Skip to content

akiiwa-games/AgentCompass / skills/agent-compass

agent-compass

Flagged

Choose owner, model and effort, outbound authorization, advisor use, and continuation for delegated work. Reads local usage and effective account policy, profiles the task with the configured System-One scorer, then allocates a compatible worker. Use for independent worker or advisor work; ordinary local execution needs no routing.

FileKindSize
SKILL.mdskill md5.5 KB
agents/openai.yamlconfig427 B
calibration/README.mdmarkdown55.2 KB
calibration/arena_capture.pyscript14.0 KB
calibration/community.pyscript25.2 KB
calibration/five_axis.pyscript196.4 KB
calibration/measurements.pyscript68.4 KB
calibration/refresh.pyscript48.6 KB
calibration/series.pyscript10.2 KB
calibration/sources.pyscript24.1 KB
calibration/tiers.pyscript14.6 KB
grok-bot/.gitignoreother47 B
grok-bot/dependency_patch.pyscript4.5 KB
grok-bot/install_cli.pyscript3.6 KB
grok-bot/test-recovery.mjsscript8.6 KB
grok-bot/test_install_cli.pyscript4.1 KB
grok-bot/upstream.jsonconfig3.4 KB
references/accounts.jsonconfig155.9 KB
references/classifier-cases.jsonconfig21.5 KB
references/dispatch-lifecycle.mdmarkdown28.9 KB
references/dispatch-rules.mdmarkdown11.3 KB
references/effort-matching.mdmarkdown5.1 KB
references/fast-modes.mdmarkdown3.5 KB
references/five-axis-scores.jsonconfig3.1 MB
references/gemini-decisions-api.mdmarkdown2.9 KB
references/grok-bot.mdmarkdown13.0 KB
references/herdr.mdmarkdown5.1 KB
references/jev-api.mdmarkdown1.6 KB
references/level-3-conversion.jsonconfig2.4 KB
references/model-capabilities.jsonconfig3.6 KB
references/model-capabilities.mdmarkdown14.6 KB
references/parent-address-gate.mdmarkdown10.1 KB
references/plan-templates.jsonconfig13.2 KB
references/provider-discovery.mdmarkdown11.5 KB
references/provider-usage.mdmarkdown4.1 KB
references/public-data.jsonconfig816 B
references/public-measurements.jsonconfig1.3 MB
references/roll-reference.mdmarkdown26.7 KB
references/router-internals.mdmarkdown93.7 KB
references/task-classifier.mdmarkdown6.1 KB
references/user-scores.jsonconfig6.8 KB
references/work-kinds.mdmarkdown4.7 KB
references/worker-communication.mdmarkdown2.1 KB
scripts/account_fleet.pyscript32.9 KB
scripts/account_state.pyscript22.2 KB
scripts/accounts_override.pyscript14.8 KB
scripts/allocator.pyscript19.8 KB
scripts/antigravity_plan.pyscript18.7 KB
scripts/antigravity_telemetry.pyscript5.1 KB
scripts/auto_bundles.pyscript31.3 KB
scripts/axis_scores.pyscript40.3 KB
scripts/caller_input.pyscript3.0 KB
scripts/candidate_eval.pyscript54.0 KB
scripts/candidate_ranking.pyscript9.5 KB
scripts/capability_catalog.pyscript8.0 KB
scripts/check_router_contract.pyscript2.8 KB
scripts/conftest.pyscript2.5 KB
scripts/cwd_policy.pyscript1.5 KB
scripts/data_age.pyscript1.5 KB
scripts/decision_ledger.pyscript18.9 KB
scripts/demo_plan.pyscript6.3 KB
scripts/dispatch_fallback.pyscript40.3 KB
scripts/dispatch_flow.pyscript58.7 KB
scripts/dispatch_ground_truth.pyscript43.5 KB
scripts/dispatch_registry.pyscript113.7 KB
scripts/entry.pyscript1.7 KB
scripts/env_vars.pyscript580 B
scripts/fast_modes.pyscript2.5 KB
scripts/fixtures/grok-api-responses.jsonconfig907 B
scripts/fixtures/reference-accounts.jsonconfig26.9 KB
scripts/grok_bot_paths.pyscript1005 B
scripts/host_herdr.pyscript16.8 KB
scripts/host_placement.pyscript9.4 KB
scripts/host_policy.pyscript10.1 KB
scripts/launch_failures.pyscript5.9 KB
scripts/launch_values.pyscript12.3 KB
scripts/ledger_snapshot.pyscript11.1 KB
scripts/live_models.pyscript21.1 KB
scripts/model_latch.pyscript7.6 KB
scripts/model_resolution.pyscript18.0 KB
scripts/override_store.pyscript2.2 KB
scripts/plan_state_residue.pyscript5.0 KB
scripts/provider_inventory.pyscript128.2 KB
scripts/provider_retry.pyscript34.6 KB
scripts/public_data.pyscript59.2 KB
scripts/quota_economy.pyscript38.0 KB
scripts/quota_exhaustion.pyscript5.9 KB
