create-quiver 0.15.2 → 0.15.4

package/.github/workflows/ci.yml

@@ -7,6 +7,9 @@ on:
       - develop
   pull_request:
 
+env:
+  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
+
 jobs:
   validate:
     runs-on: ubuntu-latest

package/AGENTS.md.es.template

@@ -0,0 +1,37 @@
+# Agentes de {{PROJECT_NAME}}
+
+## Proposito
+
+Este archivo orienta a agentes de IA y personas que trabajan en el proyecto.
+
+## Presupuesto de lectura
+
+- Empeza por `README.md`.
+- Usa `docs/INDEX.md` como mapa.
+- Lee solo los documentos necesarios para la tarea actual.
+
+## Orden de lectura
+
+1. `docs/INDEX.md`
+2. `docs/PROJECT_MAP.md`, si existe
+3. `docs/AI_CONTEXT.md`
+4. `docs/AI_ONBOARDING_PROMPT.md`
+5. El spec y slice activos, si la tarea los requiere
+
+## Politica de salida
+
+- Responde con cambios y evidencia verificable.
+- No inventes reglas de negocio, rutas, flags ni convenciones.
+- No leas todo `docs/` sin una razon documentada.
+
+## Reglas de ejecucion de slices
+
+- Un slice equivale a un commit.
+- Un spec equivale a un PR.
+- No modifiques archivos fuera del scope declarado por el slice.
+
+## Links
+
+- `docs/WORKFLOW.md`
+- `docs/STATUS.md`
+- `docs/DECISIONS.md`

package/README.md

@@ -175,6 +175,7 @@ Usá la guía que corresponda al estado de tu proyecto:
 | `npx --yes create-quiver@latest doctor` | Revisa si el contrato de Quiver está sano. |
 | `npx --yes create-quiver@latest doctor --json` | Devuelve el diagnóstico como JSON para automatizaciones. |
 | `npx --yes create-quiver@latest flow` | Indica el próximo paso seguro. |
+| `npx --yes create-quiver@latest dashboard` | Muestra estado consolidado de specs, slices, runs, approvals y agentes sin escribir archivos. |
 | `npx --yes create-quiver@latest ai prepare-context --dry-run` | Previsualiza contexto de onboarding para IA sin tocar código de producto. |
 | `npx --yes create-quiver@latest ai prepare-context --with-planner --dry-run` | Previsualiza una propuesta de contexto generada por el planner. |
 | `npx --yes create-quiver@latest ai models list` | Lista proveedores y modelos conocidos por Quiver para configurar agentes. |

