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

references/model-capabilities.md

View on GitHub
# Model capability catalogue

Generated from `accounts.json` and `five-axis-scores.json` by `scripts/capability_catalog.py`; do not edit this view.

Each model is scored on four categories (creativity, coding, aesthetics, tool operation) that gather the public boards as panel standard scores (0 = the anchor at High, one unit = one panel standard deviation), and on the quota economy; nothing else scores a model. Aesthetics evaluates design at level 1 and the weaker of design and image recognition at levels 2 and 3 (the column shows design); tool operation shows the weaker of responsiveness and image recognition. Known catalogue IDs do not prove sign-in, plan capacity, current price, or live model availability.

Route order and plan capacity ship as calibrated public defaults; plan capacity follows the discovered plan (`plan-templates.json`). Disabled models and bundles are personal settings in `accounts-override.json`. Unknown hourly cost remains unknown; it does not mean unlimited.

| Model | Tier | Creativity | Coding | Aesthetics | Tool operation | USD per hour | Image input |
| :--- | ---: | ---: | ---: | ---: | ---: | ---: | :--- |
| `beam-free` | -0.59 | -3.61 | -3.35 | -3.85 | missing! | - | unknown |
| `claude-fable-5` | -0.02 | -0.44 | -1.30~ | -1.25 | 0.05~ | 48.409 | yes |
| `claude-fable-5-1` | -0.02 | -0.89 | -0.53 | -0.67 | -0.21 | 39.05 | yes |
| `claude-fable-5-2` | 0.20 | 0.21u | 0.05u | 0.37u | -0.19u | 28.383 | yes |
| `claude-haiku-4-5` | -0.76 | -3.64 | -3.51~ | -4.57 | -3.38~ | 30.0 | yes |
| `claude-haiku-5-5` | -0.70 | -4.35 | -2.09~ | -1.96 | -3.12~ | 3.0 | yes |
| `claude-opus-4-5` | -0.27 | -1.35 | -1.76~ | -2.74 | -3.31 | 25.245 | yes |
| `claude-opus-4-6` | -0.03 | -0.52 | -1.50~ | -2.13 | -0.22~ | 25.245 | yes |
| `claude-opus-4-7` | -0.05 | -0.77 | -1.50~ | -2.58 | -0.26~ | 25.245 | yes |
| `claude-opus-4-8` | -0.20 | -1.32 | -2.19~ | -2.40 | -0.77~ | 25.245 | yes |
| `claude-opus-5` | -0.14 | -1.29 | -1.31~ | -1.01 | -0.56 | 25.245 | yes |
| `claude-opus-5-5` | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 28.0 | yes |
| `claude-sonnet-4-6` | -0.28 | -1.91 | -3.14~ | -2.49 | -1.08~ | 23.559 | yes |
| `claude-sonnet-5` | -0.38 | -2.33 | -2.14 | -2.23 | -2.00~ | 15.706 | yes |
| `claude-sonnet-5-5` | -0.04 | -2.14 | -0.89 | -0.59 | -1.69 | 20.25 | yes |
| `codestral-2508` | -0.70 | -4.85~ | -4.66~ | -4.67 | -4.66~ | 1.286 | no |
