kwargs):
                calls.append((method, url))
                return 200, {'data': [self.a, self.b]}
            with patch.object(usage, 'CLAUDE_HOME_2', home), \
                    patch.object(usage, 'CACHE_PATH', home / 'cache.json'), \
                    patch.object(usage, 'http_json', side_effect=fake_http):
                usage.fetch_claude_usage(provider_id='claude-2', force=True)
            post_urls = [url for method, url in calls if method == 'POST']
            self.assertEqual(len(post_urls), 2)

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