scripts/quota_overrides.pyscript25.6 KB
scripts/quota_pools.pyscript29.8 KB
scripts/reference_provenance.pyscript32.3 KB
scripts/released_names.pyscript3.8 KB
scripts/roll.pyscript106.3 KB
scripts/route_judge.pyscript83.4 KB
scripts/route_simulation.pyscript26.3 KB
scripts/router_test_support.pyscript6.7 KB
scripts/run_grok_bot.pyscript18.8 KB
scripts/scorer_client.pyscript55.2 KB
scripts/stage_help.pyscript5.8 KB
scripts/state_upgrade.pyscript24.0 KB
scripts/subscription_cli.pyscript3.6 KB
scripts/task_intake.pyscript33.6 KB
scripts/test_account_identity.pyscript7.1 KB
scripts/test_account_state.pyscript63.3 KB
scripts/test_accounts_override.pyscript30.1 KB
scripts/test_allocator.pyscript94.2 KB
scripts/test_antigravity_plan.pyscript13.2 KB
scripts/test_applicable_quota.pyscript9.1 KB
scripts/test_auto_bundles.pyscript10.8 KB
scripts/test_billing_routing_policy.pyscript9.9 KB
scripts/test_cadence_count.pyscript32.2 KB
scripts/test_calibration_units.pyscript27.0 KB
scripts/test_capability_catalog.pyscript5.0 KB
scripts/test_decision_ledger.pyscript8.5 KB
scripts/test_demo_plan.pyscript3.4 KB
scripts/test_derived_state.pyscript21.6 KB
scripts/test_dispatch.pyscript322.3 KB
scripts/test_dispatch_answers.pyscript14.8 KB
scripts/test_dispatch_fallback.pyscript53.2 KB
scripts/test_entry.pyscript1.6 KB
scripts/test_fast_modes.pyscript9.9 KB
scripts/test_five_axis.pyscript290.1 KB
scripts/test_five_axis_economy.pyscript105.0 KB
scripts/test_fleet_parity.pyscript15.6 KB
scripts/test_grok_bot.pyscript47.7 KB
scripts/test_ground_truth_recording.pyscript68.8 KB
scripts/test_herdr.pyscript14.1 KB
scripts/test_host_policy.pyscript24.6 KB
scripts/test_launch_values.pyscript8.0 KB
scripts/test_metered_usd.pyscript60.4 KB
scripts/test_model_resolution.pyscript9.2 KB
scripts/test_named_route_facts.pyscript28.6 KB
scripts/test_native_hosts.pyscript6.0 KB
scripts/test_new_user_fleet.pyscript3.3 KB
scripts/test_no_hardcode_classification.pyscript75.1 KB
scripts/test_no_legacy_scoring.pyscript6.5 KB
scripts/test_override_store.pyscript2.3 KB
scripts/test_plan_says_why.pyscript44.9 KB
scripts/test_provider_inventory.pyscript83.2 KB
scripts/test_provider_names.pyscript126.0 KB
scripts/test_provider_pools.pyscript14.2 KB
scripts/test_public_data.pyscript93.5 KB
scripts/test_quota_exhaustion.pyscript5.6 KB
scripts/test_rate_limit_windows.pyscript6.3 KB
scripts/test_record_says_why.pyscript26.5 KB
scripts/test_reference_provenance.pyscript16.7 KB
scripts/test_refresh_entry.pyscript110.7 KB
scripts/test_released_names.pyscript4.1 KB
scripts/test_reset_priority.pyscript4.8 KB
scripts/test_roll_answers.pyscript44.7 KB
scripts/test_roll_notifications.pyscript10.4 KB
scripts/test_route_judge.pyscript99.8 KB
scripts/test_route_simulation.pyscript7.0 KB
scripts/test_routing_parity.pyscript32.3 KB
scripts/test_routing_review.pyscript25.1 KB
scripts/test_setup_discovery_parity.pyscript9.5 KB
scripts/test_stage_help.pyscript2.0 KB
scripts/test_state_upgrade.pyscript13.8 KB
scripts/test_turn_refusal.pyscript16.7 KB
scripts/test_usage_cache.pyscript4.9 KB
scripts/test_usage_collector.pyscript21.4 KB
scripts/test_usage_core_claude_accounts.pyscript1.8 KB
scripts/test_usage_core_grok_cli_billing.pyscript15.6 KB
scripts/test_usage_core_magpie.pyscript5.4 KB
scripts/test_usage_core_magpie_pool.pyscript10.8 KB
scripts/test_usage_core_safety.pyscript24.4 KB
scripts/test_user_scores.pyscript102.3 KB
scripts/test_venice_usage.pyscript1.3 KB
scripts/test_window_scope.pyscript5.5 KB
scripts/turn_refusal.pyscript10.7 KB
scripts/usage_cache.pyscript4.7 KB
scripts/usage_collector.pyscript7.4 KB
scripts/usage_core.pyscript142.0 KB
scripts/usage_magpie.pyscript10.6 KB
scripts/usage_reading.pyscript17.1 KB
scripts/user_scores.pyscript72.8 KB
scripts/venice_usage.pyscript2.6 KB
scripts/window_scope.pyscript3.2 KB
scripts/worker_context.pyscript8.9 KB
scripts/worker_sessions.pyscript10.9 KB