package/README_FOR_AI.md

@@ -27,8 +27,10 @@ The v29 spec is implemented under `specs/quiver-v29-planner-prepare-context-cli-
 The v30 spec is implemented under `specs/quiver-v30-interactive-cli-ux-agent-selection/` and is release-ready pending package publication; it adds production-grade interactive CLI UX with visible IA progress, Quiver-branded output, configured Planner/Executor/Reviewer/Doctor selectors, real provider model-selection contracts, Doctor human/JSON parity, guided init/spec-create selectors, and cross-platform release readiness.
 The v31 spec is implemented and release-ready pending PR/package publication under `specs/quiver-v31-ai-model-catalog-agent-selection/`; slice-00 through slice-07 are completed. Implemented scope includes the local AI model catalog, alias normalization, guided provider/model selection for `ai agent set <role>`, `ai agent doctor`, `ai agent repair --dry-run`, shared live-command model preflight, clearer provider errors for invalid model ids, `ai models list`, aligned README/reference/generated-template guidance, and final smoke/package readiness.
 The v32 documentation spec is implemented under `specs/quiver-v32-npx-installation-guidance/`; it clarifies why `npx --yes create-quiver@latest` does not install Quiver into project `node_modules`, when to install `create-quiver` as a `devDependency`, and where users should look when troubleshooting that behavior.
+The v34 dashboard spec is implemented under `specs/quiver-v34-cli-dashboard-status/`; it adds the read-only top-level `dashboard` command, compact schema v1 JSON output, global vs visible progress, next-ready slice guidance, edge-case guardrails, `quiver:dashboard` generated scripts, docs, tests, smokes, and package-readiness evidence. It does not publish npm.
+The v35 dashboard/version UX spec is implemented under `specs/quiver-v35-compact-dashboard-version-ux/`; it keeps `dashboard` compact by default, adds `dashboard --details`, `dashboard --section <name>`, `dashboard --limit <n>`, and adds the Quiver-branded `version` command without changing top-level `--version` / `-V`.
 Guided AI workflow behavior is available: prepare, approvals, production-readiness plan review, spec worktrees, executor commits, execution waves, PR creation, spec close, and package safety.
-Generated projects also get `quiver:*` npm scripts that call the Node CLI directly; prefer those for repeatable project workflows, including `quiver:flow` for the read-only guided entrypoint, `quiver:plan` for sequential planning, `quiver:graph` for parallel-level inspection, `quiver:next` for the next ready slice, `quiver:evidence` for local command evidence, `quiver:spec:create` for real spec generation, `quiver:spec:validate` for full spec validation, and the AI family `quiver:ai:agent`, `quiver:ai:inspect`, `quiver:ai:export`, `quiver:ai:specs`, `quiver:ai:slices`, `quiver:ai:trace`, `quiver:ai:onboard`, `quiver:ai:prepare-context`, `quiver:ai:plan`, `quiver:ai:review-plan`, `quiver:ai:approve`, `quiver:ai:prompt-slice`, `quiver:ai:execute-slice`, `quiver:ai:execute-plan`, `quiver:ai:pr`, and `quiver:ai:doctor`. Use `quiver:graph --format mermaid` for PR-ready Markdown or `quiver:graph --format dot` for Graphviz source.
+Generated projects also get `quiver:*` npm scripts that call the Node CLI directly; prefer those for repeatable project workflows, including `quiver:version` for version metadata, `quiver:flow` for the read-only guided entrypoint, `quiver:dashboard` for consolidated read-only project/spec/slice status, `quiver:plan` for sequential planning, `quiver:graph` for parallel-level inspection, `quiver:next` for the next ready slice, `quiver:evidence` for local command evidence, `quiver:spec:create` for real spec generation, `quiver:spec:validate` for full spec validation, and the AI family `quiver:ai:agent`, `quiver:ai:inspect`, `quiver:ai:export`, `quiver:ai:specs`, `quiver:ai:slices`, `quiver:ai:trace`, `quiver:ai:onboard`, `quiver:ai:prepare-context`, `quiver:ai:plan`, `quiver:ai:review-plan`, `quiver:ai:approve`, `quiver:ai:prompt-slice`, `quiver:ai:execute-slice`, `quiver:ai:execute-plan`, `quiver:ai:pr`, and `quiver:ai:doctor`. Use `quiver:graph --format mermaid` for PR-ready Markdown or `quiver:graph --format dot` for Graphviz source.
 `quiver:ai:execute-plan` supports `--mode manual` for paste-ready executor prompts and `--mode delegated` for temporary worktrees on parallel-ready waves; unsafe waves fall back to sequential execution.
 Agent profiles live in `.quiver/agents/profiles.json`; they store role, provider, technical `model`, human `displayName`, context label, profile id, and default profile only. Do not store API keys, tokens, or credentials there.
 `model` is the technical id passed to the provider CLI, for example `gpt-5.5`. `displayName` is the human label shown in Quiver output, for example `GPT 5.5`.
@@ -53,7 +55,7 @@ The raw analyzer output is internal machinery at `.quiver/scans/PROJECT_SCAN.jso
 `npx create-quiver ai agent set <role> --provider <provider> --model <model-id> --dry-run` must preview `.quiver/agents/profiles.json` changes without writing. In TTY mode, `npx create-quiver ai agent set <role>` can guide provider/model selection; in CI/no-TTY, require explicit `--provider` and `--model`. Use dry-run before saving planner/executor/reviewer/doctor profiles.
 GitHub PR diagnostics must stay cross-platform: auth failures should point to likely account, scope, and SSH alias issues; path examples with spaces must be copy-safe for macOS/Linux, Windows PowerShell, Git Bash, and WSL.
 CLI UX standard lives in `docs/CLI_UX_GUIDE.md`. Supported Quiver colors are `#86C8F2`, `#6BADEB`, `#7F9EE8`, `#9B82E6`, and `#D56AB0`; output must respect `--no-color`, `NO_COLOR`, CI, and no-TTY environments.
-UX flags are intentionally limited: `ai prepare-context`, `ai plan`, and `spec create` support `--with-planner`, `--interactive`, and `--review`; `ai pr` supports `--interactive` and `--review` but rejects `--with-planner`; read-only commands such as `flow`, `next`, `graph`, `ai inspect`, `ai export`, `ai specs list`, `ai slices list`, and `ai trace report` reject these UX flags. `--json` must reject `--interactive` and `--review` before writing human output.
+UX flags are intentionally limited: `ai prepare-context`, `ai plan`, and `spec create` support `--with-planner`, `--interactive`, and `--review`; `ai pr` supports `--interactive` and `--review` but rejects `--with-planner`; read-only commands such as `flow`, `dashboard`, `version`, `next`, `graph`, `ai inspect`, `ai export`, `ai specs list`, `ai slices list`, and `ai trace report` reject these UX flags. `dashboard` may use read-only inspection flags `--details`, `--section`, and `--limit`; `--json` must reject human-only dashboard flags plus `--interactive` and `--review` before writing human output.
 The universal router for generated projects is `AGENTS.md`; read it before `docs/AI_CONTEXT.md` and `docs/AI_ONBOARDING_PROMPT.md`.
 Generated projects also get `docs/DECISIONS.md`; use it for durable choices that should not be re-litigated.
 If a generated project has been analyzed, the exact agent handoff prompt is `docs/AI_ONBOARDING_PROMPT.md`.
@@ -90,12 +92,12 @@ Prefer maps, metadata, diffs, and summaries over full file reads when they are e
 - The normal workflow runs from the project root without `--dir`; use `--dir` only when targeting another directory explicitly.
 - The cross-platform contract targets native macOS, Linux, and Windows users through the Node CLI (`npx create-quiver ...`) and generated `quiver:*` npm scripts. Bash wrappers are legacy or optional compatibility, not the primary path. Keep root README examples clear about adapting SSH identity paths on Windows PowerShell, Git Bash, WSL, macOS, and Linux.
 - The support contract lives in `docs/SUPPORT_MATRIX.md` and `docs/TROUBLESHOOTING.md`.
-- Generated project npm scripts should prefer `quiver:*` names such as `quiver:analyze`, `quiver:flow`, `quiver:plan`, `quiver:graph`, `quiver:next`, `quiver:doctor`, `quiver:evidence`, `quiver:ai:agent`, `quiver:ai:inspect`, `quiver:ai:export`, `quiver:ai:specs`, `quiver:ai:slices`, `quiver:ai:trace`, `quiver:ai:prepare-context`, `quiver:ai:plan`, `quiver:ai:review-plan`, `quiver:ai:approve`, `quiver:ai:prompt-slice`, `quiver:ai:execute-slice`, `quiver:ai:execute-plan`, `quiver:spec:create`, `quiver:spec:start`, `quiver:spec:status`, `quiver:spec:validate`, `quiver:spec:close`, `quiver:start-slice`, `quiver:check-slice`, and `quiver:check-pr`.
+- Generated project npm scripts should prefer `quiver:*` names such as `quiver:version`, `quiver:analyze`, `quiver:flow`, `quiver:dashboard`, `quiver:plan`, `quiver:graph`, `quiver:next`, `quiver:doctor`, `quiver:evidence`, `quiver:ai:agent`, `quiver:ai:inspect`, `quiver:ai:export`, `quiver:ai:specs`, `quiver:ai:slices`, `quiver:ai:trace`, `quiver:ai:prepare-context`, `quiver:ai:plan`, `quiver:ai:review-plan`, `quiver:ai:approve`, `quiver:ai:prompt-slice`, `quiver:ai:execute-slice`, `quiver:ai:execute-plan`, `quiver:spec:create`, `quiver:spec:start`, `quiver:spec:status`, `quiver:spec:validate`, `quiver:spec:close`, `quiver:start-slice`, `quiver:check-slice`, and `quiver:check-pr`.
 - Optional demos are created with `npx create-quiver demo create spec-viewer`; do not add demo output to the package or default init flow.
 - `quiver:graph` defaults to the tree view; choose `--format mermaid` or `--format dot` when you need exportable graph artifacts.
 - `quiver:next` prints the next ready slice and can auto-start it behind a confirmation prompt.
 - `quiver:next --all-ready` prints the whole ready level when you want to inspect every actionable slice at once.
-- Use `--include-completed` with `plan`, `graph`, or `next` only for audit/demo history; default output remains pending/actionable work.
+- Use `--include-completed` with `dashboard`, `plan`, `graph`, or `next` only for audit/demo history; default output remains pending/actionable work.
 
