@aryaminus/controlkeel-opencode 0.3.12 → 0.3.14

package/.opencode/skills/agent-pattern-verification/references/pattern-checklist.md

@@ -0,0 +1,501 @@
+# Agent Pattern Checklist
+
+Detailed patterns and examples for agent pattern verification checks.
+
+## Loop Safety Patterns
+
+### Python Patterns
+
+#### `while True` without break
+
+**Pattern:**
+```python
+# ❌ Issue - No break condition
+while True:
+    result = process()
+    if result.success:
+        return result
+    # Never breaks on failure - infinite loop
+```
+
+**Pattern:**
+```python
+# ✅ Pass - Has break condition
+while True:
+    result = process()
+    if result.success:
+        return result
+    if attempt_count >= MAX_ATTEMPTS:
+        break
+    attempt_count += 1
+```
+
+#### Recursive functions without base case
+
+**Pattern:**
+```python
+# ❌ Issue - No base case or depth limit
+def process_node(node):
+    for child in node.children:
+        process_node(child)
+```
+
+**Pattern:**
+```python
+# ✅ Pass - Has base case and depth limit
+def process_node(node, depth=0, max_depth=100):
+    if depth > max_depth:
+        return
+    for child in node.children:
+        process_node(child, depth + 1, max_depth)
+```
+
+### TypeScript/JavaScript Patterns
+
+#### `while (true)` without break
+
+**Pattern:**
+```typescript
+// ❌ Issue - No break condition
+while (true) {
+  const result = await process();
+  if (result.success) {
+    return result;
+  }
+  // Never breaks on failure
+}
+```
+
+**Pattern:**
+```typescript
+// ✅ Pass - Has break condition
+while (true) {
+  const result = await process();
+  if (result.success) {
+    return result;
+  }
+  if (attemptCount >= MAX_ATTEMPTS) {
+    break;
+  }
+  attemptCount++;
+}
+```
+
+### Go Patterns
+
+#### `for {}` without break
+
+**Pattern:**
+```go
+// ❌ Issue - No break or return
+for {
+    result := process()
+    if result.Success {
+        return result
+    }
+    // Never breaks on failure
+}
+```
+
+**Pattern:**
+```go
+// ✅ Pass - Has break condition
+for {
+    result := process()
+    if result.Success {
+        return result
+    }
+    if attemptCount >= maxAttempts {
+        break
+    }
+    attemptCount++
+}
+```
+
+## Retry Limit Patterns
+
+### Python - Tenacity
+
+**Pattern:**
+```python
+# ❌ Issue - No stop parameter
+@retry
+def api_call():
+    return requests.get(url)
+```
+
+**Pattern:**
+```python
+# ✅ Pass - Has stop parameter
+@retry(stop=stop_after_attempt(3))
+def api_call():
+    return requests.get(url)
+```
+
+### Python - Backoff
+
+**Pattern:**
+```python
+# ❌ Issue - No max_tries
+@backoff.on_exception(backoff.expo, requests.exceptions.RequestException)
+def api_call():
+    return requests.get(url)
+```
+
+**Pattern:**
+```python
+# ✅ Pass - Has max_tries
+@backoff.on_exception(backoff.expo, requests.exceptions.RequestException, max_tries=3)
+def api_call():
+    return requests.get(url)
+```
+
+### Python - urllib3
+
+**Pattern:**
+```python
+# ❌ Issue - No total parameter
+retry = urllib3.Retry()
+http = urllib3.PoolManager(retries=retry)
+```
+
+**Pattern:**
+```python
+# ✅ Pass - Has total parameter
+retry = urllib3.Retry(total=3)
+http = urllib3.PoolManager(retries=retry)
+```
+
+### JavaScript/TypeScript - async-retry
+
+**Pattern:**
+```typescript
+// ❌ Issue - No retries option
+const result = await retry(async () => {
+  return await apiCall();
+});
+```
+
+**Pattern:**
+```typescript
+// ✅ Pass - Has retries option
+const result = await retry(async () => {
+  return await apiCall();
+}, { retries: 3 });
+```
+
+### JavaScript/TypeScript - p-retry
+
+**Pattern:**
+```typescript
+// ❌ Issue - No retries option
+const result = await pRetry(async () => {
+  return await apiCall();
+});
+```
+
+**Pattern:**
+```typescript
+// ✅ Pass - Has retries option
+const result = await pRetry(async () => {
+  return await apiCall();
+}, { retries: 3 });
+```
+
+### Custom Retry Loops
+
+**Pattern:**
+```python
+# ❌ Issue - No counter
+while True:
+    try:
+        return api_call()
+    except Exception:
+        continue
+```
+
+**Pattern:**
+```python
+# ✅ Pass - Has counter with max check
+attempt = 0
+while attempt < MAX_RETRIES:
+    try:
+        return api_call()
+    except Exception:
+        attempt += 1
+        continue
+```
+
+## Tool Registry Patterns
+
+### Python - LangChain Decorator
+
+**Definition:**
+```python
+@tool
+def search_web(query: str) -> str:
+    """Search the web for information."""
+    return search_engine.search(query)
+```
+
+**Prompt reference:**
+```markdown
+You have access to the following tools:
+- search_web: Search the web for information
+```
+
+**Extracted name:** `search_web`
+
+### Python - OpenAI Function Schema
+
+**Definition:**
+```python
+tools = [{
+    "type": "function",
+    "function": {
+        "name": "get_weather",
+        "description": "Get current weather",
+        "parameters": {...}
+    }
+}]
+```
+
+**Prompt reference:**
+```markdown
+Available tools:
+- get_weather: Get current weather
+```
+
+**Extracted name:** `get_weather`
+
+### Python - LangGraph ToolNode
+
