From d155c0247e77ede29f87ae10d598c5ef0dd9b480 Mon Sep 17 00:00:00 2001
From: Markus Graf <info@markusgraf.ch>
Date: Mon, 14 Sep 2026 07:18:55 +0200
Subject: [PATCH] Add pi-zai-usage skill: query Z.ai GLM Coding Plan usage

---
 integrations/README.md                        |  3 ++
 integrations/pi-zai-usage/SKILL.md            | 16 ++++++
 .../pi-zai-usage/scripts/zai-usage.sh         | 54 +++++++++++++++++++
 3 files changed, 73 insertions(+)
 create mode 100644 integrations/README.md
 create mode 100644 integrations/pi-zai-usage/SKILL.md
 create mode 100755 integrations/pi-zai-usage/scripts/zai-usage.sh

diff --git a/integrations/README.md b/integrations/README.md
new file mode 100644
index 0000000..3e0c4ab
--- /dev/null
+++ b/integrations/README.md
@@ -0,0 +1,3 @@
+# Integration Skills Collection
+
+Skills that integrate external services and APIs with the Pi coding agent.
diff --git a/integrations/pi-zai-usage/SKILL.md b/integrations/pi-zai-usage/SKILL.md
new file mode 100644
index 0000000..2f288db
--- /dev/null
+++ b/integrations/pi-zai-usage/SKILL.md
@@ -0,0 +1,16 @@
+---
+name: zai-usage
+description: Query current Z.ai GLM Coding Plan quota and usage (5-hour/weekly credits, model tokens, MCP calls). Use when the user asks about their Z.ai usage, remaining credits, quota, or rate-limit status.
+---
+
+Run the script once and report the result:
+
+```bash
+bash ~/.pi/agent/skills/zai-usage/scripts/zai-usage.sh        # last 24h window
+bash ~/.pi/agent/skills/zai-usage/scripts/zai-usage.sh 168    # last 7 days
+```
+
+- Credentials come from `~/.pi/agent/auth.json` (`zai.key`) — never print the key.
+- Endpoints: `api.z.ai/api/monitor/usage/{model-usage,tool-usage,quota/limit}` (same as Z.ai's Claude Code plugin).
+- Present 5-hour and weekly credits (used/remaining/reset) plus model token totals in a small table.
+- If the key is missing, tell the user to run `/login zai` in pi first.
diff --git a/integrations/pi-zai-usage/scripts/zai-usage.sh b/integrations/pi-zai-usage/scripts/zai-usage.sh
new file mode 100755
index 0000000..1258e67
--- /dev/null
+++ b/integrations/pi-zai-usage/scripts/zai-usage.sh
@@ -0,0 +1,54 @@
+#!/usr/bin/env bash
+# Query Z.ai GLM Coding Plan usage (same endpoints as the Claude Code glm-plan-usage plugin).
+# Usage: zai-usage.sh [hours]   (default: 24h lookback window)
+set -euo pipefail
+
+HOURS="${1:-24}"
+AUTH_JSON="$HOME/.pi/agent/auth.json"
+KEY="$(python3 -c "import json;print(json.load(open('$AUTH_JSON'))['zai']['key'])")"
+BASE="https://api.z.ai/api/monitor/usage"
+
+NOW="$(date -u +'%Y-%m-%d %H:%M:%S')"
+START="$(date -u -d "$HOURS hours ago" +'%Y-%m-%d %H:%M:%S')"
+Q="startTime=$(python3 -c "import urllib.parse,sys;print(urllib.parse.quote(sys.argv[1]))" "$START")&endTime=$(python3 -c "import urllib.parse,sys;print(urllib.parse.quote(sys.argv[1]))" "$NOW")"
+
+fetch() { curl -sS -m 20 "$1" -H "Authorization: $KEY" -H 'Accept-Language: en-US'; }
+
+python3 - "$BASE" "$Q" <<'EOF'
+import json, subprocess, sys
+from datetime import datetime, timezone
+
+base, q = sys.argv[1], sys.argv[2]
+
+def fetch(path, params=""):
+    out = subprocess.run(["curl", "-sS", "-m", "20", f"{base}/{path}{params}",
+                          "-H", f"Authorization: {__import__('os').environ.get('KEY','')}"],
+                         capture_output=True, text=True, env={**__import__('os').environ}).stdout
+    return json.loads(out).get("data")
+
+# Quota / limits
+data = fetch("quota/limit")
+level = data.get("level", "?")
+print(f"Plan: {level.upper()}\n")
+for lim in data.get("limits", []):
+    if lim["type"] != "CREDIT_LIMIT":
+        continue
+    unit = "5-hour" if lim["unit"] == 3 else ("weekly" if lim["unit"] == 6 else f"unit{lim['unit']}")
+    reset = datetime.fromtimestamp(lim["nextResetTime"] / 1000, tz=timezone.utc)
+    delta = reset - datetime.now(timezone.utc)
+    hrs = int(delta.total_seconds() // 3600); mins = int(delta.total_seconds() % 3600 // 60)
+    when = f"in {hrs}h{mins:02d}m" if hrs else f"in {mins}m"
+    print(f"{unit:>7} credits: {lim['currentValue']:>6} / {lim['usage']} used ({lim['percentage']}%)"
+          f" — remaining {lim['remaining']}, resets {when}")
+
+# Model usage in window
+data = fetch("model-usage", f"?{q}")
+tot = data.get("totalUsage", {})
+print(f"\nLast window: {tot.get('totalModelCallCount', 0)} model calls")
+for m in tot.get("modelSummaryList", []):
+    print(f"  {m['modelName']}: {m['totalTokens']:,} tokens")
+
+tools = fetch("tool-usage", f"?{q}").get("totalUsage", {})
+ncalls = tools.get("totalNetworkSearchCount", 0) + tools.get("totalWebReadMcpCount", 0) + tools.get("totalZreadMcpCount", 0)
+print(f"MCP tool calls: {ncalls}")
+EOF