 ## Initialization Flow
 

package/docs/AI_CONTEXT.md.es.template

@@ -0,0 +1,35 @@
+# Contexto IA de {{PROJECT_NAME}}
+
+Este archivo comprime el contrato de trabajo para agentes IA. Usa los documentos canonicos cuando necesites mas detalle.
+
+## Que es este proyecto
+
+[Resumen corto del proyecto.]
+
+## Leer primero
+
+1. `docs/PROJECT_MAP.md`
+2. `docs/INDEX.md`
+3. `docs/AI_ONBOARDING_PROMPT.md`
+4. `docs/DECISIONS.md`
+5. `docs/CONTEXTO.md`
+6. `docs/WORKFLOW.md`
+7. `specs/{{PROJECT_SLUG}}/SPEC.md`
+8. `specs/{{PROJECT_SLUG}}/slices/[slice-id]/slice.json`
+
+## Reglas criticas
+
+- Un slice equivale a un commit.
+- Un spec equivale a un PR.
+- No inventes archivos, rutas, flags ni reglas de negocio.
+- No sobrescribas contenido humano sin revisar si debe preservarse.
+- Usa `TODO`, `Assumption` o `Pending confirmation` para incertidumbre.
+- Los prompts y salidas JSON son contratos estables y no deben traducirse.
+
+## Comandos utiles
+
+```bash
+npx create-quiver flow
+npx create-quiver dashboard
+npx create-quiver spec validate specs/{{PROJECT_SLUG}} --strict
+```

package/docs/AI_ONBOARDING_PROMPT.md.es.template

@@ -0,0 +1,22 @@
+# Prompt de onboarding IA de {{PROJECT_NAME}}
+
+**Fecha:** {{FECHA}}
+**Estado:** {{ESTADO}}
+
+Actua como asistente tecnico senior para este proyecto. Tu objetivo es entender el contexto minimo necesario y trabajar con WDD + SDD sin improvisar.
+
+## Reglas de ejecucion
+
+1. Lee `docs/INDEX.md` como mapa antes de abrir otros documentos.
+2. Lee solo los documentos relevantes para la tarea actual.
+3. Si hay spec/slice activo, usa `slice.json`, `EXECUTION_BRIEF.md` y `CLOSURE_BRIEF.md` como contrato.
+4. No modifiques codigo de producto sin autorizacion o slice aprobado.
+5. No traduzcas comandos, flags, rutas, ids, providers, modelos ni JSON.
+6. Si falta informacion critica, pregunta antes de avanzar.
+7. Si hay conflicto documental, reportalo y detenete.
+
+## Proximo paso recomendado
+
+```bash
+npx create-quiver flow
+```

package/docs/CLI_UX_GUIDE.md

@@ -42,6 +42,52 @@ Reglas:
 | `--json` | Emite salida machine-readable. | Incompatible con `--interactive` y `--review`. |
 | `--no-color` | Desactiva color ANSI. | Debe respetarse en toda salida humana. |
 
