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_fast_modes.py

View on GitHub
"""Fast contracts across model, harness, billing and launch surfaces; no live calls."""
import copy
import json
import unittest
from types import SimpleNamespace
from unittest.mock import patch
from datetime import datetime, timezone

import allocator
import account_fleet
import axis_scores
import candidate_ranking
import dispatch_registry as registry
import fast_modes
import roll
import route_judge
import usage_reading
from router_test_support import isolated_router_state, usage_windows


def setUpModule():
    isolated_router_state(unittest.addModuleCleanup)


class FastModesTests(unittest.TestCase):
    def test_only_an_effective_fast_capable_true_enables_fast(self):
        now = datetime.now(timezone.utc)
        accounts = account_fleet.load_accounts(account_fleet.reference_fleet_path())
        usage = usage_windows(now, {'codex': [('five_hour', 95, 3), ('seven_day', 95, 100)],
                                    'claude': [('five_hour', 95, 3), ('seven_day', 95, 100)]})
        task = dict(work_kind='code_audit', difficulty='routine', expected_hours=0.01,
                    needs={'local_only': True, 'fast': True})
        for provider, model, bid in [('codex', 'gpt-6.1-sol', 'sol_high'),
                                     ('claude', 'claude-opus-5-5', 'opus55_high')]:
            for policy in (False, True, None):
                with self.subTest(provider=provider, fast_capable=policy):
                    info = accounts['models'][model]
                    if policy is None:
                        info.pop('fast_capable', None)
                    else:
                        info['fast_capable'] = policy
                    for forced in (False, True):
                        ranking = allocator.plan(task, usage, now, accounts=accounts, route={'force_fast': forced})['ranking']
                        plain = candidate_ranking.candidate_for_bundle(ranking, bid, False)
                        self.assertFalse(plain['bundle'].get('fast') if plain else False)
                        if forced:
                            # Only Claude Opus has cited fast-mode pricing and speed; Codex models have none, so forcing
                            # fast on them is a data error, never a guessed variant.
                            fast = candidate_ranking.candidate_for_bundle(ranking, bid, True)
                            self.assertEqual(bool(fast and fast['bundle'].get('fast')), provider == 'claude' and policy is True)
                    bundle = dict(account_fleet.bundles(accounts)[bid], fast=True)
                    args = SimpleNamespace(basis='Diagnostic fixture', provider=provider, account=provider,
                        model=model, effort='high', input=None, usage_cache=None, accounts=None,
                        constraint='user_override', specialty=None, fast=True)
                    with patch.object(account_fleet, 'load_accounts', return_value=accounts), \
                            patch.object(usage_reading, 'usage_snapshot', return_value=usage):
                        if policy is not True:
                            with self.assertRaisesRegex(ValueError, 'has no verified fast mode on .*; run it without --fast'):
                                route_judge.record_constraint(args)
                            with self.assertRaisesRegex(ValueError, 'has no verified fast mode on .*; run it without --fast'):
                                registry.resolve_bundle(bundle, accounts)
                            with patch.object(roll, 'provider_definition', return_value=(provider, {})), \
                                    patch.object(roll.subprocess, 'Popen') as spawn:
                                with self.assertRaisesRegex(ValueError, 'has no verified fast mode on .*; run it without --fast'):
                                    roll.cli(SimpleNamespace(wait=0), {}, bundle, 'fixture')
                                spawn.assert_not_called()
                        else:
                            self.assertTrue(route_judge.record_constraint(args)['selected_bundle']['fast'])
                            self.assertTrue(registry.resolve_bundle(bundle, accounts)['fast'])
                    self.assertIsNotNone(registry.resolve_bundle(dict(bundle, fast=False), accounts))

    def test_fast_needs_a_declared_row_on_the_harness_of_its_api_family(self):
        # Rule (fast-modes.md): fast runs only where the row declares fast_capable: true, on its api_family's harness.
        for harness in fast_modes.HARNESSES:
            fast_modes.validate(harness, 'model-a', {'fast_capable': True, 'api_family': harness})
        other = {'codex': 'claude', 'claude': 'codex'}
        for harness, info in [('pi', {'fast_capable': True, 'api_family': 'codex'}),
                              ('antigravity-resilient', {'fast_capable': True, 'api_family': 'claude'}),
                              *((h, {'fast_capable': True, 'api_family': other[h]}) for h in fast_modes.HARNESSES),
                              *((h, {'api_family': h}) for h in fast_modes.HARNESSES),
                              *((h, {'fast_capable': False, 'api_family': h}) for h in fast_modes.HARNESSES),
                              ('claude', {})]:
            with self.subTest(harness=harness, info=info), self.assertRaises(ValueError):
                fast_modes.validate(harness, 'model-a', info)
            self.assertFalse(fast_modes.supported(harness, 'model-a', info))

