claude

feature-dev

Feature development workflows: test-driven development with coverage gates and parallel codebase exploration before planning

8 on GitHubby Juan M. Hidalgov2.9.1MITupdated 3 days agodevelopment
/

Plugin feature-dev from marketplace juanmhidalgo-plugins in juanmhidalgo/claude-plugins. Commands read from the repo's manifest — 2 days ago.

What it installs

Skills (2)

  • spec-driven-development

    Use when starting a new feature or significant change with no spec yet. Covers single-repo and multi-repo features. Do NOT use for typos, single-line fixes, or post-hoc documentation of finished work. - spec - specification - requirements - planning - acceptance-criteria - "write a spec" - "define r

  • tdd-patterns

    Use when executing TDD cycles with coverage gates and quality checks. Do NOT use for general testing advice or test writing without the full TDD cycle. - tdd - red-green-refactor - coverage-gate

Slash commands (8)

  • /feature-dev:cleanup

    Use to bulk-delete implemented features (spec, plan, review history and feedback) from .feature-dev/features/, and stale review-server pointers. Lists only safe candidates and requires Y/N confirm. Offers first to rescue a spec's Decisions Log and unticked QA items as a comment on its branch's PR or

  • /feature-dev:explore-plan

    Use when starting a feature that touches multiple parts of the codebase and you need a structured implementation plan before coding. Do NOT use for simple bug fixes or single-file changes. - exploration - planning - parallel-agents - implementation-plan - architecture - "explore and plan" - "plan th

  • /feature-dev:harden

    Use after an implementation is finished — typically right after /feature-dev:tdd — to review it in fresh context (defects, spec conformance and tech debt at once), verify every finding, fix the ones you approve, and re-review what the fixes changed. Replaces running /code-review:staged, /code-review

  • /feature-dev:plan-review

    Use to re-validate a PLAN-*.md edited by hand, or one written before explore-plan reviewed its own plans. Outputs Blocking / Should Address / Nice to Have findings. Do NOT use right after /feature-dev:explore-plan (it already ran this review), for code review, or for SPEC review (use /feature-dev:sp

  • /feature-dev:review

    Use to review a SPEC-*.md or PLAN-*.md in the browser — outline, decision cards, text-anchored comments, diff against the previous version — and apply the verdict. Do NOT use for a structural gap check (use /feature-dev:spec-review or /feature-dev:plan-review) or for code review. - review - browser

  • /feature-dev:spec-review

    Use to validate a SPEC-*.md for gaps before planning or implementation. Outputs Blocking / Should Address / Nice to Have findings. Do NOT use to verify implementation (use /prd:validate). - spec-review - spec-validation - gap-analysis - feature-dev - "review the spec" - "validate the spec" - "find g

  • /feature-dev:spec

    Use before writing code when requirements are ambiguous or a feature has non-obvious scope. Do NOT use for simple, self-evident changes. - spec - specification - requirements - planning - "write a spec" - "create specification" - "define requirements first" - "spec-driven development" - Read - Grep

  • /feature-dev:tdd

    Use when implementing a new feature or fixing a bug where you want tests to lead, not follow. Do NOT use for quick one-line fixes or refactors without behavioral change. - tdd - test-driven - feature-development - coverage - red-green-refactor - "implement with TDD" - "test-driven development" - "wr

Subagents (13)

  • api-contract-explorer

    Explores declared API contracts for a feature — OpenAPI, GraphQL, tRPC, protobuf, JSON Schema. Separate from endpoint *code* (backend-explorer covers that). Critical for multi-repo features. Opt-in primitive — invoke directly from any skill.

  • backend-explorer

    Explores backend/API layer for a feature. Finds models, views, serializers, endpoints, services, and database patterns. Spawned by explore-plan for parallel exploration.

  • config-explorer

    Explores the configuration surface for a feature. Finds env vars, settings modules, feature flags, secrets handling, and per-environment overrides. Opt-in primitive — invoke directly from any skill.

  • cross-repo-advisor

    Produces a decision brief for ONE bounded cross-repo question during feature work — which side owns a field, whether a change breaks a declared contract, how a consumer should branch on an error. Reads the spec's `repos:` block and the sibling repos and recommends. Read-only: it never edits, never r

  • feature-implementer

    Orchestrates execution of an approved PLAN-*.md (or equivalent step list) by dispatching each step to plan-step-executor in order, accumulating carry-over notes between steps, and halting on blockers. Use AFTER a plan is approved and you want a single delegate to drive the whole feature instead of s

  • frontend-explorer

    Explores frontend/UI layer for a feature. Finds components, views, hooks, API clients, routing, and state management. Spawned by explore-plan for parallel exploration.

  • history-explorer

    Explores git history and open PRs for a feature. Finds recent changes, conflicts, and historical patterns. Spawned by explore-plan for parallel exploration.

  • observability-explorer

    Explores logging, metrics, tracing, error reporting, and alerting conventions for a feature's domain. Opt-in primitive — invoke directly from any skill.

  • plan-step-executor

    Executes ONE step of an approved multi-step plan in isolation, so the orchestrating agent preserves its context budget. Spawn one instance per qualifying step — a step with its own acceptance criteria, multi-file scope, or independent verification. Do NOT use for trivial single-line changes, pure re

  • schema-explorer

    Explores database schema and migration state for a feature's domain. Finds migration files, current schema, indexes, constraints, and naming conventions. Opt-in primitive — invoke directly from any skill.

  • spec-plan-validator

    Validates a SPEC-*.md or PLAN-*.md artifact for structural and logical gaps before downstream work, and checks a spec's factual claims about the existing code (paths, symbols, fields, FK direction, endpoints) against the repository. Emits a categorical Blocking / Should Address / Nice to Have findin

  • tdd-runner

    Executes strict red-green-refactor TDD cycles for one bounded task, enforcing the discipline that RED must legitimately fail before any production code is written. Caps at 5 cycles per invocation by default. Stack-agnostic: detects backend (pytest) vs frontend (vitest) from target path or task descr

  • test-explorer

    Explores the test suite for a feature. Finds test files, fixtures, factories, patterns, and coverage config. Spawned by explore-plan for parallel exploration.

View source on GitHub

More from juanmhidalgo/claude-plugins

All 19 plugins →

Comprehensive code review workflow: branch reviews, PR triage, false positive dismissal, and fix tracking

6 skills · 14 commands · 14 agents

8

discuss

claude

Critical feature discussion and idea refinement with skeptical Staff Engineer perspective, plus adversarial review of technical documents

4 skills · 4 commands · 1 agent

8

handoff

claude

Generate self-contained prompts for use in other repositories, including API handoffs between frontend and backend teams

2 skills · 4 commands

8

Refine, analyze, and validate Product Requirements Documents (PRDs). Publish to GitHub Issues or ClickUp.

1 skill · 3 commands · 2 agents

8

refactor

claude

Structured refactoring workflow: analyze, plan, and extract code safely

3 commands · 3 agents

8

debug

claude

Systematic debugging and incident response: structured triage, root cause analysis, regression guards, error pattern recognition, and blameless postmortem generation

2 skills · 3 commands

8

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

Maintain feature-dev?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins19 plugins