+**Definition:**
+```python
+from langgraph.prebuilt import ToolNode
+
+tools = [search_web, get_weather, calculate]
+tool_node = ToolNode(tools)
+```
+
+**Prompt reference:**
+```markdown
+You have access to: search_web, get_weather, calculate
+```
+
+**Extracted names:** `search_web`, `get_weather`, `calculate`
+
+### TypeScript - OpenAI Function Schema
+
+**Definition:**
+```typescript
+const tools = [{
+  type: "function",
+  function: {
+    name: "get_weather",
+    description: "Get current weather",
+    parameters: {...}
+  }
+}];
+```
+
+**Prompt reference:**
+```markdown
+Available tools:
+- get_weather: Get current weather
+```
+
+**Extracted name:** `get_weather`
+
+### Hallucinated Tool Example
+
+**Prompt reference:**
+```markdown
+You have access to:
+- execute_sql: Execute SQL queries
+- search_web: Search the web
+- analyze_data: Analyze data
+```
+
+**Tool definitions:**
+```python
+tools = [search_web, analyze_data]  # execute_sql not defined
+```
+
+**Finding:** ❌ Issue - Hallucinated tool `execute_sql` referenced in prompt but not defined
+
+### Undocumented Tool Example
+
+**Tool definitions:**
+```python
+tools = [search_web, get_weather, calculate]
+```
+
+**Prompt reference:**
+```markdown
+You have access to:
+- search_web: Search the web
+- get_weather: Get current weather
+```
+
+**Finding:** ⚠️ Warning - Tool `calculate` defined but not documented in prompt
+
+## Context Size Patterns
+
+### System Prompt Size
+
+**Pattern:**
+```python
+# Calculate token estimate
+system_prompt_content = open("system.md").read()
+token_estimate = len(system_prompt_content) / 4
+
+if token_estimate > 8000:
+    # ❌ Issue - System prompt too large
+    record_finding("system_prompt_too_large", severity="issue")
+elif token_estimate > 4000:
+    # ⚠️ Warning - System prompt approaching limit
+    record_finding("system_prompt_large", severity="warning")
+```
+
+### Tool Description Size
+
+**Pattern:**
+```python
+# Calculate single tool description size
+tool_description = tool_schema["description"]
+token_estimate = len(tool_description) / 4
+
+if token_estimate > 1000:
+    # ❌ Issue - Tool description too large
+    record_finding("tool_description_too_large", severity="issue")
+elif token_estimate > 500:
+    # ⚠️ Warning - Tool description large
+    record_finding("tool_description_large", severity="warning")
+```
+
+### Combined Tool Descriptions
+
+**Pattern:**
+```python
+# Calculate combined tool descriptions size
+total_tool_tokens = sum(
+    len(tool["description"]) / 4
+    for tool in tools
+)
+
+if total_tool_tokens > 4000:
+    # ❌ Issue - Combined tool descriptions too large
+    record_finding("combined_tool_descriptions_too_large", severity="issue")
+elif total_tool_tokens > 2000:
+    # ⚠️ Warning - Combined tool descriptions large
+    record_finding("combined_tool_descriptions_large", severity="warning")
+```
+
+## LangGraph Cycle Analysis
+
+### Infinite Cycle Detection
+
+**Pattern:**
+```python
+# ❌ Issue - Cycle with no path to END
+workflow = StateGraph(AgentState)
+workflow.add_node("agent", agent_node)
+workflow.add_node("tools", tool_node)
+
+# Creates cycle: agent -> tools -> agent
+workflow.add_edge("agent", "tools")
+workflow.add_edge("tools", "agent")
+
+# No path to END - infinite loop
+```
+
+**Finding:** ❌ Issue - Cycle exists between agent and tools with no path to END
+
+### Valid Cycle with Conditional Exit
+
+**Pattern:**
+```python
+# ✅ Pass - Cycle with conditional path to END
+workflow = StateGraph(AgentState)
+workflow.add_node("agent", agent_node)
+workflow.add_node("tools", tool_node)
+
+workflow.add_edge("agent", "tools")
+workflow.add_edge("tools", "agent")
+
+# Conditional edge can route to END
+workflow.add_conditional_edges(
+    "agent",
+    should_continue,
+    {
+        "continue": "tools",
+        "end": END
+    }
+)
+```
+
+### Dead-End Node Detection
+
+**Pattern:**
+```python
+# ⚠️ Warning - Node with no outgoing edges
+workflow = StateGraph(AgentState)
+workflow.add_node("agent", agent_node)
+workflow.add_node("tools", tool_node)
+workflow.add_node("cleanup", cleanup_node)
+
+workflow.add_edge("agent", "tools")
+workflow.add_edge("tools", "cleanup")
+# cleanup has no outgoing edges and is not END
+```
+
+**Finding:** ⚠️ Warning - Node `cleanup` has no outgoing edges and is not END
+
+## Framework Detection Patterns
+
+### LangGraph Detection
+
+**Python imports:**
+```python
+from langgraph.graph import StateGraph, END
+from langgraph.prebuilt import ToolNode
+```
+
+**Config files:**
+- `langgraph.json`
+
+### CrewAI Detection
+
+**Python imports:**
+```python
+from crewai import Agent, Task, Crew
+```
+
+**Config files:**
+- `crew.yaml`
+
+### AutoGen Detection
+
+**Python imports:**
+```python
+from autogen import AssistantAgent, UserProxyAgent
+```
+
+### LangChain Detection
+
+**Python imports:**
+```python
+from langchain.agents import AgentExecutor
+from langchain.tools import Tool
+```
+
+### Custom Agent Detection
+
+**Direct SDK usage:**
+```python
+import openai
+import anthropic
+```
+
+No framework-specific imports detected.

