aiblueprint-cli 1.4.59 → 1.4.60

package/agents-config/skills/{subagent-creator → agents-managers}/references/context-management.md

@@ -1,4 +1,4 @@
-# Context Management for Subagents
+# Context Management for Agents
 
 <core_problem>
 
@@ -8,7 +8,7 @@
 <stateless_nature>
 LLMs are stateless by default. Each invocation starts fresh with no memory of previous interactions.
 
-**For subagents, this means**:
+**For agents, this means**:
 - Long-running tasks lose context between tool calls
 - Repeated information wastes tokens
 - Important decisions from earlier in workflow forgotten
@@ -192,7 +192,7 @@ Retrieval trigger:
 <context_switch_detection>
 Monitor for topic changes:
 - User switches from "fix bug" to "add feature"
-- Subagent transitions from "analysis" to "implementation"
+- Agent transitions from "analysis" to "implementation"
 - Task scope changes mid-execution
 
 On context switch:
@@ -308,7 +308,7 @@ Summary format:
 - Vector store memory
 - Entity extraction
 
-**Use case**: Building subagents that need sophisticated memory without manual implementation.
+**Use case**: Building agents that need sophisticated memory without manual implementation.
 </langchain>
 
 <llamaindex>
@@ -319,7 +319,7 @@ Summary format:
 - Automatic chunking and indexing
 - Retrieval augmentation
 
-**Use case**: Subagents working with large codebases, documentation, or extensive conversation history.
+**Use case**: Agents working with large codebases, documentation, or extensive conversation history.
 </llamaindex>
 
 <file_based>
@@ -331,11 +331,11 @@ Summary format:
   core-facts.md          # Essential project information
   decisions.md           # Key decisions and rationale
   patterns.md            # Discovered patterns and conventions
-  {subagent}-state.json  # Subagent-specific state
+  {agent}-state.json  # Agent-specific state
 </memory_structure>
 
 <usage>
-Subagent reads relevant files at start, updates during execution, summarizes at end.
+Agent reads relevant files at start, updates during execution, summarizes at end.
 </usage>
 ```
 
@@ -343,11 +343,11 @@ Subagent reads relevant files at start, updates during execution, summarizes at
 </file_based>
 </framework_support>
 
-<subagent_patterns>
+<agent_patterns>
 
 
-<stateful_subagent>
-**For long-running or frequently-invoked subagents**:
+<stateful_agent>
+**For long-running or frequently-invoked agents**:
 
 ```markdown
 ---
@@ -375,10 +375,10 @@ State file structure:
 - Active concerns (issues to address)
 </memory_management>
 ```
-</stateful_subagent>
+</stateful_agent>
 
-<stateless_subagent>
-**For simple, focused subagents**:
+<stateless_agent>
+**For simple, focused agents**:
 
 ```markdown
 ---
@@ -401,12 +401,12 @@ You are a syntax validator. Check code for syntax errors.
 ```
 
 **When to use stateless**: Single-purpose validators, formatters, simple transformations.
-</stateless_subagent>
+</stateless_agent>
 
 <context_inheritance>
 **Inheriting context from main chat**:
 
-Subagents automatically have access to:
+Agents automatically have access to:
 - User's original request
 - Any context provided in invocation
 
@@ -414,13 +414,13 @@ Subagents automatically have access to:
 Main chat: "Review the authentication changes for security issues.
            Context: We recently switched from JWT to session-based auth."
 
-Subagent receives:
+Agent receives:
 - Task: Review authentication changes
 - Context: Recent switch from JWT to session-based auth
 - This context informs review focus without explicit memory management
 ```
 </context_inheritance>
-</subagent_patterns>
+</agent_patterns>
 
 <anti_patterns>
 
@@ -535,13 +535,13 @@ Use context for:
 <prompt_caching_interaction>
 
 
-Prompt caching (see [subagents.md](subagents.md#prompt_caching)) works best with stable context.
+Prompt caching (see [agents.md](agents.md#prompt_caching)) works best with stable context.
 