| `deepseek-v4-flash` | -0.58 | -3.05 | -2.75~ | -2.64 | -2.87~ | 1.544 | no |
| `deepseek-v4-flash-promo` | -0.58 | -3.05~ | -2.75~ | -2.64~ | -2.87~ | - | unknown |
| `deepseek-v4-pro` | -0.40 | -1.98 | -2.11~ | -2.98 | -1.81~ | - | no |
| `deepseek-v4-pro-0813` | -0.64 | -3.05~ | -2.53u | -2.64~ | -2.87~ | 2.882 | no |
| `deepseek-v4.1-flash` | -0.48 | -2.40~ | -1.93~ | -1.20 | -2.16~ | 0.955 | yes |
| `deepseek-v4.1-flash-1017` | -0.48 | -2.64~ | -1.96~ | -1.27 | -1.72 | 0.955 | yes |
| `deepseek-v4.1-flash-economy` | -0.48 | -2.64~ | -1.96~ | -1.20~ | -1.72~ | - | unknown |
| `deepseek-v4.1-flash-free` | -0.48 | -2.40~ | -1.93~ | -1.20 | -2.16~ | 0.955 | yes |
| `deepseek-v4.1-flash-promo` | -0.48 | -2.64~ | -1.96~ | -1.20~ | -1.72~ | - | unknown |
| `dot` | 0.06 | -2.13~ | 0.01u | -0.19u | -1.86u | - | yes |
| `doubao-seed-2-1-pro-260628` | - | -3.45u | -2.62u | missing! | -2.85u | - | unknown |
| `doubao-seed-2.0-mini` | - | missing! | missing! | missing! | missing! | - | unknown |
| `doubao-seed-2.1-lite` | - | missing! | missing! | missing! | missing! | - | unknown |
| `doubao-seed-2.1-pro` | - | missing! | missing! | missing! | missing! | - | unknown |
| `doubao-seed-evolving` | - | missing! | missing! | missing! | missing! | - | unknown |
| `flint-40b-free` | - | -3.45u | -2.62u | -2.78u | -2.85u | - | unknown |
| `gemini-2.5-flash-lite` | -0.28 | -1.70~ | -2.92~ | -3.41~ | -7.75 | 0.704 | yes |
| `gemini-3-flash-preview` | -0.28 | -1.70 | -2.92~ | -3.41 | -1.34 | 3.755 | yes |
| `gemini-3.1-flash-lite` | -0.74 | -3.66~ | -3.71~ | -5.11~ | -2.89 | 1.877 | yes |
| `gemini-3.1-pro-preview` | -0.16 | -0.99 | -2.92~ | -2.50 | -0.84 | 12.429 | yes |
| `gemini-3.5-flash` | -0.23 | -1.45 | -2.55~ | -2.17 | -0.43 | 11.264 | yes |
| `gemini-3.5-flash-lite` | -0.42 | -2.27 | -3.35~ | -3.89 | -1.69 | 2.418 | yes |
| `gemini-3.6-flash` | -0.20 | -1.28 | -2.52 | -2.02 | -0.72 | 5.455 | yes |
| `gemini-3.7-flash` | -0.14 | -0.84 | -2.43 | -1.40 | -0.19~ | 5.455 | yes |
| `gemini-3.8-flash-high` | -0.08 | -0.80 | -2.12 | -1.42 | -0.12 | 5.294 | yes |
| `gemini-4-argon-high` | 0.12 | 0.15 | -0.76 | -0.58 | -1.12u | 6.0 | yes |
| `gemini-4-carbon` | 0.16 | -0.03 | 0.00u | -0.03 | -1.70u | 8.463 | yes |
| `gemini-4-hydrogen-high` | -0.13 | -0.71 | -1.27~ | -0.45 | -0.35~ | 17.094 | yes |
| `gemini-4-neon` | 0.15 | 0.11~ | -0.65~ | -0.26~ | -0.90~ | 15.41 | yes |
| `gemini-pro-orchestrator` | 0.09 | -0.20~ | -0.32~ | -0.14~ | -1.22~ | 10.089 | unknown |
