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/host_policy.py

View on GitHub
"""Local dispatch availability. No profile preserves the shared routing defaults."""
import argparse
import json
import os
from pathlib import Path
from datetime import datetime, timezone

import account_state
import accounts_override
import override_store
import state_upgrade


class HostPolicyError(ValueError):
    """Safe, local configuration diagnostic (never includes profile contents)."""


def policy_path():
    configured = os.environ.get('ROUTER_HOST_POLICY')
    if not configured and os.name == 'nt':
        import winreg
        try:
            with winreg.OpenKey(winreg.HKEY_CURRENT_USER, 'Environment') as key:
                configured = winreg.QueryValueEx(key, 'ROUTER_HOST_POLICY')[0]
        except OSError:
            pass
    if configured and not isinstance(configured, str):
        raise HostPolicyError('ROUTER_HOST_POLICY must be a path string.')
    return (Path(configured).expanduser(), True) if configured else (Path.home() / '.agent-compass/host-policy.json', False)


def load_policy():
    path, explicit = policy_path()
    try:
        raw = path.read_text(encoding='utf-8-sig')
    except FileNotFoundError:
        if not explicit:
            return None
        raise HostPolicyError(state_upgrade.format_issue(
            path, 'host-policy configuration missing',
            'create it as a JSON object with "allowed_accounts" (a list of account names), or unset ROUTER_HOST_POLICY',
        )) from None
    except UnicodeError:
        raise HostPolicyError(state_upgrade.format_issue(
            path, 'host-policy configuration must be UTF-8', state_upgrade.host_policy_fix(path),
        )) from None
    except OSError as exc:
        raise HostPolicyError(state_upgrade.format_issue(
            path, f'host-policy configuration unreadable ({exc})', state_upgrade.host_policy_fix(path),
        )) from None
    try:
        data = json.loads(raw)
    except (ValueError, UnicodeError):
        raise HostPolicyError(state_upgrade.format_issue(
            path, 'host-policy configuration invalid JSON', state_upgrade.host_policy_fix(path),
        )) from None
    try:
        return state_upgrade.validate_host_policy_doc(data, path)
    except ValueError as exc:
        raise HostPolicyError(str(exc)) from None


def sync_discovered(accounts):
    """Admit only unseen, ready registered accounts; a known omission is an intentional deny."""
    policy = load_policy()
    if policy is None:
        return {'mode': 'default', 'added': []}
    if 'known_accounts' not in policy:
        return {'mode': 'static', 'added': []}
    discovery = accounts.get('_discovery') or {}
    rows = discovery.get('accounts') or {}
    specs = accounts.get('accounts') or {}
    now = datetime.now(timezone.utc)
    ready = []
    for name, row in rows.items():
        spec = specs.get(name) or {}
        # Only subscription accounts enroll automatically; metered/unknown billing needs an explicit allow.
        if not account_state.dispatchable(row) or spec.get('verified') is not True or accounts_override.manual_only_billing(name, accounts):
            continue
        if not any(not b.get('disabled') and not b.get('discovery_unavailable')
                   for b in (spec.get('bundles') or {}).values()):
            continue
        expires = spec.get('expires_at')
        if expires:
            try:
                moment = datetime.fromisoformat(expires.replace('Z', '+00:00'))
                if (moment if moment.tzinfo else moment.replace(tzinfo=timezone.utc)) <= now:
                    continue
            except (AttributeError, TypeError, ValueError):
                continue
        ready.append(name)
    seen_fast = set(policy['known_accounts']) | set(policy['allowed_accounts'])
    if not any(name not in seen_fast for name in ready):
        return {'mode': 'enabled', 'added': []}
    path = policy_path()[0]
    with override_store.locked(path):
        policy = load_policy()
        if policy is None or 'known_accounts' not in policy:
            return {'mode': 'default' if policy is None else 'static', 'added': []}
        seen = set(policy['known_accounts']) | set(policy['allowed_accounts'])
        added = [name for name in ready if name not in seen]
        if added:
            policy['allowed_accounts'].extend(added)
            policy['known_accounts'] = list(dict.fromkeys([*policy['known_accounts'], *policy['allowed_accounts']]))
            override_store.write(path, policy)
        return {'mode': 'enabled', 'added': added}


def account_allowed(policy, account):
    """Whether the account takes part in automatic routing on this host (no policy file: every account does).