 <cache_friendly_context>
 **Structure context for caching**:
 
 ```markdown
-[CACHEABLE: Stable subagent instructions]
+[CACHEABLE: Stable agent instructions]
 <role>...</role>
 <focus_areas>...</focus_areas>
 <workflow>...</workflow>
@@ -558,7 +558,7 @@ Recent context: ...
 
 <cache_invalidation>
 **When context changes invalidate cache**:
-- Subagent prompt updated
+- Agent prompt updated
 - Core memory structure changed
 - Context reorganization
 

package/agents-config/skills/{subagent-creator → agents-managers}/references/debugging-agents.md

@@ -1,4 +1,4 @@
-# Debugging and Troubleshooting Subagents
+# Debugging and Troubleshooting Agents
 
 <core_challenges>
 
@@ -23,7 +23,7 @@ Impact: Behavior no single agent was designed to exhibit, hard to predict or dia
 </emergent_behaviors>
 
 <black_box_execution>
-**Subagents run in isolated contexts**.
+**Agents run in isolated contexts**.
 
 User sees final output, not intermediate steps. Makes diagnosis harder.
 
@@ -51,9 +51,9 @@ Common issues:
 
 <what_to_log>
 Essential logging:
-- **Input prompts**: Full subagent prompt + user request
+- **Input prompts**: Full agent prompt + user request
 - **Tool calls**: Which tools called, parameters, results
-- **Outputs**: Final subagent response
+- **Outputs**: Final agent response
 - **Metadata**: Timestamps, model version, token usage, latency
 - **Errors**: Exceptions, tool failures, timeouts
 - **Decisions**: Key choice points in workflow
@@ -63,7 +63,7 @@ Format:
 {
   "invocation_id": "inv_20251115_abc123",
   "timestamp": "2025-11-15T14:23:01Z",
-  "subagent": "security-reviewer",
+  "agent": "security-reviewer",
   "model": "claude-sonnet-4-5",
   "input": {
     "task": "Review auth.ts for security issues",
@@ -137,8 +137,8 @@ Session: workflow-20251115-abc
 <tracing_implementation>
 Generate correlation ID for each workflow:
 - Workflow ID: unique identifier for entire user request
-- Subagent ID: workflow_id + agent name + sequence number
-- Tool ID: subagent_id + tool name + sequence number
+- Agent ID: workflow_id + agent name + sequence number
+- Tool ID: agent_id + tool name + sequence number
 
 Log all events with correlation IDs for end-to-end reconstruction.
 </tracing_implementation>
@@ -181,17 +181,17 @@ Events:
 ```markdown
 ---
 name: output-validator
-description: Validates subagent outputs for correctness, completeness, and format compliance
+description: Validates agent outputs for correctness, completeness, and format compliance
 tools: Read
 model: haiku
 ---
 
 <role>
-You are a validation specialist. Check subagent outputs for quality issues.
+You are a validation specialist. Check agent outputs for quality issues.
 </role>
 
