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/usage_collector.py

View on GitHub
"""Collect provider usage once and publish it where the router reads it.

Reads every account with local credentials (narrowed only by an explicit `usage_providers` list in host policy; dispatch
exclusions in `allowed_accounts` do not suppress usage), writes the usage cache (~/.agent-compass/usage-cache.json, or under
ROUTER_STATE_DIR) and prints a receipt (also saved as usage-collector.json next to it). Needs neither the Usage Float
plugin nor the tray. `agentcompass usage --show` prints what routing reads from that cache without collecting.
"""
from pathlib import Path
import argparse
import datetime
import json
import os
import socket
import sys
import time

SCRIPTS = Path(__file__).resolve().parent
if str(SCRIPTS) not in sys.path:
    sys.path.insert(0, str(SCRIPTS))
import account_fleet
import provider_inventory
import host_policy
import usage_cache
import usage_core
import venice_usage

STATE = usage_cache.state_dir()


def discovered_subscriptions() -> list[str]:
    """Every account the core can read on this machine: Claude and Codex homes, Pi, metered USD accounts, Grok, agy."""
    usage = usage_core
    items: list[str] = []
    extra_pi = ('pi',) if usage.read_pi_codex_auth()[0] is not None and usage.pi_linked_codex_provider() is None else ()
    for pid in (*usage.discover_claude_homes().keys(), *usage.discover_codex_accounts().keys(), *extra_pi,
                *usage.discover_metered_usd_accounts().keys(), 'grok', 'antigravity'):
        if pid not in items:
            items.append(pid)
    return items


def _declared_quota_sources() -> dict[str, str]:
    sources = dict(account_fleet.configured_quota_sources())
    override = account_fleet.accounts_override_path()
    if override.is_file():
        try:
            doc = json.loads(override.read_text(encoding='utf-8-sig'))
            sources.update(provider_inventory.quota_sources(doc))
        except (OSError, ValueError):
            pass
    return sources


def _permitted_meters(policy, sources: dict[str, str], candidates: list[str]) -> list[str]:
    allowed = host_policy.usage_providers(policy, candidates + [n for n in sources if n not in candidates])
    return list(dict.fromkeys(sources.get(name, name) for name in allowed))


def resolve_targets(providers=None) -> list[str]:
    """Resolve permitted quota-meter provider IDs via load_accounts, quota_sources and host policy."""
    # Refresh opted-in admission before filtering newly discovered subscriptions.
    accounts = account_fleet.load_accounts()
    # A permitted account that draws on another's quota needs that meter even when the source's execution is disabled.
    sources = provider_inventory.quota_sources(accounts)
    permitted = _permitted_meters(host_policy.load_policy(), sources, discovered_subscriptions())
    if providers is None:
        return permitted
    allowed_set = set(permitted)
    requested = [
        sources.get(pid, pid)
        for pid in dict.fromkeys(usage_core.provider_fetch_id(item) for item in providers)
    ]
    return [pid for pid in dict.fromkeys(requested) if pid in allowed_set]


def filter_permitted_items(items) -> list[str]:
    """Filter display items only when host policy explicitly narrows usage_providers."""
    items = list(items)
    if not items:
        return []
    try:
        policy = host_policy.load_policy()
    except host_policy.HostPolicyError:
        return items
    if policy is None or 'usage_providers' not in policy:
        return items
    sources = _declared_quota_sources()
    candidates = list(dict.fromkeys(usage_core.provider_fetch_id(item) for item in items))
    permitted = set(_permitted_meters(policy, sources, candidates))
    return [
        item for item in items
        if sources.get(usage_core.provider_fetch_id(item), usage_core.provider_fetch_id(item)) in permitted
    ]


def read_usage(providers) -> list[dict]:
    """Read cached usage for policy-permitted providers without network calls or cache writes."""
    permitted = filter_permitted_items(providers)
    return usage_core.read_cached_usage(permitted) if permitted else []


def refresh_providers(providers, *, force: bool = True):
    """Collect usage for requested display items/providers using the collector's target resolution."""
    selected = usage_core.active_providers(resolve_targets(providers))
    return usage_core.fetch_all(selected, force=force) if selected else []


def collect(*, force: bool = False):
    usage = usage_core
    venice_usage.refresh(STATE)
    subscriptions = resolve_targets()
    selected = usage.active_providers(subscriptions)
    observations = usage.fetch_all(selected, force=force)
    try:
        import provider_retry
        # Holds a worker the bridge stopped for a stuck provider retry, so the tray shows it before the next roll.
        provider_retry.ingest()
    except Exception as error:  # noqa: BLE001 - never costs the usage reading
        with (STATE / 'usage-collector.log').open('a', encoding='utf-8') as stream:
            stream.write(f'{datetime.datetime.now().isoformat()} provider_retry {type(error).__name__}\n')
    result = {'hostname': socket.gethostname(), 'collection_mode': 'direct',
              'observed_at': datetime.datetime.now(datetime.timezone.utc).isoformat(),
              'cache_path': str(usage.CACHE_PATH), 'excluded': [],
              'providers': {p.provider_id: {'available': p.available, 'stale': p.stale, 'fetched_at': p.fetched_at,
                                         'window_count': len(p.windows)} for p in observations},
              'not_detected': [p for p in subscriptions if p not in selected],
              'requested_providers': subscriptions}
    STATE.mkdir(parents=True, exist_ok=True)
    target = STATE / 'usage-collector.json'
    temporary = target.with_suffix('.tmp')
    temporary.write_text(json.dumps(result, indent=2)+'\n', encoding='utf-8')
    temporary.replace(target)
    return result


def main(argv=None):
    parser = argparse.ArgumentParser(prog='agentcompass usage', description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
    parser.add_argument('--once', action='store_true', help='Collect one time and exit (what `agentcompass usage` always does); without it the tray helper repeats every 5 minutes.')
    parser.add_argument('--force', action='store_true', help='Skip poll/retry throttling (Claude 429 rate-limit backoff still applies).')
    args = parser.parse_args(argv)
    if not args.once and os.name == 'nt':
        import ctypes
        kernel = ctypes.WinDLL('kernel32', use_last_error=True)
        kernel.CreateMutexW(None, False, 'Local\\AgentCompassUsageCollector')
        if ctypes.get_last_error() == 183:
            return 0
    first_pass = True
    while True:
        try:
            result = collect(force=bool(args.force and first_pass))
            first_pass = False
            if sys.stdout is not None:
                print(json.dumps(result), flush=True)
        except Exception as error:
            STATE.mkdir(parents=True, exist_ok=True)
            # Exception text can include remote data; record its class, not its contents.
            with (STATE / 'usage-collector.log').open('a', encoding='utf-8') as stream:
                detail = str(error) if isinstance(error, host_policy.HostPolicyError) else type(error).__name__
                stream.write(f'{datetime.datetime.now().isoformat()} {detail}\n')
            if args.once:
                return 1
        if args.once:
            return 0
        time.sleep(300)


if __name__ == '__main__':
    raise SystemExit(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