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/fixtures/reference-accounts.json

View on GitHub
{
  "status": "Synthetic mixed-fleet routing scenarios. Account names and plan tiers are fictional; explicit quota capacities and model calibration values are independent test inputs, not subscription entitlements or a description of any person or machine.",
  "quota_sources": {
    "grok-bot": "grok"
  },
  "scoring": {
    "small_short_capacity_usd": 50,
    "small_short_window_floor_pct": 25,
    "small_short_safety_margin_pct": 12,
    "safety_margin_pct": 5,
    "short_window_floor_pct": 10,
    "short_window_hours": 24,
    "defer_if_reset_within_hours": 6,
    "rotate_after_carried_tokens": 2000000,
    "context_burn_extra_at_250k": 0.5,
    "harness_order": [
      "codex",
      "pi"
    ],
    "profile": {
      "difficulty_by_level": {
        "1": "routine",
        "2": "hard",
        "3": "coupled"
      }
    }
  },
  "aliases": {
    "claude-haiku-4-5@20251001": "claude-haiku-4-5",
    "claude-opus-5": "claude-opus-5-5",
    "claude-sonnet-5": "claude-sonnet-5-5",
    "claude-fable-5": "claude-fable-5-2",
    "fable": "claude-fable-5-2",
    "gemini-3.8-flash": "gemini-3.8-flash-high",
    "gemini-4-argon": "gemini-4-argon-high",
    "argon": "gemini-4-argon-high",
    "ChatGPT Pro via chatgpt-pro-consult": "gpt-6-pro",
    "grok-4.7-latest": "grok-4.7",
    "grok-4": "grok-4.7",
    "opencode/deepseek-v4.1-flash-free": "deepseek-v4.1-flash-free",
    "deepseek-v4.1-flash": "deepseek-v4.1-flash-free",
    "deepseek": "deepseek-v4.1-flash-free",
    "glm-5.3-flash": "glm-5.3-flash-free",
    "opencode/glm-5.3-flash-free": "glm-5.3-flash-free",
    "MiniMax-M3": "minimax-m3",
    "MiniMax-M3.1-Flash": "minimax-m3.1-flash",
    "mimo-v2.6-flash": "mimo-v2.6-flash-free",
    "mimo-v2.6-pro-ultraspeed": "mimo-v2.6-pro",
    "kimi-k3.1-pro-highspeed": "kimi-k3.1-pro",
    "nemotron-3-ultra-550b-a55b": "nemotron-3-ultra-free",
    "nemotron-3.5-super-vl-120b-a12b": "nemotron-3.5-super-vl-free",
    "nemotron-3.5-lightning-30b-a3b": "nemotron-3.5-lightning-free",
    "opencode/mimo-v2.6-flash-free": "mimo-v2.6-flash-free",
    "opencode/nemotron-3-ultra-free": "nemotron-3-ultra-free",
    "opencode/nemotron-3.5-super-vl-free": "nemotron-3.5-super-vl-free",
    "opencode/nemotron-3.5-lightning-free": "nemotron-3.5-lightning-free",
    "opencode/beam-free": "beam-free",
    "opencode/flint-40b-free": "flint-40b-free",
    "deepseek-flash": "deepseek-v4.1-flash-free",
    "deepseek-v4-flash": "deepseek-v4.1-flash-free",
    "qwen-flash": "qwen3-flash-2025-07-28"
  },
  "provider_names": {
    "statement": "the reference fleet's own: its model table holds none of the rows the shipped provider_names declarations name, so it declares none",
    "defaults": {},
    "rows": {}
  },
  "superseded": {
    "claude-fable-5": {
      "by": "claude-fable-5-2",
      "basis": "Claude Fable 5.2 is the newer Fable release."
    },
    "claude-fable-5-1": {
      "by": "claude-fable-5-2",
      "basis": "Claude Fable 5.2 is the newer Fable release."
    },
    "claude-haiku-4-5": {
      "by": "claude-haiku-5-5",
      "basis": "Claude Haiku 5.5 is the current Haiku generation (advertised by the same Claude accounts)."
