linter-driven-development

Plugin linter-driven-development from marketplace ai-coding-rules in buzzdan/ai-coding-rules. Commands read from the repo's manifest — 18 days ago.

Skills (7)

• code-designing

  FORWARD view over rules/ — domain type design and architectural planning for code BEFORE it exists, in whatever language the repository uses. Use when planning new features, designing self-validating types, preventing primitive obsession, or when refactoring reveals need for new types. Dispatches in

• documentation

  The repo-brain author/maintainer: writes behavior-focused documentation and wires it into the documentation network defined by rules/R9-repo-brain.md. FEATURE mode (default): after feature implementation or bug fixes — invoked by @linter-driven-development (Phase 5) — to document HOW THE PRODUCT BEH

• lint-setup

  Compares the linter setup of this repository with the LDD recommended setup, and agrees a tighter setup with the user before any edit. Applies to the languages that no installed language-specific linter-driven-development plugin covers. WHEN: the user asks to compare, align or set up the linter conf

• linter-driven-development

  META ORCHESTRATOR for any code change that should end in a commit (features, bug fixes, refactors), when no language-specific linter-driven-development plugin covers the repository's language. WHEN: User requests code work (implement, fix, add, refactor), mentions "@ldd"/"ldd", or runs a /ldd-* comm

• pre-commit-review

  ADVISORY pre-commit review that orchestrates four parallel rule-family hunters, an over-abstraction skeptic, and a comment critic against the diff. Spawns read-only agents (rule-hunter, overabstraction-skeptic, comment-critic); NEVER edits code. Invoked by @linter-driven-development (Phase 4), by @r

• refactoring

  BACKWARD view over rules/ — routes linter and review failures to the rule whose Fix pattern owns the repair. Use when linter fails with complexity issues (cyclomatic, cognitive, maintainability) or when code feels hard to read/maintain. Also the skill for removing a `lint-suppression` directive or a

• testing

  Use when creating leaf types, after refactoring, during implementation, or when testing advice is needed. Automatically invoked to write tests for new types, or use as testing expert advisor. Covers the composition ladder from rung-0 unit tests to whole-system tests, with emphasis on real in-memory

Slash commands (8)

• /linter-driven-development:ldd-analyze

  Run quality analysis only - tests + plain lint + hunter/skeptic review, combined report, no auto-fix

• /linter-driven-development:ldd-autopilot

  Start complete linter-driven autopilot workflow (Phases 1-5, incl. the autonomous PREPARE sub-phase 1.5)

• /linter-driven-development:ldd-prepare

  Preparatory refactoring — reshape the code a planned change will touch, so the feature lands add-only

• /linter-driven-development:ldd-quickfix

  Fix what is in scope — the files you are working on — through the quality gates (tests + lint + review → fix → repeat) until green

• /linter-driven-development:ldd-review

  Advisory review of the code in scope before a commit (hunters + skeptic report; no tests, no lint, no auto-fix)

• /linter-driven-development:ldd-setup

  Compare the linter setup with the LDD recommended setup, agree a tighter setup per rule, and edit only after you agree to the plan

• /linter-driven-development:ldd-status

  Show current workflow status and progress

• /linter-driven-development:wire-repo-brain

  Wire the full documentation network in one pass — code comments → docs → index.md → CLAUDE.md

Subagents (4)

• comment-critic

  WHEN: Spawned programmatically by the documentation skill (after it writes doc comments and feature docs) and by the pre-commit-review skill (when the diff contains comment lines), receiving the paths of its doctrine — R9's comment policy section and the Comment Value Toolbox catalog — in the spawn

• lint-fixer

  WHEN: Spawned programmatically by the linter-driven-development skill in Phase 3 to run the lint-fix loop in an isolated context, keeping the loop's token noise out of the main conversation. Not auto-triggered by user requests. Fixes mechanical lint issues; escalates complexity/design failures with

• overabstraction-skeptic

  WHEN: Spawned programmatically by the pre-commit-review skill after hunters report, receiving the type/package-extraction findings plus the paths of its doctrine (R1's juiciness scorecard and the CIDR over-abstraction case file) in the spawn prompt, read in its first turn. Not auto-triggered by user

• rule-hunter

  WHEN: Spawned programmatically by the pre-commit-review skill — one hunter per rule family (up to four), in parallel — with the paths of that family's rule files (rules/R*.md), the path of the scope bundle and the family's rows of the detection pass's hits and counts tables in the spawn prompt; the

Similar plugins