    An account outside `allowed_accounts` is never chosen by the router: not by a plan, a fallback, an automatic resume
    of an idle worker, nor as the scorer. It is not banned: a route the user names in the request still
    dispatches on it (`route_judge.record_constraint`, constraint `user_override`), and a turn to an existing session on
    it is not a routing choice. The model-management checkbox is the same kind of switch for a model
    (`model_unchecked`)."""
    return policy is None or account in policy['allowed_accounts']


def outside_routing(account):
    """The one wording of an account outside `allowed_accounts`; callers add why it is or is not launched."""
    return f'account {account} is out of automatic routing on this host (not in allowed_accounts of host-policy.json)'


def unchecked_routing(account, model):
    """The one wording of a model unchecked in model management; callers add why it is or is not launched."""
    return f'{account}/{model} is out of automatic routing on this host (unchecked in model management)'


# What an automatic plan adds to `outside_routing` / `unchecked_routing`: whose setting it is, and what it does.
NOT_CHOSEN = "the user's own setting on this machine, so the router does not choose it"


def sync_failed(error):
    """The one wording of a `sync_discovered` that could not run (`account_fleet.load_accounts` keeps the error)."""
    return (f'host-policy.json could not be updated with newly discovered accounts ({error}); an account discovered since '
            'it was last written is not in its allowed_accounts, so it stays out of automatic routing until the file can '
            'be written')


def model_unchecked(bundle, accounts):
    """Whether the bundle is unchecked in model management (`disabled`, the user's checkbox or off by default): its own
    row when it has one, else every row of its model on its account (a level with no row of its own)."""
    import account_fleet
    catalog = account_fleet.bundles(accounts)
    bundle_id = bundle.get('bundle_id') or bundle.get('id')
    if bundle_id in catalog:
        return bool(catalog[bundle_id].get('disabled'))
    key = account_fleet.row_key(bundle.get('model') or '', accounts)
    rows = [b for b in catalog.values()
            if b['account'] == bundle.get('account') and account_fleet.row_key(b['model'], accounts) == key]
    return bool(rows) and all(b.get('disabled') for b in rows)


def automatic_routing_exclusions(bundle, accounts, policy):
    """The automatic-routing switches a launch on `bundle` reaches past, in a fixed order: `account` (outside
    `allowed_accounts`), `model` (unchecked in model management). Both are preferences: the router never chooses past
    them, and a route the user names does (`route_judge.record_constraint`)."""
    return [name for name, out in (('account', not account_allowed(policy, bundle.get('account'))),
                                   ('model', model_unchecked(bundle, accounts))) if out]


def exclusion_texts(bundle, accounts, policy):
    """The wording of each switch `automatic_routing_exclusions` names, in its order."""
    texts = {'account': lambda: outside_routing(bundle.get('account')),
             'model': lambda: unchecked_routing(bundle.get('account'), bundle.get('model'))}
    return [texts[name]() for name in automatic_routing_exclusions(bundle, accounts, policy)]


def legacy_cause(account, accounts):
    """('legacy', text) when the account still carries leftover meter text, else None. A fact: it refuses a launch and
    a parent's new turn to its own worker alike."""
    legacy = ((accounts or {}).get('accounts') or {}).get(account, {}).get('legacy_meter')
    return ('legacy', legacy) if isinstance(legacy, str) and legacy.strip() else None


def disabled_cause(account, candidates, accounts):
    """(kind, detail) when a launch of the target needs more than a routing decision, else None. Kinds: `legacy`
    (`legacy_cause`, a fact: refused whatever the route), `bundles` (ids all unchecked in model management;
    `candidates` are the account's matching bundle rows: out of automatic routing, so only a route the user named
    launches it). A new turn to an existing worker reads only `legacy_cause`: continuing a worker is not choosing its
    model. Host policy is not a cause: it governs automatic routing only (`account_allowed`)."""
    found = legacy_cause(account, accounts)
    if found:
        return found
    if candidates and all(c.get('disabled') for c in candidates):
        return 'bundles', [c['bundle_id'] for c in candidates]
    return None


def disabled_text(cause):
    """The spawn gate's wording of a `disabled_cause`: the leftover meter text itself, or the unchecked bundles."""
    kind, detail = cause
    return detail if kind == 'legacy' else "档位 " + ", ".join(detail) + " 在模型管理中未勾选(不参与自动派发)"


def usage_providers(policy, defaults):
    if policy is None or 'usage_providers' not in policy:
        return list(defaults)
    allowed = set(policy['usage_providers'])
    return [name for name in defaults if name in allowed]


def main():
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument('--account', required=True)
    args = parser.parse_args()
    try:
        allowed = account_allowed(load_policy(), args.account)
    except HostPolicyError as error:
        parser.exit(2, str(error) + '\n')
    print(json.dumps({'account': args.account, 'allowed': allowed}))
    return 0 if allowed else 1


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