Plumbline

Agent skills that check code against A Philosophy of Software Design. Like a builder's plumb line, each skill gives your agent a simple, concrete test for whether the design is still standing straight, during implementation and review.

v1.8.0 · GitHub · Releases · All install options

Install in Claude Code

/plugin marketplace add tomymaritano/plumbline
/plugin install plumbline@plumbline-plugins

Also for Codex, Cursor, Grok Build, OpenCode, Copilot CLI, Kimi, Pi and any Agent Skills host via npx skills add tomymaritano/plumbline --skill '*'.

Structure & Modules

deep-modules Module depth, shallow modules, classitis, pass-through methods, interface vs implementation module-boundaries Merge vs split, conjoined methods, method splitting, dependency minimization information-hiding Information leakage, temporal decomposition, partial hiding, false encapsulation, git co-change evidence pull-complexity-down Caller burden, configuration parameters, the core asymmetry

Abstraction & Generality

abstraction-quality Genuine vs false abstractions, layer boundaries, decorators general-vs-special Interface generality, special-general mixture, edge-case elimination error-design Define errors out of existence, exception masking, aggregation, just crash

Clarity & Communication

naming-obviousness Isolation test, scope-length principle, consistency, avoid extra words comments-docs Comment types, comments-first workflow, cross-module documentation

Process & Evolution

strategic-mindset Strategic vs tactical, investment rule, tactical tornado design-it-twice Generate alternatives, compare on criteria, synthesize code-evolution "Designed this way" standard, repetition, technical debt; reviews a branch or PR straight from git diff complexity-recognition Change amplification, cognitive load, unknown unknowns

Diagnostic

red-flags 18-flag design smell scan covering structure, boundaries (including adapters that re-implement the core's vocabulary), documentation, naming, and process. Separates real problems from documented trade-offs, has a reading strategy for large multi-package targets, and ships Python, TypeScript, Rust and Go guides design-review Structured review funnel from complexity triage through structural, interface, and surface checks diagnose Routes a vague symptom or complaint to the most relevant skill via a decision tree apply-fixes Applies a report's findings one fix at a time, running the tests after each and reverting any fix that breaks them; flags fixes no test covers, asks before changing a public interface, and can commit each fix separately