[kenjudy]

Summary

• Adds CFP_SYSTEM_PROMPT and analyzeCfpWithClaude(client, files) to lib/claude.js; counts Entry/Exit/Read/Write data movements from the PR diff and returns { estimated_cfp_delta, estimated_cfp_breakdown }
• Wires it into pr-metrics.yml: called after semantic duplicate analysis, gated on anthropicClient !== null
• Adds an "Estimated Functional Size (COSMIC-inspired approximation)" section to the PR comment when the result is non-null; section is omitted when key is absent or estimation fails
• Informational only: labeled as approximation, no calibrated target established

Test plan

• __tests__/claudeAnalysis.test.js -- 6 new tests for analyzeCfpWithClaude: happy path, null client, API error, malformed JSON, prompt content, markdown fence stripping
• __tests__/prMetricsCfp.test.js -- 3 new workflow-level tests: CFP section appears when client available, omitted when client null, omitted when function returns null
• All 815 existing tests continue to pass

🤖 Generated with Claude Code

[github-actions]

PR Analysis

Size: small (based on production code)
Production Code: 76 lines (2 files)
Test Code: 218 lines (2 files)
Total: 294 lines (4 files)
Test-to-Production Ratio: 2.87:1
No size or quality concerns.

Commit Analysis

Total Commits: 2
Average Commit Size: 38 production lines
Average Files per Commit: 2.0

Metric	Value
Large commits (>100 prod lines)	0/2 (0%)
Sprawling commits (>5 files)	0/2 (0%)
Test/prod co-change rate	2/2 (100%)
Message quality	2/2 (100%)
Median net additions ratio	0.98
Test-only commits	0
Production-only commits	0

Commit Details

a5d4d75 Ken Judy (8/31/2026)
test(#124): RED/GREEN analyzeCfpWithClaude — COSMIC FP estimation from PR diff
59 prod lines, 2 files [test+prod]

d09eb85 Ken Judy (8/31/2026)
feat(#124): wire analyzeCfpWithClaude into pr-metrics.yml PR comment
17 prod lines, 2 files [test+prod]

Test Coverage

Test-to-Production Ratio: 2.87:1 (no calibrated target for this ratio; reported descriptively)

DORA Capability Assessment

Archetype: harmonious-high-achiever
Strong batch discipline, test coverage, and message quality. AI tools likely amplifying positive outcomes.

Capability	Metric	Value	Target
Small Batches	Large commit %	0%	<18% (no critical band established)
Small Batches	Sprawling commit %	0%	<18% (no critical band established)
Version Control	Test/prod co-change rate	100%	>23% (no critical band established)
Version Control	Message quality	100%	no band, see spec
AI Risk Signal	Net additions ratio (median)	0.98	no band, see spec
Sample size (2 commits) is below the 5-commit convention for a rate verdict (code-quality-metrics-w9f): large-commit %, sprawling-commit % and test/prod co-change rate are reported below without a pass/fail judgement.
Automated by Code Metrics Workflow