diff --git a/.opencode/command/openagents/new-agents/create-agent.md b/.opencode/command/openagents/new-agents/create-agent.md
index 89e2877..ad61057 100644
--- a/.opencode/command/openagents/new-agents/create-agent.md
+++ b/.opencode/command/openagents/new-agents/create-agent.md
@@ -424,7 +424,7 @@ Create a new agent with minimal, high-signal prompts following "right altitude"
 <anti_patterns>
   **Don't**:
   - Create sub-agents for dependent tasks (code is sequential)
-  - Pre-load entire codebase into context (use just-in-time retrieval)
+  - Preload entire codebase into context (use just-in-time retrieval)
   - Write exhaustive edge case lists in prompts (brittle, hard to maintain)
   - Give vague tool descriptions (major failure mode)
   - Use multi-agent if you could use single agent + tools
diff --git a/.opencode/context/development/react-patterns.md b/.opencode/context/development/react-patterns.md
index f0eb3a7..a0b154b 100644
--- a/.opencode/context/development/react-patterns.md
+++ b/.opencode/context/development/react-patterns.md
@@ -319,7 +319,7 @@ function VirtualList({ items }) {
 - ❌ **Using index as key** - Use stable, unique identifiers
 - ❌ **Unnecessary useEffect** - Derive state when possible
 - ❌ **Ignoring ESLint warnings** - React hooks rules prevent bugs
-- ❌ **Not memoizing context values** - Causes unnecessary re-renders
+- ❌ **Not memorizing context values** - Causes unnecessary re-renders
 
 ## References
 
diff --git a/.opencode/context/product/README.md b/.opencode/context/product/README.md
index 7f3e8c3..cfe11e6 100644
--- a/.opencode/context/product/README.md
+++ b/.opencode/context/product/README.md
@@ -15,4 +15,4 @@ This directory contains context files for product management, strategy, and user
 
 ## Usage
 
-These context files will be referenced by product-focused agents to ensure consistent product strategy, user research methodologies, and data-driven decision making.
+These context files will be referenced by product-focused agents to ensure consistent product strategy, user research methodologies, and data-driven decision-making.
diff --git a/.opencode/prompts/development/backend-specialist/README.md b/.opencode/prompts/development/backend-specialist/README.md
index 0dc3680..41a110f 100644
--- a/.opencode/prompts/development/backend-specialist/README.md
+++ b/.opencode/prompts/development/backend-specialist/README.md
@@ -1,4 +1,4 @@
-# uackend specialist Prompt Variants
+# backend specialist Prompt Variants
 
 ## Default Prompt
 
diff --git a/dev/ai-tools/opencode/cheatsheet-context-symbols.md b/dev/ai-tools/opencode/cheatsheet-context-symbols.md
index 49aa4a8..e45bd10 100644
--- a/dev/ai-tools/opencode/cheatsheet-context-symbols.md
+++ b/dev/ai-tools/opencode/cheatsheet-context-symbols.md
@@ -555,7 +555,7 @@ Reference these when setting up tools or CI/CD:
 
 1. **Simple commands**: Use `run_terminal_cmd`
 2. **Complex workflows**: Create shell scripts first
-3. **Multi-step tasks**: Use sub-agents with `task` tool
+3. **Multistep tasks**: Use sub-agents with `task` tool
 
 ---
 
diff --git a/docs/contributing/ADDING_EVALUATOR.md b/docs/contributing/ADDING_EVALUATOR.md
index b4bfb28..373e0a9 100644
--- a/docs/contributing/ADDING_EVALUATOR.md
+++ b/docs/contributing/ADDING_EVALUATOR.md
@@ -258,7 +258,7 @@ cd evals/framework
 npm run eval:sdk -- --agent=openagent --pattern="10-execution-balance/*.yaml" --debug
 ```
 
-If you want add more metricts to dashboard, add the meta (`ratio`, `readBeforeExec`) in your external metrics reports system.
+If you want to add more metrics to dashboard, add the meta (`ratio`, `readBeforeExec`) in your external metrics reports system.
 
 ---
 **End of the guide.**
diff --git a/evals/framework/LLM_INTEGRATION_VALIDATION.md b/evals/framework/LLM_INTEGRATION_VALIDATION.md
index 52d3345..28cf085 100644
--- a/evals/framework/LLM_INTEGRATION_VALIDATION.md
+++ b/evals/framework/LLM_INTEGRATION_VALIDATION.md
@@ -330,7 +330,7 @@ No mocking at the integration level.
 
 1. ❌ **Deterministic LLM behavior** - LLMs are non-deterministic
 2. ❌ **Forced violations** - Can't reliably make LLMs violate standards
-3. ❌ **100% test stability** - LLM tests may occasionally timeout
+3. ❌ **100% test stability** - LLM tests may occasionally time out
 
 ### Mitigation Strategies