agent-self-evaluation

Topics in the source

• Agent Self-Evaluation
• When to Activate
• Core Concepts
• The 5 Evaluation Axes
• Scoring Scale
• The Evidence Rule
• Workflow
• Step 1: Collect the Raw Material

After completing a complex task, the agent pauses to rate its own output against a structured 5-axis rubric. This is NOT a pass/fail gate — it's a deliberate reflection step that catches omissions, flags overconfidence, and surface areas for improvement before the user has to. After writing code that spans 3+ files or 50+ lines After completing a multi-step workflow (implement → test → review) After a debugging session that involved 3+ attempts After producing a design document, architecture decision, or written analysis When the user asks "how good was that?" or "rate yourself" At the end of any session Stop hook (if configured — see references/hook-integration.md) | Axis | Question | What it catches | |---|---|---| | Accuracy | Are the facts, claims, and outputs correct? | Hallucinations, wrong API names, incorrect syntax, false statements | | Completeness | Did it cover everything the user asked for? | Missed edge cases, unhandled error paths, forgotten requirements, skipped subtasks | | Clarity | Is the explanation understandable and well-structured? | Confusing explanations, jargon without definition, missing context, rambling | | Actionability | Can the user act on the output

This is an excerpt. Refer to the complete source and its current requirements.