 <validation_checks>
-For each subagent output:
+For each agent output:
 1. **Format compliance**: Matches expected schema
 2. **Completeness**: All required fields present
 3. **Consistency**: No internal contradictions
@@ -241,7 +241,7 @@ Validation result:
 **Mitigation**:
 ```markdown
 <anti_hallucination>
-In subagent prompt:
+In agent prompt:
 - "Only reference files you've actually read"
 - "If unsure, say so explicitly rather than guessing"
 - "Cite specific line numbers for code references"
@@ -313,7 +313,7 @@ Before returning output:
 </prompt_injection>
 
 <workflow_incompleteness>
-**Subagent skips steps or produces partial output**.
+**Agent skips steps or produces partial output**.
 
 **Symptoms**:
 - Missing expected components
@@ -383,11 +383,11 @@ Before using a tool, ask:
 
 
 <systematic_diagnosis>
-**When subagent fails or produces unexpected output**:
+**When agent fails or produces unexpected output**:
 
 <step_1>
 **1. Reproduce the issue**
-- Invoke subagent with same inputs
+- Invoke agent with same inputs
 - Document whether failure is consistent or intermittent
 - If intermittent, run 5-10 times to identify frequency
 </step_1>
@@ -435,7 +435,7 @@ Before using a tool, ask:
 <step_7>
 **7. Test hypothesis**
 - Make targeted change to prompt/input
-- Re-run subagent
+- Re-run agent
 - Observe if behavior changes as predicted
 </step_7>
 
@@ -452,11 +452,11 @@ Before using a tool, ask:
 
 - [ ] Is the failure consistent or intermittent?
 - [ ] Does the error message indicate the problem clearly?
-- [ ] Was there a recent change to the subagent prompt?
+- [ ] Was there a recent change to the agent prompt?
 - [ ] Does the issue occur with all inputs or specific ones?
 - [ ] Are logs available for the failed execution?
-- [ ] Has this subagent worked correctly in the past?
-- [ ] Are other subagents experiencing similar issues?
+- [ ] Has this agent worked correctly in the past?
+- [ ] Are other agents experiencing similar issues?
 </quick_diagnostic_checklist>
 </diagnostic_procedures>
 
@@ -464,7 +464,7 @@ Before using a tool, ask:
 
 
 <issue_specificity>
-**Problem**: Subagent too generic, produces vague outputs.
+**Problem**: Agent too generic, produces vague outputs.
 
 **Diagnosis**: Role definition lacks specificity, focus areas too broad.
 
@@ -482,7 +482,7 @@ Focus on OWASP Top 10, authentication flaws, and data exposure risks.
 </issue_specificity>
 
 <issue_context>
-**Problem**: Subagent makes incorrect assumptions or misses important info.
+**Problem**: Agent makes incorrect assumptions or misses important info.
 
 **Diagnosis**: Context failure - relevant information not in prompt or context window.
 
@@ -493,7 +493,7 @@ Focus on OWASP Top 10, authentication flaws, and data exposure risks.
 </issue_context>
 
 <issue_workflow>
-**Problem**: Subagent inconsistently follows process or skips steps.
+**Problem**: Agent inconsistently follows process or skips steps.
 
 **Diagnosis**: Workflow not explicit enough, no verification step.
 
@@ -545,7 +545,7 @@ Validate output matches this structure before returning.
 </issue_output>
 
 <issue_constraints>
-**Problem**: Subagent does things it shouldn't (modifies wrong files, runs dangerous commands).
+**Problem**: Agent does things it shouldn't (modifies wrong files, runs dangerous commands).
 
 **Diagnosis**: Constraints missing or too vague.
 
@@ -564,14 +564,14 @@ Use strong modal verbs (ONLY, NEVER, ALWAYS) for critical constraints.
 </issue_constraints>
 
 <issue_tools>
-**Problem**: Subagent uses wrong tools or uses tools inefficiently.
+**Problem**: Agent uses wrong tools or uses tools inefficiently.
 
 **Diagnosis**: Tool access too broad or tool usage guidance missing.
 
 **Fix**:
 ```markdown
 <tool_access>
-This subagent is read-only and should only use:
+This agent is read-only and should only use:
 - Read: View file contents
 - Grep: Search for patterns
 - Glob: Find files
@@ -603,7 +603,7 @@ Efficient tool usage:
 </anti_pattern>
 
 <anti_pattern name="no_logging">
-❌ Running subagents with no logging, then wondering why they failed
+❌ Running agents with no logging, then wondering why they failed
 
 **Fix**: Comprehensive logging is non-negotiable. Can't debug what you can't observe.
 </anti_pattern>
@@ -680,7 +680,7 @@ Efficient tool usage:
 - Success rate over time (trend line)
 - Error type breakdown (pie chart)
 - Latency distribution (histogram)
-- Token usage by subagent (bar chart)
+- Token usage by agent (bar chart)
 - Top 10 failure causes (ranked list)
 - Invocation volume (time series)
 </dashboards>
@@ -709,6 +709,6 @@ Efficient tool usage:
 - Add common issues to anti-patterns section
 - Update best practices based on real-world usage
 - Create troubleshooting guides for frequent problems
-- Share insights across subagents (similar fixes often apply)
+- Share insights across agents (similar fixes often apply)
 </knowledge_capture>
 </continuous_improvement>

package/agents-config/skills/{subagent-creator → agents-managers}/references/error-handling-and-recovery.md

@@ -1,4 +1,4 @@
-# Error Handling and Recovery for Subagents
+# Error Handling and Recovery for Agents
 
 <common_failure_modes>
 
@@ -6,7 +6,7 @@
 Industry research identifies these failure patterns:
 
 <specification_problems>
-**32% of failures**: Subagents don't know what to do.
+**32% of failures**: Agents don't know what to do.
 
 **Causes**:
 - Vague or incomplete role definition
@@ -14,7 +14,7 @@ Industry research identifies these failure patterns:
 - Unclear success criteria
 - Ambiguous constraints
 
-**Symptoms**: Subagent asks clarifying questions (can't if it's a subagent), makes incorrect assumptions, produces partial outputs, or fails to complete task.
+**Symptoms**: Agent asks clarifying questions (can't if it's a agent), makes incorrect assumptions, produces partial outputs, or fails to complete task.
 
