Skip to content

akiiwa-games/AgentCompass / skills/agent-compass

agent-compass

Flagged

Multi-agent task router and subscription quota scheduler. 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 md5.6 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.mdmarkdown37.7 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.mdmarkdown94.5 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.pyscript63.1 KB
scripts/dispatch_ground_truth.pyscript43.5 KB
scripts/dispatch_registry.pyscript130.8 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.pyscript83.5 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.pyscript352.4 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

grok-bot/test-recovery.mjs

View on GitHub
// Execute both installed upstream gateway modules, with synthetic storage and mocked HTTP only.
import assert from 'node:assert/strict';
import crypto from 'node:crypto';
import fs from 'node:fs';
import path from 'node:path';
import os from 'node:os';
import vm from 'node:vm';
import { test } from 'node:test';

const account = 'a'.repeat(64), other = 'b'.repeat(64), key = Buffer.alloc(32, 7);
function encrypted(text) {
  const iv = Buffer.alloc(12, 8), cipher = crypto.createCipheriv('aes-256-gcm', key, iv);
  return Buffer.concat([Buffer.from('v10'), iv, cipher.update(text), cipher.final(), cipher.getAuthTag()]).toString('base64');
}

function fixture(bundle) {
  const source = fs.readFileSync(new URL(`./runtime/bin/${bundle}`, import.meta.url), 'utf8');
  const state = { active: account, team: '41', missing: false, legacy: false, calls: [], onRequest: null };
  const modules = {};
  const env = { GROK_BOT_TEST: '1', CURSOR_API_BASE_URL: 'http://127.0.0.1:1' };
  function stored() {
    return { version: 1, 'cursor-accounts': JSON.stringify({ active: state.active, accounts: {
      [state.active]: { 'cursor-access-token': encrypted('synthetic-access'),
        ...(state.team == null ? {} : { 'cursor-selected-team-id': state.unreadable ? 'invalid-encrypted-fixture' : encrypted(state.team) }) }
    }}), ...(state.legacy ? { 'cursor-selected-team-id': encrypted('42') } : {}) };
  }
  const fakeFs = {
    existsSync: p => !state.missing && ['sand-secrets.json', 'Local State', 'desktop-status.json'].includes(path.basename(p)),
    readFileSync: p => {
      if (path.basename(p) === 'sand-secrets.json') return JSON.stringify(stored());
      if (path.basename(p) === 'Local State') return JSON.stringify({ os_crypt: { encrypted_key: Buffer.from('DPAPIfixture').toString('base64') } });
      if (path.basename(p) === 'desktop-status.json') return JSON.stringify({ appVersion: '0.77.0' });
      throw Error('Unexpected filesystem read: ' + path.basename(p));
    }
  };
  const builtin = { 'node:crypto': { ...crypto, default: crypto }, 'node:fs': fakeFs, 'node:path': path, 'node:os': os,
    'node:child_process': { execFileSync() { throw Error('Native auth/process must not run in tests'); } } };
  function load(id) {
    if (builtin[id]) return builtin[id];
    if (modules[id]) return modules[id];
    if (id.endsWith('/store.js') || id.endsWith('/grok-approvals.js')) return {};
    const marker = `    "${id}" (`;
    const start = source.indexOf(marker);
    assert.ok(start >= 0, id);
    const body = source.indexOf('{\n', start) + 1;
    const end = source.indexOf('\n    },\n    "', body);
    assert.ok(end > body, id);
    const output = {};
    modules[id] = output;
    const require = Object.assign(load, { d: (out, getters) => {
      for (const [name, get] of Object.entries(getters)) Object.defineProperty(out, name, { get, enumerable: true });
    }});
    vm.runInNewContext(source.slice(body, end), {
      __webpack_require__: require, __webpack_exports__: output,
      process: { env, platform: 'win32' }, Buffer, AbortSignal, URL, console,
      fetch: async (url, options) => {
        const operation = url.split('/').at(-1);
        state.calls.push({ operation, authorization: options.headers.authorization, team: options.headers['x-cursor-team-id'], version: options.headers['x-cursor-client-version'] });
        assert.equal(options.redirect, 'error');
        const custom = await state.onRequest?.(operation, state.calls.length);
        if (custom) return custom;
        if (operation === 'EnsureSandBox') return Response.json({ gatewayUrl: 'http://127.0.0.1:2', gatewayToken: 'synthetic-gateway' });
        if (operation === 'listAgents') return Response.json([{ id: 'fixture-bot', name: 'Fixture' }]);
        if (operation === 'sendPrompt') return Response.json({ messageId: 'fixture-message' });
        throw Error('Unexpected operation');
      }
    }, { timeout: 1000 });
    return output;
  }
  const gateway = Object.fromEntries(Object.values(load('./src/core/gateway.js')).map(fn => [fn.name, fn]));
  const options = { appSessionOptions: { platform: 'win32', appData: 'fixture', unprotectData: () => key } };
  return { state, gateway, options, env };
}
const hibernated = () => new Response('', { status: 417, headers: {
  'x-anyrun-error-source': 'anyrun-proxy', 'x-anyrun-failure-reason': 'pod_hibernated'
}});