    def test_a_missing_catalog_row_is_a_named_error(self):
        for check in (fast_modes.supported, fast_modes.validate):
            with self.subTest(check=check.__name__), self.assertRaisesRegex(ValueError, 'needs its catalog row'):
                check('codex', 'model-a', None)

    def test_fast_and_normal_requests_preserve_model_effort_and_no_pi_feature(self):
        for provider, model in [('codex', 'gpt-6-astra'), ('claude', 'claude-opus-5-5')]:
            for fast in (False, True):
                b = dict(provider=provider, model=model, effort='medium', fast=fast)
                before = copy.deepcopy(b)
                request = registry.launch_request(b, dict(title='fixture', initialPrompt='fixture'))
                self.assertEqual(b, before)
                self.assertEqual(request['provider'], provider + '/' + model)
                self.assertEqual(request['settings']['thinkingOptionId'], 'medium')
                expected = {'service_tier': 'priority' if fast else 'default'} if provider == 'codex' else {'fast_mode': fast}
                self.assertEqual(request['settings']['features'], expected)
        pi = registry.launch_request(dict(provider='pi', model='gpt-6-astra', effort='high'),
                                     dict(title='pi', initialPrompt='fixture'))
        self.assertNotIn('features', pi['settings'])
        self.assertNotIn('modeId', pi['settings'])
        with self.assertRaises(ValueError):
            registry.launch_request(dict(provider='pi', model='gpt-6-astra', fast=True),
                                    dict(title='pi', initialPrompt='fixture'))

    def test_cli_session_settings_explicitly_enable_and_disable_without_model_switch(self):
        for fast in (False, True):
            args = roll.CLI_RUNS['claude'][1]('claude-opus-5-5', 'medium', 'C:/fixture', fast)
            self.assertEqual(args[args.index('--model') + 1], 'claude-opus-5-5')
            self.assertEqual(args[args.index('--effort') + 1], 'medium')
            self.assertEqual(json.loads(args[args.index('--settings') + 1]), {'fastMode': fast})
            args = roll.CLI_RUNS['codex'][1]('gpt-6-astra', 'medium', 'C:/fixture', fast)
            self.assertIn('service_tier="priority"' if fast else 'service_tier="default"', args)
            self.assertIn('features.fast_mode=' + str(fast).lower(), args)

    def test_claude_fast_billing_follows_the_account(self):
        self.assertEqual(fast_modes.claude_billing({'billing': 'subscription'}), 'usage_credits')
        self.assertEqual(fast_modes.claude_billing({'billing': 'metered'}), 'api')
        self.assertEqual(fast_modes.claude_billing({}), 'unknown_paid')

    def test_claude_fast_is_its_own_candidate_priced_at_the_cited_multiples(self):
        now = datetime.now(timezone.utc)
        accounts = account_fleet.load_accounts(account_fleet.reference_fleet_path())
        usage = usage_windows(now, {'claude': [('five_hour', 95, 3), ('seven_day', 95, 1)]})
        task = dict(work_kind='code_audit', difficulty='routine', expected_hours=0.01,
                    needs={'local_only': True, 'fast': True})
        shipped = axis_scores.load_five_axis()['models']['claude-opus-5-5']['fast_mode']
        def rows(t, load=accounts):
            route = {k: t.pop(k) for k in ('force_fast',) if k in t}      # a route field, never a task field
            return allocator.plan(t, usage, now, accounts=load, route=route)['ranking']
        plain = candidate_ranking.candidate_for_bundle(rows(task), 'opus55_high', False)
        self.assertFalse(plain['bundle'].get('fast'))
        paid = candidate_ranking.candidate_for_bundle(rows(dict(task, force_fast=True)), 'opus55_high', True)
        self.assertEqual((paid['id'], paid['bundle']['fast']), ('opus55_high+fast', True))
        self.assertEqual(paid['base_id'], 'opus55_high')
        self.assertGreater(paid['expected_usd'], 0)
        self.assertTrue(any(f"{shipped['price_multiplier']:g}x burn" in n for n in paid['notes']))
        self.assertIsNone(candidate_ranking.candidate_for_bundle(rows(dict(task, force_fast=True, disable_fast=True)), 'opus55_high', True))
        accounts['accounts']['claude']['bundles']['opus55_high']['disabled'] = True
        self.assertTrue(candidate_ranking.candidate_for_bundle(rows(dict(task, force_fast=True)), 'opus55_high', False)['excluded'])
        accounts['accounts']['claude']['bundles']['opus55_high']['disabled'] = False
        usage = usage_windows(now, {'claude': [('five_hour', 0, 3), ('seven_day', 0, 100)]})
        self.assertTrue(candidate_ranking.candidate_for_bundle(rows(dict(task, force_fast=True)), 'opus55_high', False)['excluded'])


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