+## Idioma de salida
+
+Quiver soporta salida humana en `en` y `es`. Los comandos deben resolver el idioma con esta precedencia:
+
+1. `--lang en|es`
+2. `QUIVER_LANG`
+3. `.quiver/config.json`
+4. `~/.quiver/config.json`
+5. locale del entorno
+6. fallback `en`
+
+Reglas:
+
+- `--lang` debe funcionar antes o despues del comando.
+- `config language set es` guarda el idioma del proyecto sin exigir flags en cada ejecucion.
+- `config language set en --global` guarda el idioma global del usuario.
+- Los comandos, flags, rutas, ids, providers, modelos y snippets sugeridos no se traducen.
+- `--json` mantiene claves, codigos y estructura estable; no se localizan campos machine-readable.
+- Warnings por idioma no soportado se muestran solo en salida humana y no contaminan stdout JSON.
+- CI, no-TTY y `--no-color` deben seguir sin prompts, spinners ni ANSI inesperado.
+
+## Templates y docs generados
+
+La salida CLI y los docs generados comparten resolucion de idioma, pero son superficies distintas:
+
+- salida CLI: textos humanos impresos durante un comando;
+- docs generados: archivos Markdown creados por comandos como `init`;
+- machine artifacts: JSON, JSONL, `package.json`, `slice.json`, ids, comandos, flags, rutas, providers y modelos.
+
+Solo las dos primeras superficies se localizan. Los machine artifacts permanecen estables.
+
+Los templates humanos generados por Quiver usan el mismo idioma resuelto para la salida CLI. El template base sin sufijo es el fallback `en`; las variantes localizadas agregan el idioma antes de `.template`.
+
+Ejemplos:
+
+- `docs/INDEX.md.template` es el fallback estable en ingles.
+- `docs/INDEX.md.es.template` es la variante espanola.
+- `AGENTS.md.es.template` es la variante espanola de `AGENTS.md.template`.
+
+Reglas:
+
+- Solo se enrutan templates humanos, principalmente Markdown.
+- Artefactos machine-readable como `package.template.json` y `slice.json` no se localizan.
+- Si falta una variante localizada, Quiver debe hacer fallback explicito a `en` y la cobertura debe poder detectarlo en tests.
+- No duplicar templates grandes si una fragmentacion compartida resuelve el caso con menor mantenimiento.
+
 ## Matriz de soporte
 
 | Comando | `--with-planner` | `--interactive` | `--review` | Notas |
@@ -59,7 +105,7 @@ Reglas:
 | `ai agent repair` | no | no | no | Por ahora solo `--dry-run`; muestra before/after sin escribir. |
 | `ai models list` | no | no | no | Lista el catalogo local conocido por Quiver; no valida acceso de cuenta. |
 | `doctor` | no | no | no | Renderiza `Quiver Doctor`, `Checks` y `Suggested fixes`; `--json` usa el mismo modelo de hallazgos. |
-| `flow`, `next`, `graph` | no | no | no | Lectura/inspeccion; no deben exponer flags decorativas. |
+| `flow`, `dashboard`, `next`, `graph`, `version` | no | no | no | Lectura/inspeccion; `dashboard` puede acotarse con `--details`, `--section` y `--limit`, pero no acepta flags decorativas. |
 | `ai inspect`, `ai export`, `ai specs list`, `ai slices list`, `ai trace report` | no | no | no | Superficies read-only o machine-readable. |
 
 ## Flujo recomendado para contexto de IA

package/docs/COMMANDS.md.es.template

@@ -0,0 +1,28 @@
+# Comandos
+
+**Proyecto:** {{PROJECT_NAME}}
+**Ultima actualizacion:** {{FECHA}}
+
+Este documento resume los comandos principales del workflow Quiver. Los comandos, flags y snippets se mantienen sin traducir.
+
+## Tabla de comandos
+
+| Comando | Proposito | Ejemplo |
+|---|---|---|
+| `npx create-quiver init --name "<project>"` | Crea el contrato Quiver inicial del proyecto | `npx create-quiver init --name "{{PROJECT_NAME}}"` |
+| `npx create-quiver init --interactive` | Guia modo de proyecto, metodologia, perfil e idioma | `npx create-quiver init --interactive` |
+| `npx create-quiver analyze` | Genera mapa visible del proyecto y scan interno | `npx create-quiver analyze` |
+| `npx create-quiver flow` | Muestra el proximo paso seguro | `npx create-quiver flow` |
+| `npx create-quiver dashboard` | Resume specs, slices, runs, agentes y aprobaciones | `npx create-quiver dashboard` |
+| `npx create-quiver ai agent set planner --provider <provider> --model <model>` | Configura el perfil del planner sin guardar credenciales | `npx create-quiver ai agent set planner --provider codex --model gpt-5.5 --dry-run` |
+| `npx create-quiver ai plan --phase acceptance --input <requirements.md>` | Genera criterios de aceptacion para aprobar | `npx create-quiver ai plan --phase acceptance --input requirements.md --dry-run` |
+| `npx create-quiver ai review-plan` | Revisa el plan tecnico antes de aprobarlo | `npx create-quiver ai review-plan --dry-run` |
+| `npx create-quiver spec create` | Crea el paquete de spec desde un plan tecnico aprobado | `npx create-quiver spec create --dry-run` |
+| `npx create-quiver spec validate <spec>` | Valida estructura y handoffs del spec | `npx create-quiver spec validate specs/<spec> --strict` |
+
+## Reglas
+
+- Usa `--dry-run` antes de escrituras.
+- Usa `--json` solo para automatizacion.
+- Configura idioma con `npx create-quiver config language set es` o `--lang es`.
+- Los artefactos machine-readable no se traducen.

