PWDEV Feat — Fast Feature Plans & Execution

Plugin pwdev-feat from marketplace pwdev-claude-marketplace in pwdev-solucoes/pwdev-claude-marketplace. Commands read from the repo's manifest — 1 month ago.

Skills (13)

• feat-audit

  Use when the user wants to query the local pwdev audit trail — 'ver auditoria', 'relatório de auditoria', 'audit stats', 'exportar auditoria em PDF' — summary, events, decisions, artifacts, statistics, a Markdown/PDF export or a custom read-only SELECT. Do NOT use to enable the audit (feat-init) or

• feat-backend

  Use when the user wants a backend-only action plan — API endpoints, services, models, migrations, jobs and their tests — 'plano de backend para o endpoint X', 'plan the orders API'. Writes .planning/feat/features/{slug}/plan.md with the PWDEVIA method. Do NOT use for UI work (feat-frontend), full fe

• feat-exec

  Use when the user wants to execute an existing pwdev-feat action plan — 'executar o plano user-crud', 'exec latest', 'rodar o plano', 'retomar a execução'. Dispatches the executor (subagent when the runtime has one, inline otherwise) in IMPLEMENT or REPORT mode, handles NEEDS_ADVICE with the advisor

• feat-feature

  Use when the user wants a full feature action plan (backend + frontend + tests) with the PWDEVIA 7-question method before any code is written — 'planejar a feature X', 'criar plano de feature', 'plan the user CRUD'. Interviews the human (max 2 rounds) and writes .planning/feat/features/{slug}/plan.m

• feat-frontend

  Use when the user wants a UI-only action plan — components, pages, composables/hooks, state, forms and their E2E coverage — 'plano de frontend para a tela X', 'plan the settings page'. Writes .planning/feat/features/{slug}/plan.md with E2E scenarios and playwright-cli checks. Do NOT use for API/data

• feat-init

  Use when the user wants to set up pwdev-feat in a project — 'inicializar o pwdev-feat', 'configurar o feat', 'init feat workspace' — choosing language, model profile and the optional audit trail, and creating the .planning/feat/ workspace. Do NOT use to analyze the codebase (feat-map), to write the

• feat-loop

  Use when the user hands over a GitHub issue to be delivered end to end — 'resolver a issue #42', 'loop na issue 42', 'deliver issue https://github.com/o/r/issues/42' — or when an Orca worker preamble dispatches `feat-loop #N`. Turns the issue into a plan, executes it, reviews the result and runs at

• feat-map

  Use when the user wants the existing codebase analyzed for planning — 'mapear o código', 'analisar o projeto', 'atualizar o contexto', 'map codebase' — or when a planning skill reports a missing or stale map. Runs a deterministic read-only evidence scan and writes codebase.md plus the architecture,

• feat-quick

  Use when the user wants a small, well-bounded change done now without a plan file — a bugfix, config change, rename, doc update or simple refactor touching 1–5 files — 'corrigir rapidinho', 'quick fix no X', 'renomear Y'. Presents a mini-plan, implements after approval, verifies and commits. Do NOT

• feat-review

  Use when the user wants a code review of an explicit range or set of files — correctness, security, performance, conventions, tests — with stable findings (CR-nnn, BLOCKER..INFO) and rule citations — 'revisar os últimos commits', 'code review da feature X', 'review base..HEAD'. Plans a REPORT-mode r

• feat-setup

  Use when the user wants the project instructions file generated or updated from the detected stack and conventions — 'gerar o arquivo de instruções do projeto', 'criar convenções do projeto', 'setup governance', 'gerar AGENTS'. Writes the shared instructions file read by Claude Code, Codex, Hermes a

• feat-status

  Use when the user asks for the state of pwdev-feat plans — 'status do feat', 'quais planos estão pendentes', 'show feature status' — listing pending, complete, with-caveats, failed and resumable plans plus codebase-context health. Read-only. Do NOT use to execute (feat-exec) or query the audit trail

• feat-test

  Use when the user wants tests planned for existing code or a test audit — unit, integration, E2E scenarios exportable to Playwright, playwright-cli UI checks, a coverage matrix — 'criar testes para o UserService', 'plano de testes E2E do login', 'auditar a cobertura'. Writes .planning/feat/features/

Slash commands (13)

• /pwdev-feat:audit

  Query the audit trail database for events, decisions, artifacts, and statistics. Export a Markdown/PDF report.

• /pwdev-feat:backend

  Create a backend-focused action plan — API endpoints, services, models, migrations, tests.

• /pwdev-feat:exec

  Execute an action plan generated by PWDEVIA. Dispatches the executor subagent (fresh context); supports --resume.

• /pwdev-feat:feat

  Create a full feature action plan using the PWDEVIA 7-question methodology. Covers backend + frontend + tests.

• /pwdev-feat:frontend

  Create a frontend-focused action plan — components, pages, state, E2E scenarios and playwright-cli checks.

• /pwdev-feat:init

  Initialize the pwdev-feat framework — language, model profile, optional audit, .planning/feat/ workspace.

• /pwdev-feat:loop

  Deliver a GitHub issue end to end — plan, execute, review, at most 2 fix cycles, then a pull request that closes it. Never merges.

• /pwdev-feat:map-codebase

  Analyze the existing codebase — deterministic evidence scan plus architecture, conventions, testing and concerns context documents.

• /pwdev-feat:quick

  Quick task — no plan file, direct execution for simple tasks (bugfix, config, rename, 1-5 files).

• /pwdev-feat:review

  Create a code review plan for an explicit range — correctness, security, performance, conventions, tests.

• /pwdev-feat:setup

  Generate the project instructions file (AGENTS + Claude import) from the detected stack and conventions.

• /pwdev-feat:status

  Show current features — pending, executed, with caveats, failed, resumable — and codebase context health.

• /pwdev-feat:test

  Create a test plan or test audit — unit, integration, E2E scenarios exportable to Playwright, playwright-cli checks.

Subagents (2)

• advisor

  Senior technical advisor: resolves ONE structured decision question raised by a blocked executor (NEEDS_ADVICE) — plan ambiguity, architectural fork, or repeated verification failure. Read-only investigation; picks ONE direction. Dispatched by /pwdev-feat:exec. Never implements.

• executor

  Executes ONE pwdev-feat action plan end-to-end: implements code, verifies every quality criterion with real evidence (including playwright-cli UI checks and E2E scenario validation), commits, and writes the execution report. Dispatched by /pwdev-feat:exec. Runs in REPORT mode (findings only, no code

Hooks (6)

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/scripts/audit-hook.sh" session_start

• SubagentStart

  "${CLAUDE_PLUGIN_ROOT}/scripts/audit-hook.sh" subagent_start

• SubagentStop

  "${CLAUDE_PLUGIN_ROOT}/scripts/audit-hook.sh" subagent_stop

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/audit-hook.sh" artifact

• Stop

  "${CLAUDE_PLUGIN_ROOT}/scripts/audit-hook.sh" stop

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/guard-secrets.sh"

Similar plugins