    },
    "claude-opus-4-6": {
      "by": "claude-opus-5-5",
      "basis": "Claude Opus 5.5 is the current Opus generation; 4.6 is the 4.x line."
    },
    "claude-opus-4-7": {
      "by": "claude-opus-5-5",
      "basis": "Claude Opus 5.5 is the current Opus generation; 4.7 is the 4.x line."
    },
    "claude-opus-4-8": {
      "by": "claude-opus-5-5",
      "basis": "Claude Opus 5.5 is the current Opus generation; 4.8 is the 4.x line."
    },
    "claude-opus-5": {
      "by": "claude-opus-5-5",
      "basis": "Claude Opus 5.5 is the newer Opus release."
    },
    "claude-sonnet-4-6": {
      "by": "claude-sonnet-5-5",
      "basis": "Claude Sonnet 5.5 is the current Sonnet generation."
    },
    "claude-sonnet-5": {
      "by": "claude-sonnet-5-5",
      "basis": "Claude Sonnet 5.5 is the newer Sonnet release."
    },
    "deepseek-v4-flash": {
      "by": "deepseek-v4.1-flash-free",
      "basis": "DeepSeek V4.1 Flash is the newer Flash release."
    },
    "deepseek-v4.1-flash": {
      "by": "deepseek-v4.1-flash-1017",
      "basis": "DeepSeek's own price list names DeepSeek-V4.1-Flash-1017 as deepseek-flash; Artificial Analysis marks DeepSeek V4.1 Flash deprecated."
    },
    "gemini-3.1-pro-preview": {
      "by": "gemini-4-argon-high",
      "basis": "Gemini 4 Pro (Argon) is the newer Pro generation."
    },
    "gemini-3.7-flash": {
      "by": "gemini-3.8-flash-high",
      "basis": "Gemini 3.8 Flash is the newer Flash release."
    },
    "glm-5.2": {
      "by": "glm-5.3",
      "basis": "GLM-5.3 is the newer GLM release."
    },
    "gpt-5.6-luna": {
      "by": "gpt-6-luna",
      "basis": "GPT-6 Luna is the newer Luna release."
    },
    "gpt-5.6-sol": {
      "by": "gpt-6.1-sol",
      "basis": "GPT-6.1 Sol is two releases newer in the Sol line."
    },
    "gpt-5.6-terra": {
      "by": "gpt-6.1-terra",
      "basis": "GPT-6.1 Terra is the newer Terra release."
    },
    "gpt-6-sol": {
      "by": "gpt-6.1-sol",
      "basis": "GPT-6.1 Sol is the newer Sol release."
    },
    "grok-4.5": {
      "by": "grok-4.7",
      "basis": "Grok 4.7 is the current Grok release."
    },
    "grok-4.6": {
      "by": "grok-4.7",
      "basis": "Grok 4.7 is the current Grok release."
    },
    "kimi-k2.6": {
      "by": "kimi-k3",
      "basis": "Kimi K3 is the newer Kimi generation."
    },
    "qwen3.7-max": {
      "by": "qwen3.8-max",
      "basis": "Qwen3.8-Max is the newer Qwen Max release."
    }
  },
  "same_model": {
    "dot": {
      "model": "gpt-6-astra",
      "carries": [
        "creativity",
        "coding",
        "aesthetics",
        "duration"
      ],
      "kind": "vendor",
      "statement": "OpenAI announces dots as always-on agents powered by GPT-6 Astra (DevDay, 2026-09-29).",
      "url": "https://openai.com/index/introducing-dots/",
      "as_of": "2026-09-29",
      "not_carried": "tool_operation: Dot takes no image or screenshot input through its packet channel (owner, 2026-10-09) and its per-turn speed is the packet channel's, so tool operation is the channel's own and stays missing, not Astra's."