| `gemini-pro-orchestrator-argon` | 0.06 | -0.06~ | -0.81~ | -0.55~ | -0.79~ | 7.795 | unknown |
| `gemini-pro-orchestrator-neon` | 0.08 | -0.10~ | -0.81~ | -0.31~ | -0.62~ | 15.815 | unknown |
| `gemma-4-26b-a4b-it` | -0.57 | -3.28 | -4.09~ | -4.67 | -3.17 | 1.215 | yes |
| `gemma-4-31b-it` | -0.45 | -2.76 | -3.76~ | -4.55 | -2.33 | 2.035 | yes |
| `glm-4.5` | -0.78 | -4.06 | -3.17~ | -3.33 | -5.09~ | 14.547 | no |
| `glm-4.5-air` | -1.09 | -5.30 | -3.83~ | -3.76 | -6.45~ | - | no |
| `glm-4.5-flash` | -1.16 | -5.81~ | -5.63~ | -5.45~ | -7.35~ | - | unknown |
| `glm-4.5v` | -1.26 | -5.81 | -3.83~ | -4.78~ | -7.20 | 1.917 | yes |
| `glm-4.6` | -0.67 | -3.24 | -2.87~ | -3.92 | -5.69~ | 1.904 | no |
| `glm-4.6v` | -1.05 | -4.69 | -3.83~ | -5.35~ | -7.35 | 2.336 | yes |
| `glm-4.6v-flash` | -1.16 | -5.93~ | -5.64~ | -5.35~ | -7.35~ | - | unknown |
| `glm-4.7` | -0.53 | -3.12 | -2.49~ | -3.21 | -4.13~ | 3.785 | no |
| `glm-4.7-flash` | -1.16 | -5.93 | -4.62~ | -4.03 | -4.75~ | 0.46 | no |
| `glm-4.7-flashx` | -1.16 | -5.93~ | -4.62~ | -4.03~ | -4.75~ | - | unknown |
| `glm-5` | -0.40 | -1.96 | -2.95~ | -2.95 | -2.60~ | 3.399 | no |
| `glm-5.1` | -0.34 | -1.98 | -2.78~ | -2.38 | -2.32~ | 4.286 | no |
| `glm-5.2` | -0.34 | -2.13~ | -2.76~ | -1.93 | -1.55~ | 4.527 | no |
| `glm-5.3` | -0.34 | -1.89 | -1.86 | -1.43 | -0.77~ | 4.273 | no |
| `glm-5.3-flash` | -0.26 | -2.30 | -1.99~ | -1.58 | -1.87 | 1.139 | yes |
| `glm-5.3-flash-free` | -0.26 | -2.30 | -1.99~ | -1.58 | -1.87 | 1.139 | yes |
| `glm-5.3-flashx` | -0.26 | -2.30~ | -1.99~ | -1.58~ | -1.87~ | 2.837 | yes |
| `glm-5v-turbo` | -0.40 | -1.96~ | -2.95~ | -2.91 | -2.60~ | 30.538 | yes |
| `gpt-5.2` | -0.57 | -3.66 | -3.12~ | -4.18 | -2.06 | 9.046 | yes |
| `gpt-5.2-pro` | -0.57 | -3.66~ | -3.12~ | -4.18~ | missing! | - | yes |
| `gpt-5.4` | -0.26 | -2.14 | -2.56~ | -4.23 | -0.61 | 11.382 | yes |
| `gpt-5.4-mini` | -0.49 | -3.24 | -3.09~ | -4.26 | -2.09 | 8.602 | yes |
| `gpt-5.4-pro` | -0.26 | -2.14~ | -2.56~ | -4.23~ | -0.61~ | - | yes |
| `gpt-5.5` | -0.21 | -1.86 | -2.42~ | -2.17 | -1.05 | 24.62 | yes |
| `gpt-5.5-pro` | -0.21 | -1.86~ | -2.42~ | -2.17~ | -1.05~ | - | yes |
| `gpt-5.6-luna` | -0.64 | -3.03 | -2.75~ | -2.72 | -2.08 | 1.598 | yes |
| `gpt-5.6-sol` | -0.21 | -1.49 | -1.74~ | -0.72 | -1.21 | 24.5 | yes |
| `gpt-5.6-terra` | -0.21 | -2.84 | -2.80~ | -2.41 | -1.88 | 12.828 | yes |
| `gpt-6-astra` | 0.06 | -2.13 | 0.01u | -0.19u | -0.89 | 26.304 | yes |
| `gpt-6-luna` | -0.64 | -3.45 | -2.27u | -2.17 | -2.85u | 0.774 | yes |