 **Prevention**: Explicit `<role>`, `<workflow>`, `<focus_areas>`, and `<output_format>` sections in prompt.
 </specification_problems>
@@ -23,7 +23,7 @@ Industry research identifies these failure patterns:
 **28% of failures**: Coordination breakdowns in multi-agent workflows.
 
 **Causes**:
-- Subagents have conflicting objectives
+- Agents have conflicting objectives
 - Handoff points unclear
 - No shared context or state
 - Assumptions about other agents' outputs
@@ -40,15 +40,15 @@ Industry research identifies these failure patterns:
 - No validation step in workflow
 - Missing output format specification
 - No error detection logic
-- Blind trust in subagent outputs
+- Blind trust in agent outputs
 
 **Symptoms**: Incorrect results silently propagated, hallucinations undetected, format errors break downstream processes.
 
-**Prevention**: Include verification steps in subagent workflows, validate outputs before use, implement evaluator agents.
+**Prevention**: Include verification steps in agent workflows, validate outputs before use, implement evaluator agents.
 </verification_gaps>
 
 <error_cascading>
-**Critical pattern**: Failures in one subagent propagate to others.
+**Critical pattern**: Failures in one agent propagate to others.
 
 **Causes**:
 - No error handling in downstream agents
@@ -57,7 +57,7 @@ Industry research identifies these failure patterns:
 
 **Symptoms**: Single failure causes entire workflow to fail.
 
-**Prevention**: Defensive programming in subagent prompts, graceful degradation strategies, validation at boundaries.
+**Prevention**: Defensive programming in agent prompts, graceful degradation strategies, validation at boundaries.
 </error_cascading>
 
 <non_determinism>
@@ -103,7 +103,7 @@ Industry research identifies these failure patterns:
 </graceful_degradation>
 
 <autonomous_retry>
-**Pattern**: Subagent retries failed operations with exponential backoff.
+**Pattern**: Agent retries failed operations with exponential backoff.
 
 <example>
 ```markdown
@@ -140,7 +140,7 @@ If API endpoint has failed 5 consecutive times:
 </circuit_breaker_logic>
 ```
 
-**Application to subagents**: Include in prompt when subagent calls external APIs or services.
+**Application to agents**: Include in prompt when agent calls external APIs or services.
 
 **Benefit**: Prevents wasting time/tokens on operations known to be failing.
 </conceptual_example>
@@ -162,7 +162,7 @@ For long-running operations:
 </timeout_handling>
 ```
 
-**Note**: Claude Code has built-in timeouts for tool calls. Subagent prompts should include guidance on what to do when operations approach reasonable time limits.
+**Note**: Claude Code has built-in timeouts for tool calls. Agent prompts should include guidance on what to do when operations approach reasonable time limits.
 </implementation>
 </timeouts>
 
@@ -204,7 +204,7 @@ Know when to escalate rather than thrashing.
 </escalation_workflow>
 ```
 
-**Key insight**: Subagents should recognize their limitations and provide useful handoff information.
+**Key insight**: Agents should recognize their limitations and provide useful handoff information.
 </example>
 </reassigning_tasks>
 </recovery_strategies>
@@ -304,7 +304,7 @@ Before returning output:
 ```markdown
 Invocation ID: abc-123-def
 Timestamp: 2025-11-15T14:23:01Z
-Subagent: security-reviewer
+Agent: security-reviewer
 Model: sonnet-4.5
 Input: "Review changes in commit a3f2b1c"
 Tool calls:
@@ -365,13 +365,13 @@ Main chat [abc123]:
 ```markdown
 ---
 name: output-validator
-description: Validates subagent outputs against expected schemas and quality criteria. Use after any subagent produces structured output.
+description: Validates agent outputs against expected schemas and quality criteria. Use after any agent produces structured output.
 tools: Read
 model: haiku
 ---
 
 <role>
-You are an output validation specialist. Check subagent outputs for:
+You are an output validation specialist. Check agent outputs for:
 - Schema compliance
 - Completeness
 - Internal consistency
@@ -379,7 +379,7 @@ You are an output validation specialist. Check subagent outputs for:
 </role>
 
 <workflow>
-1. Receive subagent output and expected schema
+1. Receive agent output and expected schema
 2. Validate structure matches schema
 3. Check for required fields
 4. Verify value constraints (enums, formats, ranges)
@@ -403,7 +403,7 @@ Partial: Minor issues that don't prevent use - flag warnings
 