package/docs/COMMANDS.md.template

@@ -13,13 +13,19 @@ This document is the canonical command reference for the orchestration roadmap.
 | `npx create-quiver init --interactive` | Guides project mode, methodology `wdd-sdd`, init profile, and agent-profile next steps without running providers | macOS, Linux, Windows | next | `npx create-quiver init --interactive` |
 | `npx create-quiver --name "<project>"` | Compatibility alias for the recommended init flow | macOS, Linux, Windows | current | `npx create-quiver --name "{{PROJECT_NAME}}"` |
 | `npx create-quiver --version` | Prints the installed CLI version | macOS, Linux, Windows | current | `npx create-quiver --version` |
+| `npx create-quiver version` | Prints the Quiver-branded version report with CLI, runtime, package manager, and detected project metadata | macOS, Linux, Windows | next | `npx create-quiver version --no-color` |
+| `quiver:version` | Runs the Quiver-branded version report through the generated npm script | macOS, Linux, Windows | next | `npm run quiver:version -- --json` |
 | `npx create-quiver --help` | Lists all public commands with descriptions, key options, and recommended examples | macOS, Linux, Windows | current | `npx create-quiver --help` |
 | `npx create-quiver help` | Readable alias for the complete CLI help | macOS, Linux, Windows | current | `npx create-quiver help` |
 | `quiver --help` | Shows the same help when Quiver is installed locally as a project dependency | macOS, Linux, Windows | current | `quiver --help` |
 | `npx create-quiver flow` | Shows the read-only guided flow entrypoint, context source/freshness, package-manager-aware script guidance, and next safe command | macOS, Linux, Windows | v0.11 | `npx create-quiver flow` |
+| `npx create-quiver dashboard` | Shows a compact read-only summary of project, spec, slice, run, approval, and agent status | macOS, Linux, Windows | next | `npx create-quiver dashboard --spec <spec>` |
+| `npx create-quiver dashboard --details` | Shows the full human dashboard report for audit/debug sessions | macOS, Linux, Windows | next | `npx create-quiver dashboard --details` |
+| `npx create-quiver dashboard --section <name>` | Shows one human dashboard section such as `specs`, `slices`, `blockers`, `warnings`, `agents`, `approvals`, `runs`, `active-slice`, or `next-steps` | macOS, Linux, Windows | next | `npx create-quiver dashboard --section slices --limit 10` |
 | `npx create-quiver analyze --dry-run` | Previews scan, project-map, and AI context writes without creating files | macOS, Linux, Windows | v0.13 | `npx create-quiver analyze --dry-run` |
 | `quiver:analyze` | Writes raw analyzer data to `.quiver/scans/PROJECT_SCAN.json`, the visible project map to `docs/PROJECT_MAP.md`, and refreshed AI context | macOS, Linux, Windows | v0.8 | `npm run quiver:analyze` |
 | `quiver:flow` | Runs the guided flow entrypoint through the generated npm script | macOS, Linux, Windows | v0.11 | `npm run quiver:flow` |
+| `quiver:dashboard` | Runs the consolidated read-only dashboard through the generated npm script | macOS, Linux, Windows | next | `npm run quiver:dashboard -- --json` |
 | `quiver:prepare` | Runs guided setup diagnostics and context preparation | macOS, Linux, Windows | v0.10 | `npm run quiver:prepare -- --dry-run --provider codex` |
 | `quiver:doctor` | Validates the Quiver contract and reports layout or migration guidance | macOS, Linux, Windows | v0.8 | `npm run quiver:doctor` |
 | `quiver:doctor -- --json` | Emits the Doctor checks and suggested fixes as stable machine-readable JSON | macOS, Linux, Windows | next | `npm run quiver:doctor -- --json` |
@@ -95,12 +101,15 @@ This document is the canonical command reference for the orchestration roadmap.
 | `--output <file>` | `evidence run` | Write the evidence Markdown file to an explicit path instead of `.quiver/evidence/` |
 | `--max-output <n>` | `evidence run` | Limit captured stdout and stderr characters per section |
 | `--dir <target>` | `demo create spec-viewer` | Select the demo target directory; default is `./quiver-spec-viewer` |
-| `--json` | `plan`, `graph`, `next` | Emit machine-readable JSON |
+| `--json` | `dashboard`, `version`, `plan`, `graph`, `next` | Emit machine-readable JSON |
+| `--details` | `dashboard` | Show the full human dashboard report instead of the compact default; incompatible with `--json` and `--section` |
+| `--section <name>` | `dashboard` | Show one human dashboard section; incompatible with `--json` and `--details` |
+| `--limit <n>` | `dashboard` | Limit compact dashboard lists between 1 and 100; incompatible with `--json` |
 | `--all-ready` | `next` | List all ready slices instead of just the next one |
 | `--only-ready` | `plan` | Show only slices with no pending dependencies |
-| `--include-completed` | `plan`, `graph`, `next` | Include completed slices for audit/demo history without changing default pending-only behavior |
+| `--include-completed` | `dashboard`, `plan`, `graph`, `next` | Include completed slices for audit/demo history without changing default pending-only behavior |
 | `--local` | `check-slice` | Run structural validation without remote/base checks; use normal mode before PR readiness |
-| `--spec <slug>` | `plan`, `graph`, `spec create` | Restrict output to one spec or override the generated spec slug |
+| `--spec <slug>` | `dashboard`, `plan`, `graph`, `spec create` | Restrict output to one spec or override the generated spec slug |
 | `--format <tree\|mermaid\|dot\|json\|markdown>` | `graph`, `ai export` | Select graph or lifecycle export output format |
 | `--provider <codex\|claude\|gemini>` | `ai onboard`, `ai plan`, `ai revise`, `ai review-plan`, `ai execute-slice`, `ai execute-plan` | Select the local AI CLI adapter |
 | `--model <model-id>` | `ai agent set`, provider-backed AI commands | Store or pass the technical model id. Quiver normalizes known display aliases, but the catalog is known by Quiver and does not guarantee account availability |
@@ -146,6 +155,8 @@ This document is the canonical command reference for the orchestration roadmap.
 - `init --interactive` and `spec create --interactive` are human-only wrappers. They fail in no-TTY/CI/JSON and always keep `WDD + SDD` as the only methodology option.
 - Quiver human output uses the palette `#86C8F2`, `#6BADEB`, `#7F9EE8`, `#9B82E6`, and `#D56AB0`; respect `--no-color`, `NO_COLOR`, CI, and no-TTY environments.
 - `quiver:flow` reports the detected package manager and the matching generated project script, for example `npm run quiver:flow`, `pnpm run quiver:flow`, `yarn run quiver:flow`, or `bun run quiver:flow`.
+- `quiver:version` prints the Quiver-branded version report; `--json` emits schema version 1 for automation and the top-level `--version` / `-V` semver flags stay unchanged.
+- `quiver:dashboard` reports compact read-only project, spec, slice, run, approval, and agent status by default; use `--details` for the full human report, `--section <name>` for focused inspection, and `--json` for schema version 1 automation.
 - `npx create-quiver ai models list` shows the local catalog of provider/model ids known by Quiver. It does not prove account-level access in Codex, Claude, or Gemini.
 - Agent profiles separate `model` and `displayName`: `model` is the technical id passed to the provider CLI, while `displayName` is the human label used in selectors and reports.
 - `quiver:ai:agent -- set ... --dry-run` previews provider/model profile changes without writing `.quiver/agents/profiles.json`.

