Plumbline — a self-learning, customer-value-governed agile AI agent team for Claude Code. 87 subagents + skills, TDD defense-in-depth gates, Kaizen retros, a four-body adversarial council, and an empirically benchmarked QA harness. Does it hang true?
Latest release v0.25.0 · 23 Aug 2026
7 files for Claude Code: bench-watch, release-doctor, triage-impact, SessionStart and 3 more — 12,434 tokens loaded in every session.
CLAUDE.md B 12,434 tok .claude/settings.json A — .claude/settings.json A — .claude/skills/plumbline-measurement-slices/SKILL.md A 86 tok .claude/commands/bench-watch.md A 54 tok .claude/commands/release-doctor.md A 60 tok .claude/commands/triage-impact.md A 49 tok These files are DYAI2025/Plumbline's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.