 
 <anti_pattern name="silent_failures">
-❌ Subagent fails but doesn't indicate failure in output
+❌ Agent fails but doesn't indicate failure in output
 
 **Example**:
 ```markdown
@@ -416,7 +416,7 @@ Output: "No issues found" (incomplete review, but looks successful)
 </anti_pattern>
 
 <anti_pattern name="no_fallback">
-❌ When ideal path fails, subagent gives up entirely
+❌ When ideal path fails, agent gives up entirely
 
 **Example**:
 ```markdown
@@ -474,7 +474,7 @@ Total workflow failure from single upstream error
 <recovery_checklist>
 
 
-Include these patterns in subagent prompts:
+Include these patterns in agent prompts:
 
 **Error detection**:
 - [ ] Validate inputs before processing

package/agents-config/skills/{subagent-creator → agents-managers}/references/evaluation-and-testing.md

@@ -1,4 +1,4 @@
-# Evaluation and Testing for Subagents
+# Evaluation and Testing for Agents
 
 <evaluation_framework>
 
@@ -7,15 +7,15 @@
 **Primary metric**: Proportion of tasks completed correctly and satisfactorily.
 
 Measure:
-- Did the subagent complete the requested task?
+- Did the agent complete the requested task?
 - Did it produce the expected output?
 - Would a human consider the task "done"?
 
-**Testing approach**: Create test cases with known expected outcomes, invoke subagent, compare results.
+**Testing approach**: Create test cases with known expected outcomes, invoke agent, compare results.
 </task_completion>
 
 <tool_correctness>
-**Secondary metric**: Whether subagent calls correct tools for given task.
+**Secondary metric**: Whether agent calls correct tools for given task.
 
 Measure:
 - Are tool selections appropriate for the task?
@@ -26,7 +26,7 @@ Measure:
 </tool_correctness>
 
 <output_quality>
-**Quality metric**: Assess quality of subagent-generated outputs.
+**Quality metric**: Assess quality of agent-generated outputs.
 
 Measure:
 - Accuracy of analysis
@@ -38,7 +38,7 @@ Measure:
 </output_quality>
 
 <robustness>
-**Resilience metric**: How well subagent handles failures and edge cases.
+**Resilience metric**: How well agent handles failures and edge cases.
 
 Measure:
 - Graceful handling of missing files
@@ -81,7 +81,7 @@ Evaluate the security review output on a 1-5 scale:
 Think step-by-step about which vulnerabilities were checked and which were missed.
 ```
 
-**Implementation**: Pass subagent output and criteria to Claude, get structured evaluation.
+**Implementation**: Pass agent output and criteria to Claude, get structured evaluation.
 </example>
 
 **When to use**: Complex quality metrics that can't be measured programmatically (thoroughness, insight quality, appropriateness of recommendations).
@@ -99,11 +99,11 @@ Think step-by-step about which vulnerabilities were checked and which were misse
    - Edge cases (boundary conditions, unusual inputs)
    - Error conditions (missing data, tool failures)
    - Adversarial inputs (malformed, malicious)
-2. Invoke subagent with each test case
+2. Invoke agent with each test case
 3. Compare outputs to expected results
 4. Document failures and iterate on prompt
 
-**Example test suite for code-reviewer subagent**:
+**Example test suite for code-reviewer agent**:
 ```markdown
 Test 1 (Happy path): Recent commit with SQL injection vulnerability
 Expected: Identifies SQL injection, provides fix, rates as Critical
@@ -120,7 +120,7 @@ Expected: Identifies pattern despite obfuscation
 </offline_testing>
 
 <simulation>
-**Simulation testing**: Run subagent in realistic but controlled environments.
+**Simulation testing**: Run agent in realistic but controlled environments.
 
 **Use cases**:
 - Testing against historical issues (can it find bugs that were previously fixed?)
@@ -147,7 +147,7 @@ Expected: Identifies pattern despite obfuscation
 <evaluation_driven_development>
 
 
-**Philosophy**: Integrate evaluation throughout subagent lifecycle, not just at validation stage.
+**Philosophy**: Integrate evaluation throughout agent lifecycle, not just at validation stage.
 
 <workflow>
 1. **Initial creation**: Define success criteria before writing prompt
@@ -158,16 +158,16 @@ Expected: Identifies pattern despite obfuscation
 6. **Continuous**: Ongoing evaluation → feedback → refinement cycles
 </workflow>
 
-**Anti-pattern**: Writing subagent, deploying, never measuring effectiveness or iterating.
+**Anti-pattern**: Writing agent, deploying, never measuring effectiveness or iterating.
 