    },
    "grok-bot": {
      "model": "claude-opus-5-5",
      "carries": [
        "creativity",
        "coding",
        "aesthetics",
        "duration",
        "usd_per_hour"
      ],
      "kind": "maintainer",
      "statement": "maintainer: grok-bot is Opus 5.5",
      "as_of": "2026-11-11",
      "not_carried": "tool_operation: grok-bot's per-turn speed and image recognition are the web channel's own, so tool operation stays channel-specific rather than Opus 5.5's.",
      "capacity_rule": {
        "kind": "maintainer",
        "as_of": "2026-11-11",
        "statement": "maintainer: grok-bot price and quota capacity follow the same-price Claude subscription",
        "target_family": "grok",
        "target_window": "credits",
        "reference_family": "claude",
        "reference_window": "seven_day"
      }
    }
  },
  "models": {
    "deepseek-v4.1-flash-free": {},
    "claude-fable-5-1": {
      "api_family": "claude"
    },
    "claude-fable-5-2": {
      "fast_capable": true,
      "api_family": "claude"
    },
    "claude-opus-5-5": {
      "fast_capable": true,
      "api_family": "claude"
    },
    "gpt-6.1-sol": {
      "fast_capable": true,
      "api_family": "codex"
    },
    "gpt-6-astra": {
      "fast_capable": true,
      "api_family": "codex"
    },
    "gemini-4-argon-high": {},
    "claude-sonnet-5-5": {
      "api_family": "claude"
    },
    "grok-4.7": {},
    "gemini-3.8-flash-high": {},
    "grok-bot": {
      "fixed_effort": "medium",
      "excluded_when": "local_only",
      "image_input_source": {
        "kind": "maintainer",
        "statement": "maintainer: grok-bot accepts image input",
        "as_of": "2026-11-11"
      }
    },
    "dot": {
      "excluded_when": "local_only"
    },
    "gpt-6-pro": {
      "advisor_only": true,
      "advisor_for": [
        "architecture_reasoning",
        "creative_ideation"
      ],
      "api_family": "codex"
    },
    "claude-haiku-5-5": {
      "api_family": "claude"
    },
    "gpt-6.1-terra": {
      "fast_capable": true,
      "context_window": 500000,
      "api_family": "codex"
    },
    "gpt-6-sol": {
      "fast_capable": true,
      "context_window": 272000,
      "api_family": "codex"
    },
    "gpt-6-luna": {
      "fast_capable": true,
      "context_window": 272000,
      "api_family": "codex"
    },
    "gpt-5.6-sol": {
      "context_window": 272000,
      "api_family": "codex"
    },
    "gpt-5.6-terra": {
      "context_window": 272000,
      "api_family": "codex"
    },
    "gpt-5.6-luna": {
      "context_window": 272000,
      "api_family": "codex"
    },
    "grok-4.7-build-fast": {},
    "deepseek-v4-pro": {},
    "glm-5.3": {},
    "glm-5.3-flash-free": {},
    "qwen3-coder-next": {},
    "qwen3.8-max": {},
    "kimi-k3.1-pro": {},
    "kimi-k3": {},
    "minimax-m3": {},
    "minimax-m3.1-flash": {},
    "doubao-seed-2-1-pro-260628": {},
    "mimo-v2.6-pro": {},
    "mimo-v2.6-flash-free": {},
    "nemotron-3-ultra-free": {},
    "nemotron-3.5-super-vl-free": {},
    "nemotron-3.5-lightning-free": {},
    "mistral-large-4": {},
    "muse-wonder-1.0": {},
    "beam-free": {},
    "flint-40b-free": {},
    "claude-haiku-4-5": {
      "api_family": "claude"
    },
    "claude-opus-4-6": {
      "api_family": "claude"
    },
    "claude-sonnet-4-6": {
      "api_family": "claude"
    },
    "glm-5.2": {},
    "gpt-oss-120b": {
      "api_family": "codex"
    },
    "gemini-3.1-flash-lite": {},
    "kimi-k2.7-code": {},
    "qwen3.6-plus": {},
    "claude-opus-4-7": {
      "api_family": "claude"
    },
    "claude-opus-4-8": {
      "fast_capable": true,
      "api_family": "claude"
    },
    "grok-4.5": {},
    "grok-4.6": {},
    "gemini-3.1-pro-preview": {},
    "gemini-3.7-flash": {},
    "kimi-k2.6": {},
    "qwen3.7-max": {},
    "qwen3-flash-2025-07-28": {
      "context_window": 1000000
    },
    "gemini-4-carbon": {}
  },
  "dispatch_efforts": {
    "grok": {
      "grok-4.7": [
        "low",
        "high",
        "xhigh"
      ],
      "grok-4.7-build-fast": [
        "high"
      ]
    },
    "claude": {
      "claude-opus-4-6": [
        "high"
      ],
      "claude-sonnet-4-6": [