package/.opencode/skills/align/SKILL.md

@@ -11,6 +11,27 @@ compatibility:
   - copilot-plugin
   - github-repo
   - open-standard
+  - cline-native
+  - cursor-native
+  - windsurf-native
+  - continue-native
+  - letta-code-native
+  - pi-native
+  - roo-native
+  - goose-native
+  - opencode-native
+  - gemini-cli-native
+  - kiro-native
+  - kilo-native
+  - amp-native
+  - augment-native
+  - hermes-native
+  - multica-native
+  - openclaw-native
+  - devin-terminal-native
+  - warp-native
+  - droid-bundle
+  - forge-acp
 metadata:
   author: controlkeel
   version: "1.0"
@@ -37,9 +58,10 @@ Reach a **shared design concept** with the user before any plan or code is writt
    **Why** — What problem does this solve? What is the success signal?
    **Who** — Who uses the result? Which roles, systems, or integrations are affected?
    **Layers** — Which system layers does this touch? (schema, services, APIs, UI, infra, third-party) Record each touched layer explicitly — this drives vertical slice decomposition later.
-   **Acceptance criteria** — What does "done" look like? What would a failing test catch?
+   **Acceptance criteria** — What does "done" look like? What would a failing test catch? Reframe vague requirements into concrete, testable conditions.
    **Edge cases** — What breaks if inputs are invalid, empty, or unexpected?
    **Constraints** — Budget, timeline, tech stack limits, compliance requirements, or must-not-change areas.
+   **Assumptions** — What are you assuming about the environment, tech stack, data sources, or integrations? Surface these explicitly before proceeding.
    **Unknowns** — What do you not know yet? What needs a spike or research before implementation starts?
 
 5. After each resolved decision, call `ck_memory_record` with type `decision` to persist it. Future agents resuming this work will recover these without asking again.
@@ -58,7 +80,7 @@ Reach a **shared design concept** with the user before any plan or code is writt
 ## What you produce
 
 At the end of this skill:
-- A `ck_goal` record with: objective, acceptance criteria, touched layers, known constraints, open unknowns.
+- A `ck_goal` record with: objective, acceptance criteria, touched layers, known constraints, explicit assumptions, open unknowns.
 - One or more `ck_memory_record` entries (type: `decision`) for each resolved design choice.
 - A clear recommendation on whether to proceed to `plan-slice` or directly to `ck_review_submit`.
 

