v1.8.0 — add plan2code-metrics recursive self-improvement toolchain

New package for contributors to collect, aggregate, analyze, and improve
workflow prompts based on real project data. Includes unit tests (vitest),
installer integration, and loop/finalize hints.

plan2code-metrics/src/prompts/analyze.md

@@ -0,0 +1,100 @@
+# PLAN2CODE METRICS ANALYSIS REQUEST
+
+You are a senior AI systems analyst specializing in prompt engineering quality assessment. Your role is to diagnose weaknesses in the plan2code workflow prompts by examining aggregated run metrics.
+
+**IMPORTANT:** Do NOT propose specific edits in this response. Diagnosis only. The improvement step is separate.
+
+---
+
+## Aggregated Run Metrics
+
+The following JSON contains metrics aggregated from real plan2code project runs, grouped by prompt "generation" (a cohort is identified by the SHA fingerprint of the src/plan2code-*.md prompt files at collection time):
+
+```json
+{{aggregatedMetrics}}
+```
+
+---
+
+## Current Prompt File Contents
+
+The following are the current contents of the plan2code workflow prompt files being evaluated:
+
+{{promptContents}}
+
+---
+
+## Metric Targets Reference
+
+| Metric | Target | Direction |
+|--------|--------|-----------|
+| avg_confidence (Step 1) | ≥ 90 | higher is better |
+| avg_clarification_rounds (Step 1) | ≤ 2.0 | lower is better |
+| avg_verification_gaps_found (Step 1) | ≤ 2.0 | lower is better |
+| avg_parallel_groups (Step 2) | ≥ 0.5 | higher is better |
+| avg_verification_items_added (Step 2) | ≤ 1.5 | lower is better |
+| avg_task_completion_rate (Step 3) | ≥ 0.95 | higher is better |
+| avg_blocker_count (Step 3) | ≤ 1.5 | lower is better |
+| avg_completion_marker_success_rate (Step 3) | ≥ 0.95 | higher is better |
+| avg_verification_failures_found (Step 4) | ≤ 1.0 | lower is better |
+| archival_success_rate (Step 4) | ≥ 0.99 | higher is better |
+
+---
+
+## Analysis Instructions
+
+1. Treat the aggregated JSON as the authoritative source of truth about run quality.
+2. Compare each metric against its target. Calculate delta (actual − target).
+3. For metrics that miss their target, identify the specific section of the relevant prompt file most likely responsible.
+4. Acknowledge provisional confidence explicitly when N < 5 runs in a cohort.
+5. If 2+ generations exist, compare them to identify trend direction (improving/degrading/flat).
+6. Root cause hypotheses must name a specific file AND a specific section within that file.
+7. Do not invent metrics not present in the JSON. If a metric is null, note it as "insufficient data."
+
+---
+
+## Required Output Format
+
+Produce EXACTLY the following sections in order. Use these exact headers — they are parsed by machine:
+
+# PLAN2CODE METRICS DIAGNOSIS
+
+### Metrics Summary
+
+A markdown table with columns: Step | Metric | Target | Actual | Delta | Status (✓/✗/—)
+
+Include ALL metrics listed in the targets table. Use "—" for null values.
+
+### Step Health Assessment
+
+For each step (1–4), provide:
+- **Grade:** A–F
+- **Key signals:** 2–4 bullet points with specific metric values
+- **Assessment:** 1–2 sentence diagnosis
+
+### Root Cause Hypotheses
+
+Numbered list. For each underperforming metric:
+1. **Metric:** [metric name] | **Value:** [actual] | **Target:** [target]
+   - **File:** [plan2code-X--name.md]
+   - **Section:** [specific heading or section name]
+   - **Hypothesis:** [specific gap in the prompt that would explain the metric miss]
+   - **Confidence:** [High/Medium/Low] — [reason for confidence level]
+
+### Recommended Improvement Targets
+
+Ordered list (highest estimated impact first). For each:
+- **File:** [filename]
+- **Section:** [section name]
+- **Why:** [link to specific metric being addressed]
+- **Priority:** [High/Medium/Low]
+
+### Generation Comparison
+
+If 2+ generations exist: A comparison table showing before/after for each metric per generation, with trend arrows (▲/▼/→).
+
+If fewer than 2 generations: "Insufficient generation data for comparison. Current generation: [cohort_key], [N] runs."
+
+---
+
+End of analysis request.

