plugin

Decompose a use case into ordered, independently-executable slices. Owns the slice file format — one Markdown file per slice, holding the contract surface and the test plan as language-tagged snippets and nested bullets. Referenced by /m:plan (default and cover modes) to emit the per-slice files the build consumes.

Engineering principles that bind any code Molcajete plans, builds, or reviews — integration tests as the trust contract, hexagonal default, dependency injection, 80% coverage floor, universal software craft (small functions, clear boundaries, no god files, refactor to reuse), technology-agnostic. Loaded by /m:plan and /m:build. Mirrored to the host project at `.claude/rules/principles.md` by /m:setup.

Technology-agnostic rules for the test-first build loop. Implementer and Validator role contracts, outer-edge mocking, reading specs/TECH-STACK.md, Runner Inference, coverage gate scoped to touched files, reactive refactor.

Rules and templates for the /m:setup command. One-shot foundation setup from a single project description plus codebase detection. Generates PROJECT.md, TECH-STACK.md, ACTORS.md, GLOSSARY.md, MODULES.md, DOMAINS.md, FEATURES.md, and .molcajete/settings.json.

Conventions for generating README.md files as LLM-optimized navigation documents. Covers YAML frontmatter, file tables, subdirectory tables, Mermaid diagrams, and stack-specific variants (backend, frontend, config). Used by /m:doc and the documentation task in build plans.

Status as first-class state on slices, use cases, and features. Defines the three-value enum (pending | dirty | implemented), per-level semantics, the bottom-up roll-up rule, and which command writes which level's status. Status lives on the artifact's frontmatter and is the source of truth — the CHANGELOG is for context and markers, not state.

Per-UC change log mechanics. Defines the CHANGELOG.md sidecar file path, TODO/DONE section layout, entry line format, and entry-status transitions (pending → dirty → implemented). Referenced by /m:spec, /m:fix, /m:change, /m:cover, /m:plan, and /m:build. The changelog is a context log + marker file; it is NOT the source of truth for artifact status (see status-rollup).

Schema, section definitions, and population rules for ARCHITECTURE.md — the feature-level artifact that maps specs to code. Referenced by feature-authoring (scaffold creation) and reverse-engineering (code-driven population).

Rules and templates for creating and updating feature documents. Defines EARS syntax patterns, Fit Criteria, Non-Goals positioning, FEAT-XXXX ID assignment, FEATURES.md row management, and the creation interview pattern. Used by /m:spec.

Rules and methodology for extracting specs from existing codebases. Defines research patterns, ARCHITECTURE.md population from code analysis, scope discovery, extraction patterns mapping code constructs to spec elements, and subagent dispatch for spec extraction.

Rules and templates for creating and updating use case files. Defines UC file structure with flat inline scenario blocks, mandatory Side Effects field with non-side-effects, YAML frontmatter schema, UC-XXXX ID assignment, USE-CASES.md row management, and the creation interview pattern.

Lightweight, silent research that runs before spec-writing. Checks for existing research (user-provided or cached), runs 2 parallel agents if needed, and saves a machine-oriented context brief to .molcajete/research/. No user interaction.

Full research orchestration skill — detects tech stack, parses input type, launches 4 parallel agents (web docs, community, library discovery, local codebase), and synthesizes findings into a progressive research guide.

Standards for structuring git commits during automated task execution. Covers message format, project style detection, atomic commit principles, scope assessment, and commit splitting. Read by build agents before committing work.

Reference material for resolving git merge and rebase conflicts. Covers conflict marker anatomy, resolution strategies by file type, context gathering, and rules for correct resolution.

Rule enforcing canonical ID generation for all entity identifiers (FEAT, UC, SC, FR, NFR, US, ADR). All IDs must be generated via the shared script — never compute base-62 manually.

Version bump conventions and changelog update rules for the m plugin