        "high"
      ],
      "claude-haiku-4-5": [
        "high"
      ],
      "claude-opus-5-5": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
      ],
      "claude-sonnet-5-5": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
      ],
      "claude-fable-5-1": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
      ],
      "claude-fable-5-2": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
      ],
      "claude-haiku-5-5": [
        "high"
      ]
    },
    "claude-lab": {
      "claude-opus-5-5": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
      ],
      "claude-sonnet-5-5": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
      ],
      "claude-fable-5-1": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
      ],
      "claude-fable-5-2": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
      ]
    },
    "codex": {
      "gpt-6-pro": [
        "high"
      ],
      "gpt-6-astra": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max",
        "ultra"
      ],
      "gpt-6.1-sol": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max",
        "ultra"
      ],
      "gpt-6.1-terra": [
        "high"
      ],
      "gpt-6-sol": [
        "high"
      ],
      "gpt-6-luna": [
        "high"
      ],
      "gpt-5.6-sol": [
        "high"
      ],
      "gpt-5.6-terra": [
        "high"
      ],
      "gpt-5.6-luna": [
        "high"
      ]
    },
    "codex-work": {
      "gpt-6-astra": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max",
        "ultra"
      ],
      "gpt-6.1-sol": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max",
        "ultra"
      ]
    },
    "opencode": {
      "deepseek-v4.1-flash-free": [
        "default",
        "low",
        "high",
        "max"
      ]
    },
    "antigravity-resilient": {
      "claude-opus-5-5": [
        "low",
        "medium",
        "high"
      ],
      "claude-sonnet-5-5": [
        "low",
        "medium",
        "high"
      ]
    },
    "pi": {
      "gpt-6-pro": [
        "high"
      ],
      "gpt-6-astra": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
      ],
      "gpt-6.1-sol": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
      ],
      "gpt-6.1-terra": [
        "high"
      ],
      "gpt-6-sol": [
        "high"
      ],
      "gpt-6-luna": [
        "high"
      ],
      "gpt-5.6-sol": [
        "high"
      ],
      "gpt-5.6-terra": [
        "high"
      ],
      "gpt-5.6-luna": [
        "high"
      ]
    }
  },
  "accounts": {
    "grok": {
      "plan": "subscription",
      "billing": "subscription",
      "verified": false,
      "expires_at": null,
      "unmetered": true,
      "windows": {},
      "bundles": {
        "grok47_high": {
          "provider": "grok",
          "harness": "grok",
          "model": "grok-4.7",
          "effort": "high"
        }
      },
      "label": "Text subscription sandbox"
    },
    "claude": {
      "family": "claude",
      "plan": "max5",
      "billing": "subscription",
      "verified": true,
      "expires_at": null,
      "windows": {
        "five_hour": {
          "hours": 5
        },
        "seven_day": {
          "hours": 168
        },
        "weekly_fable": {
          "hours": 168,
          "models": [
            "fable"
          ]
        }
      },
      "bundles": {
        "fable51_high": {
          "model": "claude-fable-5-1",
          "effort": "high",
          "disabled": true
        },
        "fable52_high": {
          "model": "claude-fable-5-2",
          "effort": "high",
          "disabled": true
        },
        "opus55_xhigh": {
          "model": "claude-opus-5-5",
          "effort": "xhigh"
        },
        "opus55_high": {
          "model": "claude-opus-5-5",
          "effort": "high"
        },
        "sonnet55_high": {
          "model": "claude-sonnet-5-5",
          "effort": "high"
        },
        "opus55_medium": {
          "model": "claude-opus-5-5",
          "effort": "medium"
        },
        "opus55_max": {
          "model": "claude-opus-5-5",
          "effort": "max"
        },
        "sonnet55_medium": {
          "model": "claude-sonnet-5-5",
