diff --git a/.config/opencode/RULES.md b/.config/opencode/RULES.md
new file mode 100644
index 0000000..c50c7b6
--- /dev/null
+++ b/.config/opencode/RULES.md
@@ -0,0 +1,16 @@
+# Response Tone
+
+1. **Accuracy over agreeableness:** Do not open with compliments, validation, or social pleasantries. Begin every response with the substance of the answer. Praise is noise; signal is the goal.
+2. **Default to skepticism:** Treat every user claim as potentially flawed until verified. If a statement is wrong, say so immediately and state the correction. Do not use hedging language like "You might want to consider...". Say "That is incorrect" and explain why.
+3. **Never apologize for correcting the user:** Corrections are the primary value. Phrases like "I'm sorry, but..." or "With all due respect..." are forbidden. State the correction directly.
+4. **Be blunt and argumentative when warranted:** If reasoning is unsound, challenge it. Name the flaw in the logic explicitly. You have standing permission to disagree and hold your position if reasoning is stronger.
+5. **Do not mirror the user's confidence:** Evaluate claims on merits alone. A confidently stated falsehood receives the same direct correction as a tentative one.
+6. **Distinguish certainty levels honestly:** When certain, be assertive. When genuinely ambiguous, say so plainly without manufacturing false uncertainty.
+
+# Style & Formatting Constraints
+
+1. **Code Comment Tone:** Keep all comments objective or imperative. It is strictly forbidden to use words like "we", "us", or any first-person plural personal pronouns in code comments or explanations.
+2. **No Emojis:** NEVER use emojis in code comments, `README.md` files, or any other Markdown documentation. Maintain a purely professional, text-only formatting style.
+
+# Git
+When asked, write professional Git commit messages for requested changes. NEVER add an AI co-author tag to commit messages.
diff --git a/.config/opencode/agents/glm-quota-exec.md b/.config/opencode/agents/glm-quota-exec.md
new file mode 100644
index 0000000..ec22519
--- /dev/null
+++ b/.config/opencode/agents/glm-quota-exec.md
@@ -0,0 +1,20 @@
+---
+description: Minimal executor for GLM quota tool
+mode: subagent
+hidden: true
+permission:
+  edit: deny
+  bash: deny
+---
+
+CRITICAL INSTRUCTION: When the glm_quota tool returns output, you MUST return it EXACTLY as received, character-for-character, with NO modifications.
+
+- Do NOT add introductory text
+- Do NOT summarize
+- Do NOT reformat
+- Do NOT explain anything
+- Do NOT add any commentary
+- Return ONLY the raw string from the tool
+
+Example of WRONG behavior: 'Here is your usage: [summary]'
+Example of CORRECT behavior: [paste entire tool output verbatim]
diff --git a/.config/opencode/command/glm_quota.md b/.config/opencode/command/glm_quota.md
new file mode 100644
index 0000000..409d3da
--- /dev/null
+++ b/.config/opencode/command/glm_quota.md
@@ -0,0 +1,5 @@
+---
+description: Execute GLM quota check
+agent: glm-quota-exec
+---
+Execute glm_quota tool and return its output EXACTLY as received without any modification or summarization.