| `gpt-6-pro` | 0.06 | 0.00u | 0.52f | 0.93f | -4.44u | - | yes |
| `gpt-6-sol` | -0.29 | -3.36u | -0.53u | -1.30 | -2.17u | 20.036 | yes |
| `gpt-6.1-sol` | -0.01 | -2.13 | -0.21u | -0.34 | -0.74 | 7.546 | yes |
| `gpt-6.1-terra` | -0.04 | -2.27~ | -0.47u | -1.25 | -0.57 | 5.412 | yes |
| `gpt-6.2-astra` | 0.16 | -1.42~ | 0.81~ | -0.10~ | -0.10 | 16.145 | yes |
| `gpt-6.2-sol` | 0.06 | -1.85~ | 0.33~ | -0.09~ | 0.07~ | 7.546 | yes |
| `gpt-oss-120b` | -1.27 | -6.67 | -5.73~ | -5.86 | -5.60~ | 8.211 | no |
| `gpt-oss-20b` | -1.54 | -7.72 | -5.73~ | -5.86~ | -5.60~ | - | no |
| `grok-4.20-0309-non-reasoning` | -0.53 | -3.67~ | -2.88~ | -4.94~ | -6.07~ | - | unknown |
| `grok-4.20-0309-reasoning` | -0.53 | -2.66~ | -2.88~ | -4.11~ | -2.34~ | - | unknown |
| `grok-4.20-multi-agent-0309` | -0.53 | -2.66~ | -2.88~ | -4.11~ | -2.34~ | - | unknown |
| `grok-4.3` | -0.53 | -2.66 | -2.88~ | -4.11 | -2.34 | 4.749 | yes |
| `grok-4.5` | -0.33 | -1.83 | -2.34~ | -2.08 | -1.23 | 7.508 | yes |
| `grok-4.6` | -0.41 | -2.09 | -2.15~ | -1.74 | -1.57 | 10.5 | yes |
| `grok-4.7` | -0.07 | -2.72 | -1.44 | -1.76 | -1.88~ | 10.449 | yes |
| `grok-4.7-build-fast` | -0.07 | -2.72~ | -1.44~ | -1.76~ | -1.88~ | - | unknown |
| `grok-bot` | 0.00 | 0.00~ | 0.00~ | 0.00~ | -1.16u | 28.0 | yes |
| `grok-build-0.1` | -0.37 | -2.41~ | -2.04~ | -2.45~ | -1.68~ | 4.387 | yes |
| `hy3` | -0.43 | -2.62 | -2.91~ | -2.54 | -1.94~ | 1.2 | no |
| `hy4` | -0.07 | -1.05~ | -0.87~ | -2.28 | -2.28~ | 2.26 | yes |
| `hy4-flash` | - | -1.40~ | -1.22~ | -2.63 | -2.28~ | 0.189 | yes |
| `hy4-preview` | -0.07 | -1.05~ | -1.85 | -2.12 | -2.28~ | 1.872 | no |
| `kimi-for-coding-highspeed` | -0.20 | -2.37~ | -2.83~ | -2.58~ | -1.45~ | - | unknown |
| `kimi-k2.6` | -0.37 | -2.37 | -2.85~ | -2.38 | -1.95 | 2.38 | yes |
| `kimi-k2.7-code` | -0.37 | -2.37~ | -2.83~ | -2.58 | -1.45~ | 2.651 | yes |
| `kimi-k2.8-preview` | -0.20 | -1.66~ | -2.34~ | -1.47~ | -0.92~ | - | unknown |
| `kimi-k3` | -0.02 | -1.89~ | -1.67~ | -0.36 | -1.78 | 5.813 | yes |
| `kimi-k3.1-pro` | -0.02 | -2.06~ | -1.41~ | -0.11 | -2.66 | 6.0 | yes |
| `kimi-k3.1-pro-highspeed` | -0.02 | -2.06~ | -1.41~ | -0.11~ | -1.49~ | - | unknown |
| `mimo-v2.5` | -0.60 | -3.47 | -2.88~ | -2.72 | -2.46~ | 0.188 | yes |
| `mimo-v2.5-pro` | -0.33 | -2.36 | -2.88~ | -2.58 | -1.28~ | 0.52 | no |
| `mimo-v2.6-flash-free` | -0.48 | -3.50 | -2.38~ | -1.72 | -2.64 | 0.281 | yes |
| `mimo-v2.6-pro` | -0.22 | -1.93 | -1.50 | -1.25 | -1.53 | 0.667 | yes |
| `mimo-v2.6-pro-ultraspeed` | -0.22 | -1.93~ | -1.50~ | -1.25~ | -1.53~ | 6.67 | yes |