          "effort": "medium"
        }
      },
      "label": "Studio reasoning pool"
    },
    "claude-lab": {
      "family": "claude",
      "plan": "pro",
      "billing": "subscription",
      "verified": true,
      "expires_at": null,
      "windows": {
        "five_hour": {
          "hours": 5,
          "launch_min_remaining_pct": 25
        },
        "seven_day": {
          "hours": 168
        },
        "weekly_fable": {
          "hours": 168,
          "models": [
            "fable"
          ]
        }
      },
      "bundles": {
        "lab_fable51_high": {
          "model": "claude-fable-5-1",
          "effort": "high",
          "disabled": true
        },
        "lab_fable52_high": {
          "model": "claude-fable-5-2",
          "effort": "high",
          "disabled": true
        },
        "lab_opus55_xhigh": {
          "model": "claude-opus-5-5",
          "effort": "xhigh",
          "disabled": true
        },
        "lab_opus55_high": {
          "model": "claude-opus-5-5",
          "effort": "high",
          "disabled": true
        },
        "lab_sonnet55_high": {
          "model": "claude-sonnet-5-5",
          "effort": "high"
        },
        "lab_opus55_medium": {
          "model": "claude-opus-5-5",
          "effort": "medium",
          "disabled": true
        },
        "lab_opus55_max": {
          "model": "claude-opus-5-5",
          "effort": "max",
          "disabled": true
        },
        "lab_sonnet55_medium": {
          "model": "claude-sonnet-5-5",
          "effort": "medium"
        }
      },
      "label": "Research sandbox"
    },
    "codex": {
      "family": "codex",
      "plan": "plus",
      "billing": "subscription",
      "verified": true,
      "expires_at": null,
      "windows": {
        "usage": {
          "hours": 168
        }
      },
      "bundles": {
        "sol_max": {
          "model": "gpt-6.1-sol",
          "effort": "max"
        },
        "sol_xhigh": {
          "model": "gpt-6.1-sol",
          "effort": "xhigh"
        },
        "sol_high": {
          "model": "gpt-6.1-sol",
          "effort": "high"
        },
        "sol_medium": {
          "model": "gpt-6.1-sol",
          "effort": "medium"
        },
        "astra_high": {
          "model": "gpt-6-astra",
          "effort": "high"
        },
        "astra_xhigh": {
          "model": "gpt-6-astra",
          "effort": "xhigh"
        },
        "pi_sol_max": {
          "model": "gpt-6.1-sol",
          "effort": "max",
          "provider": "pi",
          "launch_model": "openai-codex/gpt-6.1-sol"
        },
        "pi_sol_xhigh": {
          "model": "gpt-6.1-sol",
          "effort": "xhigh",
          "provider": "pi",
          "launch_model": "openai-codex/gpt-6.1-sol"
        },
        "pi_sol_high": {
          "model": "gpt-6.1-sol",
          "effort": "high",
          "provider": "pi",
          "launch_model": "openai-codex/gpt-6.1-sol"
        },
        "pi_sol_medium": {
          "model": "gpt-6.1-sol",
          "effort": "medium",
          "provider": "pi",
          "launch_model": "openai-codex/gpt-6.1-sol"
        },
        "pi_astra_high": {
          "model": "gpt-6-astra",
          "effort": "high",
          "provider": "pi",
          "launch_model": "openai-codex/gpt-6-astra"
        },
        "pi_astra_xhigh": {
          "model": "gpt-6-astra",
          "effort": "xhigh",
          "provider": "pi",
          "launch_model": "openai-codex/gpt-6-astra"
        }
      },
      "label": "Individual coding sandbox"
    },
    "codex-work": {
      "family": "codex",
      "plan": "team",
      "billing": "subscription",
      "verified": false,
      "expires_at": null,
      "windows": {
        "usage": {
          "hours": 168
        }
      },
      "bundles": {
        "work_sol_xhigh": {
          "model": "gpt-6.1-sol",
          "effort": "xhigh"
        }
      },
      "label": "Shared coding workspace"
    },
    "antigravity": {
      "plan": "ultra5",
      "billing": "subscription",
      "verified": true,
      "expires_at": null,
      "windows": {
        "gemini-5h": {
          "hours": 5,