for (const bundle of ['gbot.mjs', 'gbot-flight.mjs']) {
  test(`${bundle}: missing descriptor bootstraps same scope; hibernated read recovers, send exactly once`, async () => {
    const { state, gateway, options } = fixture(bundle);
    let reads = 0;
    state.onRequest = operation => operation === 'listAgents' && ++reads === 1 ? hibernated() : null;
    const session = await gateway.connectGateway(options);
    await gateway.sendPrompt(session, 'fixture-bot', 'synthetic prompt');
    assert.deepEqual(state.calls.map(x => x.operation), ['EnsureSandBox', 'listAgents', 'EnsureSandBox', 'listAgents', 'sendPrompt']);
    for (const call of state.calls) {
      assert.equal(call.authorization, 'Bearer ' + (call.operation === 'EnsureSandBox' ? 'synthetic-access' : 'synthetic-gateway'));
      if (call.operation === 'EnsureSandBox') {
        assert.equal(call.team, '41');
        assert.equal(call.version, '0.77.0');
      }
    }
  });
  test(`${bundle}: write failure is never replayed`, async () => {
    const { state, gateway, options } = fixture(bundle);
    state.onRequest = operation => operation === 'sendPrompt' ? hibernated() : null;
    const session = await gateway.connectGateway(options);
    await assert.rejects(gateway.sendPrompt(session, 'fixture-bot', 'synthetic prompt'), /sendPrompt failed: 417/);
    assert.deepEqual(state.calls.map(x => x.operation), ['EnsureSandBox', 'listAgents', 'sendPrompt']);
  });
  test(`${bundle}: account/team drift before or during Ensure, or before send, aborts`, async () => {
    for (const kind of ['account', 'team']) {
      for (const phase of ['during-ensure', 'before-send', 'during-refresh']) {
        const { state, gateway, options } = fixture(bundle);
        const change = () => { if (kind === 'account') state.active = other; else state.team = '42'; };
        if (phase === 'during-ensure') {
          state.onRequest = operation => { if (operation === 'EnsureSandBox') change(); };
          await assert.rejects(gateway.connectGateway(options), /account|team/);
        } else {
          const session = await gateway.connectGateway(options);
          if (phase === 'before-send') {
            state.onRequest = operation => { if (operation === 'listAgents') change(); };
          } else {
            state.onRequest = operation => {
              if (operation === 'listAgents') return hibernated();
              if (operation === 'EnsureSandBox') change();
            };
          }
          await assert.rejects(gateway.sendPrompt(session, 'fixture-bot', 'synthetic prompt'), /account|team/);
        }
        assert.equal(state.calls.filter(x => x.operation === 'sendPrompt').length, 0);
      }
    }
  });
  test(`${bundle}: missing credentials, unsupported scope, legacy or corrupt team fail before HTTP`, async () => {
    for (const change of [s => s.missing = true, s => s.active = 'unknown-scope',
      s => { s.team = null; s.legacy = true; }, s => s.team = 'not-a-team', s => s.unreadable = true]) {
      const { state, gateway, options } = fixture(bundle);
      change(state);
      await assert.rejects(gateway.connectGateway(options));
      assert.equal(state.calls.length, 0);
    }
  });
  test(`${bundle}: absent team is personal, expired auth fails without token refresh or send`, async () => {
    const { state, gateway, options } = fixture(bundle);
    state.team = null;
    await gateway.connectGateway(options);
    assert.equal(state.calls[0].team, undefined);
    state.calls.length = 0;
    state.onRequest = () => new Response('', { status: 401 });
    await assert.rejects(gateway.connectGateway(options), /EnsureSandBox failed: 401/);
    assert.deepEqual(state.calls.map(x => x.operation), ['EnsureSandBox']);
  });
  test(`${bundle}: explicit gateway overrides never fall back to native credentials`, async () => {
    const { state, gateway, options, env } = fixture(bundle);
    state.missing = true;
    env.GROK_BOT_GATEWAY_URL = 'http://127.0.0.1:2';
    env.GROK_BOT_GATEWAY_TOKEN = 'synthetic-override';
    state.onRequest = () => hibernated();
    const session = await gateway.connectGateway(options);
    await assert.rejects(gateway.listAgents(session), /listAgents failed: 417/);
    assert.deepEqual(state.calls.map(x => x.operation), ['listAgents']);
    assert.equal(state.calls[0].authorization, 'Bearer synthetic-override');
  });
}
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: 472kUpdated 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