package/.opencode/skills/benchmark-operator/SKILL.md

@@ -11,6 +11,27 @@ compatibility:
   - copilot-plugin
   - github-repo
   - open-standard
+  - cline-native
+  - cursor-native
+  - windsurf-native
+  - continue-native
+  - letta-code-native
+  - pi-native
+  - roo-native
+  - goose-native
+  - opencode-native
+  - gemini-cli-native
+  - kiro-native
+  - kilo-native
+  - amp-native
+  - augment-native
+  - hermes-native
+  - multica-native
+  - openclaw-native
+  - devin-terminal-native
+  - warp-native
+  - droid-bundle
+  - forge-acp
 disable-model-invocation: true
 metadata:
   author: controlkeel

package/.opencode/skills/compliance-audit/SKILL.md

@@ -11,6 +11,27 @@ compatibility:
   - copilot-plugin
   - github-repo
   - open-standard
+  - cline-native
+  - cursor-native
+  - windsurf-native
+  - continue-native
+  - letta-code-native
+  - pi-native
+  - roo-native
+  - goose-native
+  - opencode-native
+  - gemini-cli-native
+  - kiro-native
+  - kilo-native
+  - amp-native
+  - augment-native
+  - hermes-native
+  - multica-native
+  - openclaw-native
+  - devin-terminal-native
+  - warp-native
+  - droid-bundle
+  - forge-acp
 metadata:
   author: controlkeel
   version: "2.0"

package/.opencode/skills/controlkeel-governance/SKILL.md

@@ -11,6 +11,27 @@ compatibility:
   - copilot-plugin
   - github-repo
   - open-standard
+  - cline-native
+  - cursor-native
+  - windsurf-native
+  - continue-native
+  - letta-code-native
+  - pi-native
+  - roo-native
+  - goose-native
+  - opencode-native
+  - gemini-cli-native
+  - kiro-native
+  - kilo-native
+  - amp-native
+  - augment-native
+  - hermes-native
+  - multica-native
+  - openclaw-native
+  - devin-terminal-native
+  - warp-native
+  - droid-bundle
+  - forge-acp
 allowed-tools:
   - ck_validate
   - ck_execute_code
@@ -53,7 +74,7 @@ You are operating inside a **ControlKeel-governed session**. Start here whenever
 
 ## Before new work
 
-For any new feature, fix, or project — before writing plans or code — use the `align` skill to reach shared understanding of the goal, layers, and acceptance criteria. Once aligned, use `plan-slice` to decompose the goal into vertical slices with explicit blocking relationships before any implementation begins. Planning is always human-in-the-loop; implementation of an approved slice can be AFK.
+For any new feature, fix, or project — before writing plans or code — use the `align` skill to reach shared understanding of the goal, layers, acceptance criteria, and **assumptions**. Surface assumptions explicitly before proceeding to prevent expensive misalignments caught after implementation. Once aligned, use `plan-slice` to decompose the goal into vertical slices with explicit blocking relationships and concrete success criteria before any implementation begins. Planning is always human-in-the-loop; implementation of an approved slice can be AFK.
 
 ## Core loop
 

package/.opencode/skills/cost-optimization/SKILL.md

@@ -11,6 +11,27 @@ compatibility:
   - copilot-plugin
   - github-repo
   - open-standard
+  - cline-native
+  - cursor-native
+  - windsurf-native
+  - continue-native
+  - letta-code-native
+  - pi-native
+  - roo-native
+  - goose-native
+  - opencode-native
+  - gemini-cli-native
+  - kiro-native
+  - kilo-native
+  - amp-native
+  - augment-native
+  - hermes-native
+  - multica-native
+  - openclaw-native
+  - devin-terminal-native
+  - warp-native
+  - droid-bundle
+  - forge-acp
 metadata:
   author: controlkeel
   version: "2.0"

package/.opencode/skills/domain-audit/SKILL.md

@@ -11,6 +11,27 @@ compatibility:
   - copilot-plugin
   - github-repo
   - open-standard
+  - cline-native
+  - cursor-native
+  - windsurf-native
+  - continue-native
+  - letta-code-native
+  - pi-native
+  - roo-native
+  - goose-native
+  - opencode-native
+  - gemini-cli-native
+  - kiro-native
+  - kilo-native
+  - amp-native
+  - augment-native
+  - hermes-native
+  - multica-native
+  - openclaw-native
+  - devin-terminal-native
+  - warp-native
+  - droid-bundle
+  - forge-acp
 metadata:
   author: controlkeel
   version: "2.0"

package/.opencode/skills/handoff/SKILL.md

@@ -11,6 +11,27 @@ compatibility:
   - copilot-plugin
   - github-repo
   - open-standard
+  - cline-native
+  - cursor-native
+  - windsurf-native
+  - continue-native
+  - letta-code-native
+  - pi-native
+  - roo-native
+  - goose-native
+  - opencode-native
+  - gemini-cli-native
+  - kiro-native
+  - kilo-native
+  - amp-native
+  - augment-native
+  - hermes-native
+  - multica-native
+  - openclaw-native
+  - devin-terminal-native
+  - warp-native
+  - droid-bundle
+  - forge-acp
 metadata:
   author: controlkeel
   version: "1.0"