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_launch_values.py

View on GitHub
"""Rule (router-internals §5, Launch values): no launch passes a value through cmd.exe. A Windows batch launcher (an npm
`.cmd` shim) is started as the program its launch line runs (launch_values.program), so a value holding cmd.exe syntax
(`&`, `|`, `^`, `%VAR%`, `>`) reaches the program as one argument and runs nothing; a launcher that cannot be read that
way refuses the launch, stated. The fake shims and the recording program live in a temporary directory."""
import argparse
import json
import os
import sys
import tempfile
import unittest
from pathlib import Path
from unittest.mock import patch

import host_herdr
import launch_values
import public_data
import roll
import scorer_client
import subscription_cli

RECORDER = """import json, os, sys
from pathlib import Path
with open(Path(__file__).with_name('argv.jsonl'), 'a', encoding='utf-8') as out:
    out.write(json.dumps({'argv': sys.argv[1:], 'shim_env': os.environ.get('SHIM_SET')}) + '\\n')
print('{}')
"""
# The shape npm's cmd-shim writes (the program in `_prog`, the script beside `%dp0%`), with a variable of its own.
NPM_SHIM = """@ECHO off\r
GOTO start\r
:find_dp0\r
SET dp0=%~dp0\r
EXIT /b\r
:start\r
SETLOCAL\r
CALL :find_dp0\r
IF EXIST "%dp0%\\node.exe" (\r
  SET "_prog=%dp0%\\node.exe"\r
) ELSE (\r
  SET "_prog={python}"\r
  SET PATHEXT=%PATHEXT:;.JS;=;%\r
)\r
\r
endLocal & goto #_undefined_# 2>NUL || title %COMSPEC% & "%_prog%"  "%dp0%\\record.py" %*\r
"""
DESKTOP_SHIM = """@echo off\r
setlocal\r
set "SCRIPT_DIR=%~dp0"\r
set "SHIM_SET=from-the-launcher"\r
"{python}" "%SCRIPT_DIR%record.py" node-script %*\r
exit /b %errorlevel%\r
"""
# The reviewer's probe shim: it hands %* to cmd.exe itself, so it cannot be read as a program and its arguments.
UNREADABLE_SHIM = '@echo off\r\necho %* > "%~dp0args-%~n0.txt"\r\n'


class BatchLauncherTests(unittest.TestCase):
    def setUp(self):
        self.folder = Path(tempfile.mkdtemp(prefix='launch-values-'))
        self.addCleanup(lambda: __import__('shutil').rmtree(self.folder, ignore_errors=True))
        (self.folder / 'record.py').write_text(RECORDER, encoding='utf-8')
        self.marker = self.folder / 'INJECTED.txt'
        self.hostile = [f'm&echo.pwned>{self.marker}', f'm|echo.pwned>{self.marker}', f'm^&echo.pwned>{self.marker}',
                        'm%PWN%', f'm>{self.marker}']
        env = patch.dict(os.environ, {'PATH': str(self.folder) + os.pathsep + os.environ.get('PATH', ''),
                                      'PWN': 'EXPANDED'})
        env.start()
        self.addCleanup(env.stop)

    def shim(self, name, text):
        path = self.folder / f'{name}.CMD'
        path.write_bytes(text.replace('{python}', sys.executable).encode('ascii'))
        return path

    def recorded(self):
        path = self.folder / 'argv.jsonl'
        return [json.loads(line) for line in path.read_text(encoding='utf-8').splitlines()] if path.exists() else []

    def assert_nothing_injected(self):
        self.assertFalse(self.marker.exists(), 'a value ran as a command')
        self.assertFalse(any(p.name.startswith('pwned') for p in self.folder.iterdir()))

    def test_a_shim_is_read_as_its_program_and_script(self):
        shim = self.shim('pi', NPM_SHIM)
        argv, env = launch_values.program(shim)
        self.assertEqual([os.path.normcase(a) for a in argv],
                         [os.path.normcase(sys.executable), os.path.normcase(str(self.folder / 'record.py'))])
        self.assertEqual(env, {})                    # dp0 and _prog are consumed; PATHEXT's substring edit is not a value
        argv, env = launch_values.program(self.shim('paseo', DESKTOP_SHIM))
        self.assertEqual(argv[2], 'node-script')
        self.assertEqual(env, {'SHIM_SET': 'from-the-launcher'})
        self.assertEqual(launch_values.program(self.folder / 'tool.exe'), ([str(self.folder / 'tool.exe')], {}))