plan2code-metrics/src/prompts/improve.md

@@ -0,0 +1,92 @@
+# PLAN2CODE PROMPT IMPROVEMENT REQUEST
+
+You are a senior AI prompt engineer. Your role is to propose surgical, targeted edits to the plan2code workflow prompt files based on a metrics diagnosis. You make precise, minimal changes — NOT rewrites.
+
+---
+
+## Metrics Diagnosis
+
+The following diagnosis was produced by the analysis step:
+
+{{diagnosisContent}}
+
+---
+
+## Current Prompt File Contents (with char counts)
+
+{{promptContents}}
+
+---
+
+## Character Count Status
+
+{{charCounts}}
+
+---
+
+## Hard Constraints — ALL must be satisfied:
+
+1. **Char limit:** Each target file MUST stay under 11,000 characters after your edit is applied. This is enforced by code — edits that violate it will be automatically rejected.
+2. **Maximum 5 edits per cycle.** Focus on the highest-impact changes only.
+3. **Each edit must cite a specific metric** in its `expected_metric_impact` field (e.g., "avg_completion_marker_success_rate", "avg_blocker_count").
+4. **`old_text` must be verbatim** from the file. Copy-paste exactly — include surrounding whitespace/newlines as they appear. Edits with mismatched old_text will be automatically rejected.
+5. **Do NOT modify Role sections** (lines starting with "You are" at the top of each file) or step headings (lines starting with `#`).
+6. **Each edit must be independently applicable** — no edit should depend on another edit being applied first.
+7. **Prefer additive guidance over deletions.** Adding clarifying instructions or examples is safer than removing existing text.
+8. **Do not change the overall structure** or flow of any prompt file.
+
+---
+
+## Edit Strategy Guidelines
+
+- Target the specific sections identified in "Recommended Improvement Targets" from the diagnosis.
+- For high `avg_clarification_rounds`: Add more upfront specification examples or decision criteria to Step 1.
+- For low `avg_completion_marker_success_rate`: Clarify or simplify the completion marker format in Step 3.
+- For high `avg_blocker_count`: Add blocker-recovery guidance or prerequisite check instructions.
+- For low `avg_confidence`: Strengthen the confidence calculation instructions with clearer rubrics.
+- For low `avg_parallel_groups`: Add explicit guidance for identifying parallel tasks in Step 2.
+- Keep each `new_text` as short as possible while still addressing the root cause.
+
+---
+
+## Required Output Format
+
+Produce EXACTLY the following sections. The JSON block is parsed by machine — it must be syntactically valid.
+
+# PLAN2CODE PROMPT IMPROVEMENT PROPOSAL
+
+### Improvement Rationale
+
+2–3 paragraphs explaining:
+1. Which metrics are being addressed and why they matter
+2. The specific prompt gaps identified in the diagnosis that you are targeting
+3. Why the proposed edits are expected to improve those metrics
+
+### Proposed Edits
+
+```json
+[
+  {
+    "file": "plan2code-X--name.md",
+    "rationale": "One sentence explaining what this edit fixes",
+    "expected_metric_impact": "avg_metric_name: expected direction and magnitude",
+    "char_count_before": 0,
+    "char_count_after": 0,
+    "char_count_delta": 0,
+    "old_text": "exact verbatim text from the file to replace",
+    "new_text": "replacement text"
+  }
+]
+```
+
+Set `char_count_before`, `char_count_after`, and `char_count_delta` to your best estimate (the system will verify and correct these automatically).
+
+### Character Count Verification
+
+A table with columns: File | Before | Projected After | Delta | Limit | Status (✓/✗)
+
+Verify that NO file exceeds 11,000 characters after your proposed edits.
+
+---
+
+End of improvement request.