scripts/usage_magpie.py

View on GitHub
"""Read subscription windows from a user's Magpie gateway, without local OAuth."""
from __future__ import annotations

import hashlib
import json
import math
from datetime import datetime
from dataclasses import dataclass
from pathlib import Path
from urllib.parse import urlsplit


@dataclass(frozen=True)
class Source:
    url: str
    token: str
    account: str
    provider: str = "claude"
    explicit: bool = True

    @property
    def valid(self):
        address = urlsplit(self.url)
        return (address.scheme == "https" and bool(address.hostname)
                and not address.username and not address.password
                and not address.query and not address.fragment
                and bool(self.token))

    @property
    def credential_key(self):
        return hashlib.sha256("\0".join(
            ("magpie", self.url, self.token, self.provider, self.account)
        ).encode()).hexdigest()


def read_source(home: Path, extra_env: dict[str, str] | None = None) -> Source | None:
    """Discover a Magpie gateway from usage-float.json, settings.json, or Paseo provider env."""
    try:
        config = json.loads((home / "usage-float.json").read_text(encoding="utf-8"))
        if not isinstance(config, dict):
            config = {}
    except (OSError, ValueError):
        config = {}
    try:
        settings = json.loads((home / "settings.json").read_text(encoding="utf-8"))
        if not isinstance(settings, dict):
            settings = {}
    except (OSError, ValueError):
        settings = {}
    if not config and isinstance(settings.get("usageFloat"), dict):
        config = settings["usageFloat"]
    source_kind = str(config.get("source") or "").strip().lower()
    if source_kind and source_kind != "magpie":
        return None
    env: dict[str, str] = {}
    if isinstance(extra_env, dict):
        for k, v in extra_env.items():
            if isinstance(v, str) and v.strip():
                env[k] = v.strip()
    if isinstance(settings.get("env"), dict):
        for k, v in settings["env"].items():
            if isinstance(v, str) and v.strip():
                env[k] = v.strip()
    url = str(env.get("ANTHROPIC_BASE_URL") or "").strip().rstrip("/")
    token = str(env.get("ANTHROPIC_AUTH_TOKEN") or env.get("ANTHROPIC_API_KEY") or "").strip()
    if not source_kind:
        address = urlsplit(url)
        host = (address.hostname or "").lower()
        if (address.scheme != "https" or not host
                or host in ("api.anthropic.com", "claude.ai", "platform.claude.com")
                or not token):
            return None
    return Source(
        url,
        token,
        str(config.get("account") or "").strip(),
        str(config.get("provider") or "claude").strip() or "claude",
        explicit=(source_kind == "magpie"),
    )