          "models": [
            "gemini"
          ]
        },
        "gemini-weekly": {
          "hours": 168,
          "models": [
            "gemini"
          ]
        },
        "3p-5h": {
          "hours": 5,
          "models_except": [
            "gemini"
          ]
        },
        "3p-weekly": {
          "hours": 168,
          "models_except": [
            "gemini"
          ]
        }
      },
      "bundles": {
        "flash_high": {
          "provider": "antigravity-resilient",
          "model": "gemini-3.8-flash-high",
          "effort": "high",
          "modeId": "full-access"
        },
        "argon_high": {
          "provider": "antigravity-resilient",
          "model": "gemini-4-argon-high",
          "effort": "high",
          "modeId": "full-access"
        },
        "agy_opus55_low": {
          "provider": "antigravity-resilient",
          "model": "claude-opus-5-5-low",
          "launch_model": "claude-opus-5-5-low",
          "effort": "low",
          "modeId": "full-access",
          "draws": [
            "3p-5h",
            "3p-weekly"
          ]
        },
        "agy_opus55_medium": {
          "provider": "antigravity-resilient",
          "model": "claude-opus-5-5-medium",
          "launch_model": "claude-opus-5-5-medium",
          "effort": "medium",
          "modeId": "full-access",
          "draws": [
            "3p-5h",
            "3p-weekly"
          ]
        },
        "agy_opus55_high": {
          "provider": "antigravity-resilient",
          "model": "claude-opus-5-5-high",
          "launch_model": "claude-opus-5-5-high",
          "effort": "high",
          "modeId": "full-access",
          "draws": [
            "3p-5h",
            "3p-weekly"
          ]
        },
        "agy_sonnet55_low": {
          "provider": "antigravity-resilient",
          "model": "claude-sonnet-5-5-low",
          "launch_model": "claude-sonnet-5-5-low",
          "effort": "low",
          "modeId": "full-access",
          "draws": [
            "3p-5h",
            "3p-weekly"
          ]
        },
        "agy_sonnet55_medium": {
          "provider": "antigravity-resilient",
          "model": "claude-sonnet-5-5-medium",
          "launch_model": "claude-sonnet-5-5-medium",
          "effort": "medium",
          "modeId": "full-access",
          "draws": [
            "3p-5h",
            "3p-weekly"
          ]
        },
        "agy_sonnet55_high": {
          "provider": "antigravity-resilient",
          "model": "claude-sonnet-5-5-high",
          "launch_model": "claude-sonnet-5-5-high",
          "effort": "high",
          "modeId": "full-access",
          "draws": [
            "3p-5h",
            "3p-weekly"
          ]
        }
      },
      "label": "Mixed model pool"
    },
    "dot": {
      "plan": "remote",
      "billing": "subscription",
      "verified": true,
      "expires_at": null,
      "unmetered": true,
      "unlimited": true,
      "windows": {},
      "bundles": {
        "dot_text": {
          "model": "dot",
          "provider": "dot"
        }
      },
      "label": "Remote execution sandbox"
    },
    "chatgpt-web": {
      "plan": "pro",
      "billing": "subscription",
      "verified": true,
      "expires_at": null,
      "unmetered": true,
      "windows": {},
      "bundles": {
        "pro_max": {
          "model": "gpt-6-pro",
          "effort": "max",
          "provider": "chatgpt-web"
        }
      },
      "cadence": {
        "window_seconds": 43200,
        "limit": 5
      },
      "label": "Web advisory sandbox"
    },
    "opencode": {
      "plan": "free",
      "billing": "subscription",
      "verified": true,
      "expires_at": null,
      "unmetered": true,
      "unlimited": true,
      "windows": {},
      "bundles": {
        "deepseek_flash_high": {
          "provider": "opencode",
          "model": "deepseek-v4.1-flash-free",
          "launch_model": "opencode/deepseek-v4.1-flash-free",
          "effort": "high",
          "modeId": "build"
        }
      },
      "label": "Free model sandbox"
    }
  },
  "capability_policy": {
    "routes": {
      "creative_ideation": {