| `minimax-m3` | -0.58 | -3.38 | -2.62 | -2.78 | -2.00 | 7.448 | yes |
| `minimax-m3.1-flash` | -0.48 | -2.89~ | -1.89~ | -1.51 | -1.88 | 1.556 | yes |
| `ministral-14b-2512` | - | -6.49~ | -6.49~ | -6.49~ | -10.11 | 0.798 | yes |
| `ministral-3b-2512` | - | -8.14~ | -8.14~ | -8.14~ | -13.40 | 0.399 | yes |
| `ministral-8b-2512` | - | -7.04~ | -7.04~ | -7.04~ | -11.19 | 0.598 | yes |
| `mistral-large-4` | -0.70 | -4.42 | -2.42~ | -2.48 | -2.10 | 3.0 | yes |
| `mistral-small-2603` | -0.70 | -3.84~ | -3.43~ | -3.72~ | -3.15~ | 0.665 | yes |
| `muse-ember` | -0.04 | -1.00~ | -1.85~ | -0.39 | -0.24~ | 2.769 | yes |
| `muse-spark-1.3` | -0.04 | -2.34~ | -1.95~ | -0.86~ | -1.00~ | 7.297 | yes |
| `muse-spark-open` | -0.04 | -1.00~ | -3.24~ | -1.76~ | -1.54~ | 8.232 | yes |
| `muse-wonder-1.0` | -0.04 | -1.39 | -1.35 | -0.72 | -0.57 | 19.412 | yes |
| `nemotron-3-ultra-free` | -0.64 | -3.57~ | -3.83~ | -3.74 | -2.87~ | 2.545 | unknown |
| `nemotron-3.5-lightning-free` | -0.99 | -5.08~ | -4.74~ | -5.75~ | -4.41~ | 3.952 | no |
| `nemotron-3.5-super-vl-free` | -0.64 | -3.57~ | -3.47~ | -4.42 | -2.87~ | 6.161 | yes |
| `qwen-max` | -0.30 | -3.12~ | -4.00~ | -3.02~ | -2.88~ | - | unknown |
| `qwen-plus` | -0.30 | -2.11~ | -1.84~ | -2.19~ | -1.38~ | 1.715 | no |
| `qwen3-coder-flash` | -0.90 | -6.03~ | -5.62~ | -6.71~ | -4.61~ | - | no |
| `qwen3-coder-next` | - | missing! | missing! | missing! | missing! | 6.334 | no |
| `qwen3-flash-2025-07-28` | -0.90 | -3.45u | -2.62u | -2.78u | -2.85u | - | unknown |
| `qwen3-omni-flash` | -0.90 | -5.01~ | -4.32~ | -5.88~ | -3.47~ | - | unknown |
| `qwen3-vl-plus` | -0.52 | -3.06~ | -2.45~ | -3.03~ | -2.34~ | - | unknown |
| `qwen3.5-122b-a10b` | -0.74 | -4.24 | -2.88~ | -4.65 | -2.57 | - | yes |
| `qwen3.5-27b` | -0.80 | -4.46 | -3.34~ | -4.68 | -2.62 | - | yes |
| `qwen3.5-35b-a3b` | -0.92 | -4.89 | -3.67~ | -5.78 | -3.70 | - | yes |
| `qwen3.5-397b-a17b` | -0.53 | -3.10 | -2.88~ | -3.45 | -2.01 | - | yes |
| `qwen3.5-flash` | -0.90 | -5.01 | -3.62~ | -5.88 | -3.47~ | - | unknown |
| `qwen3.5-plus` | -0.52 | -3.09~ | -2.45~ | -2.91~ | -2.01~ | - | unknown |
| `qwen3.6-27b` | -0.77 | -4.28~ | -2.88~ | -4.67~ | -3.15 | - | yes |
| `qwen3.6-35b-a3b` | -0.77 | -4.28~ | -2.88~ | -4.67~ | -3.03 | - | yes |
| `qwen3.6-flash` | -0.90 | -5.01~ | -3.25~ | -5.88~ | -3.68~ | - | yes |
| `qwen3.6-plus` | -0.52 | -3.09 | -2.88~ | -2.91 | -2.21 | 1.695 | yes |
| `qwen3.7-flash` | -0.60 | -4.41~ | -3.12~ | -2.23~ | -2.27~ | 0.208 | yes |