    def test_the_cli_worker_passes_every_value_as_one_argument(self):
        """roll.cli for the npm-shim CLIs (pi, opencode): the model and the prompt reach the program unchanged."""
        for family in ('pi', 'opencode'):
            self.shim(family, NPM_SHIM)
        started = []
        real = roll.subprocess.Popen

        def popen(*args, **kwargs):
            started.append(real(*args, **kwargs))
            return started[-1]
        out = {'parent_id': 'p', 'parent_host': 'paseo', 'parent_address': 'p'}
        with patch.object(roll, 'provider_definition', lambda provider, bundle=None: (provider, {})), \
                patch.object(roll.host_placement, 'place', lambda *a, **k: {'cwd': str(self.folder)}), \
                patch.object(roll, 'CLI_RUNS_DIR', self.folder / 'runs'), \
                patch.object(roll.subprocess, 'Popen', popen):
            for family in ('pi', 'opencode'):
                for value in self.hostile:
                    result, code = roll.cli(argparse.Namespace(workspace=None), out,
                                            {'provider': family, 'model': value}, f'task {value}')
                    self.assertEqual((result['launched'], code), (True, 0), result)
                    started[-1].wait(30)
        seen = [line['argv'] for line in self.recorded()]
        self.assertEqual(len(seen), 2 * len(self.hostile))
        for value in self.hostile:
            self.assertTrue(any(any(arg.endswith(value) for arg in argv) for argv in seen), value)
        self.assertNotIn('EXPANDED', json.dumps(seen))
        self.assert_nothing_injected()

    def test_the_scorer_and_cli_worker_command_passes_values_unchanged(self):
        """subscription_cli.cli_prefix (the scorer's command and roll's CLI worker command) on an npm shim."""
        self.shim('claude', NPM_SHIM)
        prefix = subscription_cli.cli_prefix('claude')
        for value in self.hostile:
            code, _out, _err = subscription_cli.run_process([*prefix, '--model', value], str(self.folder), prompt='x',
                                                            timeout=30)
            self.assertEqual(code, 0)
        self.assertEqual([line['argv'][-1] for line in self.recorded()], self.hostile)
        self.assert_nothing_injected()

    def test_herdr_core_runs_as_its_program(self):
        self.shim('hc', NPM_SHIM)
        for value in self.hostile:
            host_herdr.hc('terminal', 'spawn', '--command', value)
        self.assertEqual([line['argv'][-1] for line in self.recorded()], self.hostile)
        self.assert_nothing_injected()

    def test_a_launcher_that_cannot_be_read_refuses_the_launch_and_runs_nothing(self):
        for family in ('pi', 'opencode', 'claude'):
            self.shim(family, UNREADABLE_SHIM)
        with self.assertRaisesRegex(launch_values.UnreadableLauncher, 'goes on after %\\*'):
            subscription_cli.cli_prefix('claude')
        out = {'parent_id': 'p', 'parent_host': 'paseo', 'parent_address': 'p'}
        before = public_data._EFFECTS[0]
        with patch.object(roll, 'provider_definition', lambda provider, bundle=None: (provider, {})), \
                patch.object(roll.host_placement, 'place', lambda *a, **k: {'cwd': str(self.folder)}), \
                patch.object(roll, 'CLI_RUNS_DIR', self.folder / 'runs'), \
                patch.object(roll.subprocess, 'Popen', side_effect=AssertionError('started')):
            result, code = roll.cli(argparse.Namespace(workspace=None), out, {'provider': 'pi', 'model': self.hostile[0]},
                                    'task')
        self.assertEqual((result['launched'], code), (False, 1))
        self.assertIn('cannot be started without cmd.exe', result['next'])
        self.assertEqual(public_data._EFFECTS[0], before)                     # refused before the launch's effect
        with patch.dict(scorer_client.SCORER, {'provider': 'claude'}), \
                self.assertRaisesRegex(scorer_client.ScorerUnavailable, 'cannot be started without cmd.exe'):
            scorer_client.scorer_prefix()
        self.assertEqual(self.recorded(), [])
        self.assertFalse(list(self.folder.glob('args-*.txt')))
        self.assert_nothing_injected()


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