def _matches(payload, source: Source):
    pooled = source.account in ("", "*")
    return [q for q in payload["data"] if isinstance(q, dict)
            and q.get("provider") == source.provider
            and q.get("kind") == "subscription"
            and (pooled or q.get("user") == source.account or q.get("id") == source.account)]


def reread_targets(payload, source: Source, now: float, max_age: float, force: bool = False):
    """Accounts whose reading Magpie should take again (POST /v1/magpie/quotas/refresh?provider=&user=).

    Magpie reads a Claude account only when asked (a saved account only on its card's refresh), so a reading
    can be hours old; one older than max_age seconds, or every account when forced, is asked for again."""
    if not isinstance(payload, dict) or not isinstance(payload.get("data"), list):
        return []
    targets = []
    for quota in _matches(payload, source):
        user = quota.get("user") or quota.get("id")
        try:
            age = now - _timestamp(quota.get("readAt"))
        except ValueError:
            age = float("inf")
        if user and (force or age > max_age):
            targets.append((quota["provider"], user))
    return targets


GENERAL_WINDOWS = {"5 hours": ("five_hour", "5h"), "7 days": ("seven_day", "7d")}
SCOPED_WEEK_PREFIX = "7 days · "


def window_name(name):
    """(window id, label) for a Magpie window name, or None for one we do not show.

    "7 days · Fable" is the account's model-scoped week. It gets the id Claude's own usage API gives it
    (weekly_fable), so "<account>:fable" shows it like a direct Claude account's fable 7d row."""
    if not isinstance(name, str):
        return None
    if name in GENERAL_WINDOWS:
        return GENERAL_WINDOWS[name]
    if name.startswith(SCOPED_WEEK_PREFIX):
        model = name[len(SCOPED_WEEK_PREFIX):].strip()
        slug = "".join(model.lower().split())
        if slug.isalnum():
            return f"weekly_{slug}", f"{slug} 7d"
    return None


def parse_quota(payload, source: Source):
    """Read the configured account; with none (or '*'), every subscription account of the provider."""
    if not isinstance(payload, dict) or not isinstance(payload.get("data"), list):
        raise ValueError("Magpie 用量响应无效")
    pooled = source.account in ("", "*")
    matches = _matches(payload, source)
    if pooled and len(matches) > 1:
        return _parse_pool(matches, source)
    if len(matches) != 1:
        raise ValueError("Magpie 中未找到唯一匹配的订阅账户" if matches or not pooled else "Magpie 中未找到订阅账户")
    quota = matches[0]
    if quota.get("error") or not quota.get("readAt"):
        raise ValueError("VPS 暂未取得有效用量")
    windows = []
    for window in quota.get("windows") or []:
        named = window_name(window.get("name")) if isinstance(window, dict) else None
        if named is None:
            continue
        value = window.get("used")
        if isinstance(value, bool) or not isinstance(value, (int, float)) or not math.isfinite(value):
            raise ValueError("Magpie 用量窗口无效")
        window_id, label = named
        windows.append(dict(id=window_id, label=label, used_pct=float(value),
                            resets_at=window.get("resetsAt"),
                            **({"models": [window["name"][len(SCOPED_WEEK_PREFIX):].strip()]}
                               if window_id not in ("five_hour", "seven_day") else {})))
    if not windows:
        raise ValueError("Magpie 未返回订阅用量窗口")
    windows.sort(key=lambda w: w["id"] != "seven_day")
    return quota, windows


def _timestamp(value):
    try:
        parsed = datetime.fromisoformat(value.replace("Z", "+00:00"))
        if parsed.tzinfo is None:
            raise ValueError
        return parsed.timestamp()
    except (AttributeError, TypeError, ValueError):
        raise ValueError("Magpie 用量时间无效") from None