| `qwen3.7-max` | -0.42 | -2.40~ | -2.95~ | -1.96 | -1.37~ | 9.529 | no |
| `qwen3.7-plus` | -0.42 | -2.40 | -3.12~ | -2.13 | -1.37 | 2.204 | yes |
| `qwen3.8-27b` | -0.60 | -4.41 | -2.62 | -2.23 | -1.43 | 3.478 | yes |
| `qwen3.8-flash` | -0.60 | -4.41~ | -2.62~ | -2.23~ | -2.17~ | 0.367 | yes |
| `qwen3.8-max` | -0.19 | -1.27 | -2.04 | -1.45 | -2.17 | 5.299 | yes |
| `qwen3.8-omni-flash` | -0.60 | -4.41~ | -2.62~ | -2.23~ | -2.17~ | 0.367 | yes |
| `qwen4-max` | -0.04 | -0.63~ | -1.60~ | -0.71~ | -2.60~ | 5.478 | yes |
| `step-3.5-flash` | -0.93 | -4.83 | -3.70~ | -3.81~ | -2.95~ | 0.589 | unknown |
| `step-3.5-flash-2603` | -0.93 | -4.83~ | -3.70~ | -3.81~ | -2.95~ | 0.589 | unknown |
| `step-3.7-flash` | -0.93 | -4.83~ | -3.70~ | -3.81 | -2.95 | 1.254 | yes |
| `step-5-preview` | -0.48 | -2.92 | -2.23 | -2.42 | -2.13 | 3.894 | yes |
| `voxtral-small-2507` | - | missing! | missing! | missing! | missing! | - | unknown |

Tier is the arena.ai Overall position at High relative to the anchor (or its linear alignment from the Artificial Analysis Intelligence Index at High, or its same-series sibling tier); it is not a score and only estimates facets a model lacks when the panel regression has positive leave-one-out skill. A value marked `~` holds such an estimate (a same-series sibling, else an accepted fit of that facet on the tier); `u` marks a manual score (`user-scores.json`); `f` marks a maintainer score that its operating point bounds: the row is declared as another row at an operating point and the cell of that row there, above the score, is the value (`operating_point_floor` in the overlay); `!` marks a category with one or more missing facets (`tool_operation` keeps its level-2 responsiveness when `image_recognition` is missing; `coding` stays `missing!` so a missing facet is never silently skipped); `missing` excludes the model under mode B when a demanded level requires that facet. The record of each estimate is in `five-axis-scores.json` (`estimate`).

## Effective policy

Routes describe task scope and modality requirements and ship a calibrated harness order. A route can fix the harness order or imply a modality flag; it does not rank models. The allocator applies this effective policy (`candidate_ranking`, `task_intake`).

## Regeneration

Run `python -X utf8 skills/agent-compass/scripts/capability_catalog.py` from the repository root. Use `--check` to verify both generated views without writing them.
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