        "scope": "Cross-domain association, de-novo concept or mechanism invention, creative writing, narrative dialogue, and open-ended brainstorming.",
        "role": "ideation worker or advisor",
        "harness_order": [
          "pi",
          "codex"
        ]
      },
      "architecture_reasoning": {
        "scope": "First-principles system architecture, formal or mathematical reasoning, trade-off critique, and multi-system design planning without modifying source code.",
        "role": "architect or reasoning advisor",
        "harness_order": [
          "pi",
          "codex"
        ]
      },
      "code_implementation": {
        "scope": "Write, fix, refactor, or test backend, CLI, library, algorithm, configuration, or quantitative/experiment code.",
        "role": "worker",
        "harness_order": [
          "codex",
          "pi"
        ]
      },
      "frontend_ui": {
        "scope": "Implement, refactor, or style user-facing web or desktop UI views, interactive components, charts, layouts, CSS, and animations.",
        "role": "frontend worker",
        "harness_order": [
          "codex",
          "pi"
        ]
      },
      "code_audit": {
        "scope": "Independent read-only review or audit of code, pull requests, diffs, branches, security invariants, or release readiness (including writing a review report file).",
        "role": "independent reviewer",
        "harness_order": [
          "codex",
          "pi"
        ]
      },
      "exploration_forensics": {
        "scope": "Read-only codebase exploration, log/database/metric forensics, and runtime root-cause diagnosis on local evidence without modifying code.",
        "implies": {
          "local_only": true
        },
        "role": "explorer or forensic analyst",
        "harness_order": [
          "pi",
          "codex"
        ]
      },
      "web_research": {
        "scope": "Gather, verify, and synthesize information from the public web, literature, documentation, or vendor sources into a sourced report.",
        "role": "research worker",
        "harness_order": [
          "pi",
          "codex"
        ]
      },
      "visual_analysis": {
        "scope": "Static offline inspection of images, photos, screenshots, or design mockups: OCR, UI layout/mockup diffs, and fine-grained aesthetic, styling, material, or lighting classification.",
        "implies": {
          "visual": true
        },
        "role": "visual analyst",
        "harness_order": [
          "pi",
          "codex"
        ]
      },
      "text_processing": {
        "scope": "Rule-defined structured text cleaning, translation, format conversion, mechanical extraction, and bounded summarization.",
        "role": "text worker",
        "harness_order": [
          "pi",
          "codex"
        ]
      },
      "live_loop": {
        "scope": "Low-latency observe-decide-act loop attached to a live external text, WebSocket, or API stream where per-turn response time affects the outcome.",
        "role": "live-loop worker",
        "harness_order": [
          "codex",
          "pi"
        ]
      },
      "gui_control": {
        "scope": "Operate a live desktop, browser, or mobile graphical interface via screenshots, mouse clicks, and keyboard actions, or continuously monitor a live visual screen.",
        "implies": {
          "visual": true
        },
        "role": "computer-use worker",
        "harness_order": [
          "codex",
          "pi"
        ]
      },
      "other_or_mixed": {
        "scope": "Unprofiled fallback route when no canonical work_kind was supplied.",
        "role": "bounded worker"
      }
    },
    "remote_reroute_guard": {
      "enabled": true,
      "bundle_id": "dot_text",
      "window_seconds": 600
    }
  },
  "priority_targets": [
    {
      "account": "codex",
      "model": "gpt-6-astra",
      "label": "Astra"
    },
    {
      "account": "antigravity",
      "model": "gemini-4-argon-high",
      "label": "Argon"
    },
    {
      "account": "claude",
      "model": "claude-opus-5-5",
      "label": "Opus 5.5"
    }
  ]
}
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