package/docs/CONTEXTO.md.es.template

@@ -0,0 +1,33 @@
+# Contexto de {{PROJECT_NAME}}
+
+## Que es {{PROJECT_NAME}}?
+
+[Uno o dos parrafos que expliquen el proyecto.]
+
+## Propuesta de valor
+
+> "[Frase principal del proyecto]"
+
+## Usuario objetivo
+
+[Describe el usuario principal.]
+
+## Foco actual
+
+- [Objetivo actual 1]
+- [Objetivo actual 2]
+- [TODO: confirmar contexto antes de ampliar alcance]
+
+## Donde vive el stack
+
+El stack, package manager y comandos se generan en `docs/PROJECT_MAP.md` despues de ejecutar `analyze`.
+
+## Seguridad y privacidad
+
+- [Datos sensibles que nunca se guardan]
+- [Datos que si se guardan]
+- [Medida de seguridad importante]
+
+## Proximo paso
+
+Si sos agente IA, lee `AI_CONTEXT.md`. Si sos humano, usa `INDEX.md` para navegar la documentacion.

package/docs/DECISIONS.md.es.template

@@ -0,0 +1,17 @@
+# Registro de decisiones de {{PROJECT_NAME}}
+
+**Fecha:** {{FECHA}}
+**Estado:** {{ESTADO}}
+
+Este archivo registra decisiones durables para que agentes y personas no vuelvan a discutir elecciones ya tomadas.
+
+## Registro
+
+| Fecha | Decision | Razon | Alternativas | Impacto |
+|---|---|---|---|---|
+
+## Reglas
+
+- Registra una decision por fila.
+- Manten cada entrada corta y especifica.
+- Agrega una nueva fila cuando una eleccion pueda reabrirse en trabajos futuros.

package/docs/GITFLOW_PR_GUIDE.md.es.template

@@ -0,0 +1,25 @@
+# Guia Git y PR
+
+## Reglas principales
+
+- Un slice equivale a un commit.
+- Un spec equivale a un PR.
+- No mezclar specs en la misma branch.
+- No abrir PR sin evidencia de validacion.
+
+## Preflight de PR
+
+```bash
+npx create-quiver ai pr --dry-run --ssh-host-alias <alias> --identity-file <key> --input <pr.md>
+```
+
+## Secciones requeridas del PR
+
+- `## Title`
+- `## Summary`
+- `## Scope`
+- `## Files`
+- `## How to Test (DETAILED - REQUIRED)`
+- `## Evidence`
+- `## Rollback`
+- `## Risks / Notes`

