Plugin Claude Code
19 software engineering skills from Code Complete, APOSD, GoF, and Clean Architecture, driving a research → plan → build workflow: per-phase gates (Full | Standard | Minimal) that set review timing rather than review existence, batched cross-phase review on a configurable cadence, Fable/Sonnet 5 model ladder with…
Instructions file
Claude Code instructions for ryanthedev/code-foundations, covering claude.md, project overview, architecture, skill families and directory structure.
Agent
Discovery, design, and implementation in one pass. Scopes phase work, makes design decisions, stubs the interface, implements it, then validates with tests.
Agent
Independent, execution-grounded review of a build phase against its done-when requirements. Runs the suite first, verifies each requirement with evidence and a trace, returns PASS or FAIL with specific findings.
Skill Claude CodeCodex
Placeholder skill directory required by skill-eval's runeval tool signature. This benchmark runs configurations=['withoutskill'] only — we are measuring raw model tiers, not a skill — so this file's content is never mounted or read by a subject session.
Skill Claude CodeCodex
Implements a coding task from a written spec with Done-When acceptance items. Use when given a spec to implement: stub the interface, implement it, then write tests that validate the Done-When items and any important behavior beyond them.
Skill Claude CodeCodex
Implements a coding task from a written spec with Done-When acceptance items. Use when given a spec to implement: for each Done-When item, write a failing test first, then the minimum code to make it pass (red-green).
Command
Execute an approved plan through gated phases (BUILD → REVIEW → commit) with subagent dispatch. Use when a plan exists in .code-foundations/plans/ and the user wants it implemented — phased implementation, per-phase quality gates, orchestrator commits, and a final trust report.
Command
Runs the scientific debugging method on an active bug — reproduce, locate, hypothesize, fix, verify, search for siblings. Use to chase a failing test, a flaky or intermittent failure, a crash, or any 'why is this broken' investigation, or to audit whether a debugging session was systematic.
Command
Turn a feature request or research doc into a phased, build-ready implementation plan. Use after research, or whenever a change needs decomposition into phases with skills, models, and gates before building.
Command
Extract and document what the user wants — even when they don't know yet. Use before plan, or standalone when exploring an idea.
Skill Claude CodeCodex
Guides module and API design using APOSD principles: generates multiple design alternatives, compares them on information hiding and interface depth, and produces a documented design decision. For creating new module/API design; not for assessing existing designs (use aposd-reviewing-module-design) or routine-level…
Skill Claude CodeCodex
Assesses existing module and interface design for complexity symptoms: information leakage, shallow interfaces, pass-through layers, and unknown unknowns. Produces a structured assessment — not transformations (use aposd-simplifying-complexity to edit) and not new-design generation (use aposd-designing-deep-modules).
Skill Claude CodeCodex
Transforms complex code by applying APOSD's pull-complexity-downward principle: resolves error hierarchies, collapses configuration, and moves caller-side logic into modules. Produces edited code; not for assessment-only review (use aposd-reviewing-module-design) or designing new modules from scratch (use…
Skill Claude CodeCodex
Verifies implementation completeness across functional correctness, error handling, concurrency, and security dimensions using APOSD's post-implementation checklist. Run after a coding task is nominally complete, not during active bug investigation (use cc-debugging).
Skill Claude CodeCodex
Applies Clean Architecture's dependency-direction and SRP-by-actor rules to system-level boundary design: separates business logic from infrastructure, identifies actor-coupling risks, and enforces inward-pointing dependency arrows. For system scope (multiple components, layers, or services), not routine or module…
Skill Claude CodeCodex
Audits and restructures control flow using Code Complete's nesting, cyclomatic complexity, loop design, guard-clause, and boolean simplification rules. Covers deep nesting, loop exit design, index naming, and callback chains. For statement-level flow inside a routine; not for routine/class structure (use…
Skill Claude CodeCodex
Applies Code Complete's scientific debugging method: STABILIZE → LOCATE → HYPOTHESIZE → EXPERIMENT → FIX → TEST → SEARCH. For active bug investigation, not QA process design or test coverage planning (use cc-quality-practices).
Skill Claude CodeCodex
Applies Code Complete's defensive programming rules: barricade design, assertion vs error-handling selection, input validation policy, and correctness-vs-robustness strategy for the current context. For hardening code at trust boundaries; not for diagnosing an active failure (use cc-debugging) or post-completion…
Skill Claude CodeCodex
Structures routine design through pseudocode-first iteration: clarifies naming and purpose before any code, catches design flaws cheaply, and prevents compile-debug loops on poorly understood routines. For designing a routine before writing it; not for assessing routines that already exist (use…
Skill Claude CodeCodex
Applies Code Complete's QA process design: selects defect-detection techniques by phase, sizes the test suite, and designs review and inspection processes. For QA planning and process design, not active bug investigation (use cc-debugging).
Skill Claude CodeCodex
Guides safe refactoring using Code Complete's fix-first-then-refactor discipline: decides between refactor, rewrite, and fix-first; enforces separate commits; applies small-change rigor to high-error-rate one-liners. Not for diagnosing the bug itself (use cc-debugging), transforming working code's complexity (use…
Skill Claude CodeCodex
Applies Code Complete's routine and class design rules at the routine level: cohesion classification, parameter-count thresholds, LSP inheritance verification, and containment-vs-inheritance decision. For routine and class scope, not system architecture (use ca-architecture-boundaries).
Skill Claude CodeCodex
Decomposes underspecified requests by classifying gaps (missing info, ambiguity, false premises) and generating targeted clarifying questions. Produces a confirmed problem statement before any implementation begins. For sharpening a request that already exists; not for open-ended requirement discovery from a vague…