# Larger subscriptions first; the codex and claude ladders share the words they use (plus < pro < max 5x < max 20x).
PLAN_RANKS = (("20x", 5), ("max", 4), ("team", 3), ("enterprise", 3), ("business", 3), ("pro", 2), ("plus", 1))


def plan_rank(plan):
    label = str(plan or "").lower()
    return next((rank for word, rank in PLAN_RANKS if word in label), 0)


def _masked(identity):
    """An account as its hover line names it: 'k***@gmail.com', never the whole address."""
    name, at, domain = str(identity).partition("@")
    return f"{name[:1]}***{at}{domain}" if at else f"{name[:2]}***"


def _parse_pool(matches, source):
    """The largest plan's N accounts as one window set: mean usage, N accounts' worth (two fresh ones = 200%)."""
    members = []
    seen = set()
    for account in matches:
        identity = account.get("id") or account.get("user")
        if not identity or identity in seen:
            raise ValueError("Magpie 订阅账户标识缺失或重复")
        seen.add(identity)
        selected = Source(source.url, source.token, identity, source.provider)
        try:
            quota, windows = parse_quota({"data": [account]}, selected)
        except ValueError as error:
            if "暂未取得有效用量" in str(error):
                continue  # an unread account is left out; it is not counted as free capacity
            raise
        _timestamp(quota["readAt"])
        by_id = {w["id"]: w for w in windows}
        if len(by_id) != len(windows):
            raise ValueError("Magpie 用量窗口重复")
        if any(not 0 <= w["used_pct"] <= 100 for w in windows):
            raise ValueError("Magpie 用量窗口无效")
        for window in windows:
            if window["resets_at"]:
                _timestamp(window["resets_at"])
        members.append({"label": _masked(identity), "plan": quota.get("plan"), "read_at": quota["readAt"],
                        "windows": by_id})
    if not members:
        raise ValueError("VPS 暂未取得有效用量")
    top = max(plan_rank(m["plan"]) for m in members)
    largest = [m for m in members if plan_rank(m["plan"]) == top]
    count = len(largest)
    for member in members:
        member["counted"] = plan_rank(member["plan"]) == top  # smaller plans are listed, not added up
    general = {"five_hour", "seven_day"}
    if any(set(m["windows"]) & general != set(largest[0]["windows"]) & general for m in largest):
        raise ValueError("Magpie 账户池用量窗口不完整")
    # A model-scoped week (fable 7d) is pooled only when every counted account reports it; one an
    # account does not list is left out rather than counted as free capacity.
    ids = set.intersection(*(set(m["windows"]) for m in largest))
    suffix = f"×{count}" if count > 1 else ""
    combined = []
    for window_id in sorted(ids, key=lambda i: (i != "seven_day", i)):
        values = [m["windows"][window_id] for m in largest]
        # The latest reset is when every account has refilled; an earlier one refills only part of the pool.
        resets = [w["resets_at"] for w in values if w["resets_at"]]
        combined.append(dict(id=window_id, label=values[0]["label"] + suffix,
                             used_pct=sum(w["used_pct"] for w in values) / count,
                             resets_at=max(resets, key=_timestamp) if resets else None, accounts=count,
                             **({"models": values[0]["models"]} if values[0].get("models") else {})))
    fingerprint = hashlib.sha256("\0".join(sorted(seen)).encode()).hexdigest()
    plan = largest[0]["plan"] or "subscription"
    return {"readAt": min((m["read_at"] for m in largest), key=_timestamp),
            "plan": f"{plan} ×{count}" if count > 1 else plan,
            "usage_details": {"kind": "magpie_pool", "aggregation": "plan_sum",
                              "account_count": len(members), "plan_count": count, "pool_key": fingerprint,
                              "members": members}}, combined
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