package/docs/INDEX.md

@@ -0,0 +1,96 @@
+# Quiver Documentation Index
+
+**Last updated:** 2026-05-29
+
+Use this file as the first documentation map before planning, implementing, reviewing, or opening PRs in this repository. Prefer the smallest set of linked documents that fits the task.
+
+## Start Here
+
+- **Public overview:** [`../README.md`](../README.md)
+- **AI guide:** [`../README_FOR_AI.md`](../README_FOR_AI.md)
+- **CLI UX standards:** [`./CLI_UX_GUIDE.md`](./CLI_UX_GUIDE.md)
+- **Command reference:** [`./reference/commands.md`](./reference/commands.md)
+- **Troubleshooting:** [`./TROUBLESHOOTING.md`](./TROUBLESHOOTING.md)
+- **Git and PR workflow:** [`./GITFLOW_PR_GUIDE.md`](./GITFLOW_PR_GUIDE.md)
+
+## Getting Started
+
+- **Install and npx behavior:** [`./getting-started/installation.md`](./getting-started/installation.md)
+- **macOS setup:** [`./getting-started/macos.md`](./getting-started/macos.md)
+- **Linux setup:** [`./getting-started/linux.md`](./getting-started/linux.md)
+- **Windows PowerShell setup:** [`./getting-started/windows-powershell.md`](./getting-started/windows-powershell.md)
+- **Windows Git Bash / WSL setup:** [`./getting-started/windows-git-bash-wsl.md`](./getting-started/windows-git-bash-wsl.md)
+
+## Workflows
+
+- **New project:** [`./workflows/new-project.md`](./workflows/new-project.md)
+- **Existing project:** [`./workflows/existing-project.md`](./workflows/existing-project.md)
+- **Legacy Quiver project:** [`./workflows/legacy-quiver-project.md`](./workflows/legacy-quiver-project.md)
+- **Full AI spec-to-PR flow:** [`./workflows/full-ai-spec-to-pr.md`](./workflows/full-ai-spec-to-pr.md)
+
+## AI Configuration
+
+- **AI principles:** [`./ai/PRINCIPLES.md`](./ai/PRINCIPLES.md)
+- **AI rules:** [`./ai/RULES.yaml`](./ai/RULES.yaml)
+
+## Specs
+
+Canonical specs live outside `docs/` in [`../specs/`](../specs/).
+
+Recent specs:
+
+- [`../specs/quiver-v45-ci-actions-node24-readiness/SPEC.md`](../specs/quiver-v45-ci-actions-node24-readiness/SPEC.md)
+- [`../specs/quiver-v44-provider-live-output-tui-lite/SPEC.md`](../specs/quiver-v44-provider-live-output-tui-lite/SPEC.md)
+- [`../specs/quiver-v43-cli-i18n-audit-release-readiness/SPEC.md`](../specs/quiver-v43-cli-i18n-audit-release-readiness/SPEC.md)
+- [`../specs/quiver-v42-cli-i18n-generated-docs/SPEC.md`](../specs/quiver-v42-cli-i18n-generated-docs/SPEC.md)
+- [`../specs/quiver-v41-cli-i18n-ai-lifecycle/SPEC.md`](../specs/quiver-v41-cli-i18n-ai-lifecycle/SPEC.md)
+- [`../specs/quiver-v40-cli-i18n-spec-slice-workflows/SPEC.md`](../specs/quiver-v40-cli-i18n-spec-slice-workflows/SPEC.md)
+- [`../specs/quiver-v39-cli-i18n-setup-onboarding/SPEC.md`](../specs/quiver-v39-cli-i18n-setup-onboarding/SPEC.md)
+- [`../specs/quiver-v38-cli-i18n-read-only-commands/SPEC.md`](../specs/quiver-v38-cli-i18n-read-only-commands/SPEC.md)
+- [`../specs/quiver-v37-cli-i18n-foundation/SPEC.md`](../specs/quiver-v37-cli-i18n-foundation/SPEC.md)
+- [`../specs/quiver-v36-ai-run-watch-portable/SPEC.md`](../specs/quiver-v36-ai-run-watch-portable/SPEC.md)
+- [`../specs/quiver-v35-compact-dashboard-version-ux/SPEC.md`](../specs/quiver-v35-compact-dashboard-version-ux/SPEC.md)
+- [`../specs/quiver-v34-cli-dashboard-status/SPEC.md`](../specs/quiver-v34-cli-dashboard-status/SPEC.md)
+
+For implementation work, read the target spec and the target slice's `slice.json`, `EXECUTION_BRIEF.md`, and `CLOSURE_BRIEF.md` only.
+
+## Templates
+
+These files are templates for generated projects or optional profiles. Do not treat them as concrete project state unless the task is about templates or init output:
+
+- [`./AI_CONTEXT.md.template`](./AI_CONTEXT.md.template)
+- [`./AI_ONBOARDING_PROMPT.md.template`](./AI_ONBOARDING_PROMPT.md.template)
+- [`./COMMANDS.md.template`](./COMMANDS.md.template)
+- [`./CONTEXTO.md.template`](./CONTEXTO.md.template)
+- [`./DECISIONS.md.template`](./DECISIONS.md.template)
+- [`./DOCUMENTATION_GUIDE.md.template`](./DOCUMENTATION_GUIDE.md.template)
+- [`./STATUS.md.template`](./STATUS.md.template)
+- [`./SUPPORT_MATRIX.md.template`](./SUPPORT_MATRIX.md.template)
+- [`./TESTING_GUIDE_FOR_AI.md.template`](./TESTING_GUIDE_FOR_AI.md.template)
+- [`./WORKFLOW.md.template`](./WORKFLOW.md.template)
+- [`./ai/LESSONS.md.template`](./ai/LESSONS.md.template)
+
+## Task Routing
+
+- **Documentation/index work:** read this index, then the affected docs only.
+- **CLI UX, output, dashboard, or version work:** read [`./CLI_UX_GUIDE.md`](./CLI_UX_GUIDE.md), [`./reference/commands.md`](./reference/commands.md), and the relevant spec.
+- **Spec or slice execution:** read the relevant [`../specs/`](../specs/) package, especially the target slice files.
+- **PR creation:** read [`./GITFLOW_PR_GUIDE.md`](./GITFLOW_PR_GUIDE.md) and the relevant `pr.md`.
+- **Troubleshooting or install issues:** read [`./TROUBLESHOOTING.md`](./TROUBLESHOOTING.md) and the matching getting-started guide.
+- **AI agent behavior:** read [`../README_FOR_AI.md`](../README_FOR_AI.md), [`./ai/PRINCIPLES.md`](./ai/PRINCIPLES.md), and [`./ai/RULES.yaml`](./ai/RULES.yaml).
+
+## Known Documentation Debt
+
+The following concrete docs are referenced by templates or generated-project guidance but do not currently exist as repository docs:
+
+- `docs/CONTEXTO.md`
+- `docs/WORKFLOW.md`
+- `docs/STATUS.md`
+- `docs/SUPPORT_MATRIX.md`
+- `docs/TESTING_GUIDE_FOR_AI.md`
+- `docs/AI_CONTEXT.md`
+- `docs/AI_ONBOARDING_PROMPT.md`
+- `docs/DECISIONS.md`
+- `docs/ai/LESSONS.md`
+
+Use the `.template` files only when the task is about generated project output or template maintenance.