diff --git a/.config/opencode/opencode.jsonc b/.config/opencode/opencode.jsonc
new file mode 100644
index 0000000..0ea6f3e
--- /dev/null
+++ b/.config/opencode/opencode.jsonc
@@ -0,0 +1,116 @@
+{
+    "$schema": "https://opencode.ai/config.json",
+    "permission": {
+        "bash": {
+            "*": "ask",
+            "git log *": "allow",
+            "git commit *": "ask",
+            "git status *": "allow",
+            "git diff *": "allow",
+            "git show *": "allow",
+            "git push *": "ask",
+            "sudo *": "deny",
+            "curl *": "ask",
+            "wget *": "ask",
+            "diff *": "allow",
+            "npm *": "allow",
+            "rm -rf *": "deny",
+            "rm *": "ask",
+            "grep *": "allow",
+            "sort *": "allow",
+            "head *": "allow",
+            "tail *": "allow",
+            "ls *": "allow",
+            "wc *": "allow",
+            "go build *": "allow",
+            "go test *": "allow",
+            "go vet *": "allow",
+            "go mod tidy": "allow",
+            "go mod download": "allow",
+            "dotnet *": "allow",
+            "docker ps *": "allow",
+            "docker logs *": "allow",
+            "docker compose logs *": "allow",
+        },
+        "read": {
+            ".env": "deny",
+            ".secrets": "deny",
+            "*.key": "deny",
+            "*.pem": "deny",
+            "id_rsa": "deny",
+            "id_ed25519": "deny",
+            ".aws/credentials": "deny",
+            "opencode.jsonc": "deny",
+            "~/.ssh/known_hosts": "allow",
+        },
+        "grep": "allow",
+        "glob": "allow",
+        "question": "allow",
+        "lsp": "allow",
+        "websearch": "allow",
+    },
+    "mcp": {
+        "zai-mcp-server": {
+            "type": "local",
+            "command": ["npx", "-y", "@z_ai/mcp-server"],
+            "environment": {
+                "Z_AI_API_KEY": "{env:ZAI_API_KEY}",
+                "Z_AI_MODE": "ZAI",
+            },
+        },
+        "web-search-prime": {
+            "type": "remote",
+            "url": "https://api.z.ai/api/mcp/web_search_prime/mcp",
+            "headers": {
+                "Authorization": "Bearer {env:ZAI_API_KEY}",
+            },
+        },
+        "web-reader": {
+            "type": "remote",
+            "url": "https://api.z.ai/api/mcp/web_reader/mcp",
+            "headers": {
+                "Authorization": "Bearer {env:ZAI_API_KEY}",
+            },
+        },
+        "zread": {
+            "type": "remote",
+            "url": "https://api.z.ai/api/mcp/zread/mcp",
+            "headers": {
+                "Authorization": "Bearer {env:ZAI_API_KEY}",
+            },
+        },
+        "ibmi-server": {
+            "type": "local",
+            "command": [
+                "npx",
+                "-y",
+                "@ibm/ibmi-mcp-server@latest",
+                "--tools",
+                "/home/colem/mcp/ibmi-mcp-server/tools/custom-tools.yaml",
+            ],
+            "enabled": true,
+            "environment": {
+                "DB2i_HOST": "{env:DB2i_HOST}",
+                "DB2i_USER": "{env:DB2i_USER}",
+                "DB2i_PASS": "{env:DB2i_PASS}",
+                "DB2i_PORT": "8076",
+                "DB2i_IGNORE_UNAUTHORIZED": "true",
+            },
+        },
+    },
+    "lsp": true,
+    "formatter": true,
+    "model": "zai-coding-plan/glm-5.2",
+    "small_model": "zai-coding-plan/glm-4.5-air",
+    "agent": {
+        "explore": {
+            "model": "zai-coding-plan/glm-4.5-air",
+        },
+        "scout": {
+            "model": "zai-coding-plan/glm-4.5-air",
+        },
+    },
+    "share": "disabled",
+    "snapshot": true,
+    "plugin": ["opencode-glm-quota"],
+}
diff --git a/.config/opencode/skills/glm-quota/SKILL.md b/.config/opencode/skills/glm-quota/SKILL.md
new file mode 100644
index 0000000..ae175da
--- /dev/null
+++ b/.config/opencode/skills/glm-quota/SKILL.md
@@ -0,0 +1,10 @@
+---
+name: glm-quota
+description: Query Z.ai GLM Coding Plan usage statistics including quota limits, model usage, and MCP tool usage
+parameters:
+  - name: detailed
+    type: boolean
+    optional: true
+    description: Show detailed usage breakdown
+---
+Query GLM quota usage including token limits and MCP tool usage.