-**Best practice**: Treat subagent prompts as living documents that evolve based on real-world performance data.
+**Best practice**: Treat agent prompts as living documents that evolve based on real-world performance data.
 </evaluation_driven_development>
 
 <testing_checklist>
 
 
 <before_deployment>
-Before deploying a subagent, complete this validation:
+Before deploying a agent, complete this validation:
 
 **Basic functionality**:
 - [ ] Invoke with representative task, verify completion
@@ -219,11 +219,11 @@ Synthetic data generation useful for:
 ```markdown
 Persona: Junior developer
 Task: "Fix the bug where the login page crashes"
-Expected behavior: Subagent provides detailed debugging steps
+Expected behavior: Agent provides detailed debugging steps
 
 Persona: Senior engineer
 Task: "Investigate authentication flow security"
-Expected behavior: Subagent performs deep security analysis
+Expected behavior: Agent performs deep security analysis
 ```
 
 **Scenario simulation**: Generate variations of common scenarios.
@@ -255,14 +255,14 @@ Maintain a validation set of real usage examples. Synthetic data can miss:
 
 
 <basic_pattern>
-Use LLM to evaluate subagent outputs when human review is impractical at scale.
+Use LLM to evaluate agent outputs when human review is impractical at scale.
 
 **Example evaluation prompt**:
 ```markdown
-You are evaluating a security code review performed by an AI subagent.
+You are evaluating a security code review performed by an AI agent.
 
 Review output:
-{subagent_output}
+{agent_output}
 
 Code that was reviewed:
 {code}
@@ -288,8 +288,8 @@ Expected vulnerabilities in test code:
 2. XSS vulnerability on line 67
 3. Missing authentication check on line 103
 
-Subagent identified:
-{subagent_findings}
+Agent identified:
+{agent_findings}
 
 Calculate:
 - Precision: % of identified issues that are real
@@ -305,15 +305,15 @@ Calculate:
 Anthropic guidance: "Test-driven development becomes even more powerful with agentic coding."
 
 <approach>
-**Before writing subagent prompt**:
+**Before writing agent prompt**:
 1. Define expected input/output pairs
-2. Create test cases that subagent must pass
+2. Create test cases that agent must pass
 3. Write initial prompt
 4. Run tests, observe failures
 5. Refine prompt based on failures
 6. Repeat until all tests pass
 
-**Example for test-writer subagent**:
+**Example for test-writer agent**:
 ```markdown
 Test 1:
 Input: Function that adds two numbers
@@ -331,7 +331,7 @@ Expected output: Test file with:
   - Mocked HTTP calls (no real API calls)
 ```
 
-**Invoke subagent → check if outputs match expectations → iterate on prompt.**
+**Invoke agent → check if outputs match expectations → iterate on prompt.**
 </approach>
 
 **Benefit**: Clear acceptance criteria before development, objective measure of prompt quality.
@@ -341,9 +341,9 @@ Expected output: Test file with:
 
 
 <anti_pattern name="no_testing">
-❌ Deploying subagents without any validation
+❌ Deploying agents without any validation
 
-**Risk**: Subagent fails on real tasks, wastes user time, damages trust.
+**Risk**: Agent fails on real tasks, wastes user time, damages trust.
 
 **Fix**: Minimum viable testing = invoke with 3 representative tasks before deploying.
 </anti_pattern>
@@ -351,7 +351,7 @@ Expected output: Test file with:
 <anti_pattern name="only_happy_path">
 ❌ Testing only ideal scenarios
 
-**Risk**: Subagent fails on edge cases, error conditions, or unusual (but valid) inputs.
+**Risk**: Agent fails on edge cases, error conditions, or unusual (but valid) inputs.
 
 **Fix**: Test matrix covering happy path, edge cases, and error conditions.
 </anti_pattern>
@@ -367,7 +367,7 @@ Expected output: Test file with:
 <anti_pattern name="test_once_deploy_forever">
 ❌ Testing once at creation, never revisiting
 
-**Risk**: Subagent degrades over time as usage patterns shift, codebases change, or models update.
+**Risk**: Agent degrades over time as usage patterns shift, codebases change, or models update.
 
 **Fix**: Periodic re-evaluation with current usage patterns and edge cases.
 </anti_pattern>