package/docs/INDEX.md.es.template

@@ -0,0 +1,36 @@
+# Indice de documentacion de {{PROJECT_NAME}}
+
+**Ultima actualizacion:** {{FECHA}}
+
+## Empezar aca
+
+- **Contexto** - `./CONTEXTO.md`
+- **Contexto para IA** - `./AI_CONTEXT.md`
+- **Decisiones** - `./DECISIONS.md`
+- **Prompt de onboarding IA** - `./AI_ONBOARDING_PROMPT.md`
+- **Workflow** - `./WORKFLOW.md`
+- **Comandos** - `./COMMANDS.md`
+- **Matriz de soporte** - `./SUPPORT_MATRIX.md`
+- **Troubleshooting** - `./TROUBLESHOOTING.md`
+
+## Configuracion de IA
+
+- **Principios** - `./ai/PRINCIPLES.md`
+- **Reglas** - `./ai/RULES.yaml`
+- **Lecciones** - `./ai/LESSONS.md`
+
+## Mapa del proyecto
+
+`docs/PROJECT_MAP.md` se crea con:
+
+```bash
+npx create-quiver analyze
+```
+
+Usalo despues del analisis para stack, package manager, comandos y pistas de archivos.
+
+## Docs opcionales y perfiles
+
+- `npx create-quiver init --full` agrega notas multi-agente, ejemplos y assets iniciales de spec.
+- Los specs y slices reales se crean despues de aprobar criterios y plan tecnico con `npx create-quiver spec create`.
+- Los wrappers Bash heredados solo se agregan con `--full` o `--legacy-scripts`.

package/docs/STATUS.md.es.template

@@ -0,0 +1,28 @@
+# Estado de {{PROJECT_NAME}}
+
+Este archivo registra progreso, bloqueos y slice actual. Stack y comandos viven en `docs/PROJECT_MAP.md`.
+
+## Estado general
+
+- Progreso: {{X}}% completo
+- Fase actual: {{FASE}}
+- Proximo hito: [Descripcion]
+
+## Resumen de slices
+
+Todavia no hay slices de implementacion. Crea specs y slices solo despues de aprobar criterios de aceptacion y plan tecnico.
+
+| Slice | Titulo | Estado | Progreso | Spec |
+|---|---|---|---|---|
+| slice-00 | Fundacion documental | Pendiente | 0% | `specs/<spec>/slices/slice-00-.../slice.json` |
+
+## Bloqueos
+
+| Bloqueo | Impacto | Mitigacion |
+|---|---|---|
+| - | - | - |
+
+## Notas
+
+- Actualiza este archivo al cerrar cada slice.
+- Registra incertidumbre con `TODO`, `Assumption` o `Pending confirmation`.

package/docs/SUPPORT_MATRIX.md.es.template

@@ -0,0 +1,22 @@
+# Matriz de soporte
+
+**Proyecto:** {{PROJECT_NAME}}
+**Ultima actualizacion:** {{FECHA}}
+
+## Entornos soportados
+
+| Area | Soportado | Notas |
+|---|---|---|
+| Sistemas operativos | macOS, Linux y Windows | Runtime principal: Node CLI y scripts `quiver:*`. |
+| Shells | Terminal, shells compatibles con bash, PowerShell y CMD | Bash es compatibilidad heredada, no dependencia obligatoria. |
+| Git | Git 2.40+ | Debe soportar worktrees y refs estandar. |
+| Node.js | Node 22.x LTS | Requerido en todos los OS soportados. |
+| Branch base | `develop` o `main` | Preferir branch local; `origin` es opcional. |
+| Estado del worktree | Limpio | La ejecucion de slices espera no mezclar cambios. |
+
+## Reglas cross-platform
+
+- Usar APIs Node para paths y filesystem.
+- Mantener `--json` como contrato primario de automatizacion.
+- Respetar `NO_COLOR`, CI y terminales sin TTY.
+- No concatenar prompts largos en comandos shell.

package/docs/TESTING_GUIDE_FOR_AI.md.es.template

@@ -0,0 +1,19 @@
+# Guia de testing para IA
+
+**Proyecto:** {{PROJECT_NAME}}
+**Ultima actualizacion:** {{FECHA}}
+
+## Reglas
+
+- Ejecuta primero tests focalizados del slice.
+- Ejecuta validacion amplia solo cuando el cambio toque superficie compartida.
+- No inventes comandos; usa los documentados en `docs/PROJECT_MAP.md` o `package.json`.
+- Registra evidencia en el spec o slice correspondiente.
+
+## Comandos sugeridos
+
+```bash
+npm test
+npx create-quiver spec validate specs/<spec> --strict
+git diff --check
+```

package/docs/TROUBLESHOOTING.md.es.template

@@ -0,0 +1,35 @@
+# Troubleshooting
+
+**Proyecto:** {{PROJECT_NAME}}
+**Ultima actualizacion:** {{FECHA}}
+
+Usa esta guia cuando falle bootstrap, validacion o ejecucion de Quiver.
+
+## Quiver no aparece en node_modules
+
+### Sintoma
+
+- `npx --yes create-quiver@latest ...` funciona.
+- `node_modules/create-quiver` no existe.
+- `package.json` no declara `create-quiver`.
+
+### Recuperacion
+
+1. Esto es esperado cuando se usa `npx`.
+2. Usa `npx --yes create-quiver@latest` para ejecutar la version publicada mas reciente.
+3. Instala localmente solo si el equipo quiere un workflow pineado:
+
+```bash
+npm install --save-dev create-quiver
+```
+
+## Falta branch base
+
+### Sintoma
+
+- `start-slice` no encuentra `develop` o `main`.
+
+### Recuperacion
+
+1. Crea o fetchea la branch base.
+2. Vuelve a ejecutar la validacion del slice.