@tacuchi/agent-workflow-cli 20.6.0 → 20.8.1

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@tacuchi/agent-workflow-cli",
-  "version": "20.6.0",
-  "description": "Agnostic runtime CLI for AI development workflows — a stages + loops + artifacts harness. Bundles the universal `w` skill set under `skills/w/` (slash commands `/w:*`: spec-new/spec-refine, plan-new/plan-exec, quick, workspace-init, export-*); `self install --target <host>` copies SKILL + commands + hooks into the host. Pluggable capability skills via `.workflow/skills.toml`. Multi-empresa parametrization via `profile.json` cascade. Namespace auto-detected from any `.<ns>/sessions/` dir in CWD; default `workflow`.",
+  "version": "20.8.1",
+  "description": "Runtime CLI for Workline — the stages + loops + artifacts system for agent work. Bundles the universal `w` skill set under `skills/w/` (slash commands `/w:*`: spec-new/spec-refine, plan-new/plan-exec, quick, persist, workspace-init, export-*); `self install --target <host>` copies SKILL + commands + hooks into the host. Pluggable capability skills via `.workflow/skills.toml`. Multi-empresa parametrization via `profile.json` cascade. Namespace auto-detected from any `.<ns>/sessions/` dir in CWD; default `workflow`.",
   "type": "module",
   "bin": {
     "agent-workflow": "dist/cli/main.js",

package/skills/w/README.md

@@ -1,6 +1,6 @@
-# w — agent-workflow skill bundle
+# w — Workline skill bundle
 
-> The `w` bundle (`w` = *workflow*) packages the agent-workflow harness as Claude Code skills + `/w:` slash commands. Runtime: [`@tacuchi/agent-workflow-cli`](../../README.md) (`agent-workflow` / `aw`).
+> The `w` bundle (`w` = *workline*) packages **Workline** — the stages + loops + artifacts system for agent work — as Claude Code skills + `/w:` slash commands. Runtime: [`@tacuchi/agent-workflow-cli`](../../README.md) (`agent-workflow` / `aw`).
 
 It implements the **stages + loops + artifacts** model. The design source lives under `docs/referencias/` in the agent-workflow hub. This README is the bundle index; the normative text lives in its canonical docs:
 

package/skills/w/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: w
 description: >-
-  Orientation skill for the whole agent-workflow harness — built-in default for the
-  `overview` role. Load this to understand the model end-to-end: the 3-layer
+  Orientation skill for Workline (`w` = *workline*), the whole system — built-in
+  default for the `overview` role. Load this to understand the model end-to-end: the 3-layer
   architecture (commands → loops → sessions/artifacts) plus the docs/ zone, the 3
   flows (SPEC / PLAN / QUICK), the `/w:` commands, the 5 loops and their chassis, the
   `export-*` family, the composable capability skills + `.workflow/skills.toml`
@@ -11,7 +11,7 @@ description: >-
   skill to reach for.
 ---
 
-# w — agent-workflow overview
+# w — Workline overview
 
 ## Role
 
@@ -19,7 +19,7 @@ description: >-
 
 ## Purpose
 
-Explain the **complete model** of agent-workflow so an agent knows: what the user invokes, what the AI runs, where every deliverable lands, and which rules never break. This is the map; the fine detail lives in each loop/command/export/role.
+Explain the **complete model** of Workline so an agent knows: what the user invokes, what the AI runs, where every deliverable lands, and which rules never break. This is the map; the fine detail lives in each loop/command/export/role.
 
 ## Composed by
 
@@ -48,7 +48,7 @@ USER invokes
         │ the export-* read the artifacts
         ▼
   docs/ ZONE — permanent, user-facing documents
-    specs · plans (flows) · scripts · manuals · diagrams · reports (export-*) · tools (ambient)
+    specs · plans (flows) · research (persist / no-flow) · scripts · manuals · diagrams · reports (export-*) · tools (ambient)
 ```
 
 - **Layer 1** — high level. Single-pass or starts a loop. No iteration logic.
@@ -75,7 +75,7 @@ Before any loop, the AI resolves its **operating context** on **every prompt** w
 |---|---|---|
 | **Yes** | **flow command** (`quick`·`spec-*`·`plan-*`) | **new work line** → creates a **new** session (except re-running the same flow over the same input: `create_or_resume` reopens the existing one), starts the loop → artifacts go to **that** session (`SCRIPTS.sql`, …) |
 | **Yes** | **prompt with no command** (related) | **continues/reopens the most recent session** → scripts edit **its** `SCRIPTS.sql` (no new session) |
-| **Yes** | **prompt with no command** (unrelated / no session) | **no flow**: direct work → writes into `docs/` by convention + numbering (`aw next-number`) |
+| **Yes** | **prompt with no command** (unrelated / no session) | **no flow**: direct work → writes into `docs/` by convention + numbering (`aw next-number`). To persist work already done in this conversation, `/w:persist` classifies and routes it (`docs/research` · spec draft · plan adoption) |
 | **No** | anything | **vanilla** — no workspace, no flow; the AI is free (native) |
 
 **Continuity rule** (single source — the chassis and the loops reference here):
@@ -89,6 +89,10 @@ Before any loop, the AI resolves its **operating context** on **every prompt** w
 
 It is the **inter-turn** face of the *persistent objective* (same `CHECKPOINT`+resume, applied to the next prompt) — agnostic doctrine, not a host hook. It applies to **every artifact** (`SCRIPTS.sql` is the worked example; QUICK case: `loops/quick-loop/LOOP.md`).
 
+### Host as producer — adopted context
+
+The flows are **composable with host-native work, never exclusive**. The host is not only the executor of the loops: it is a legitimate **producer** of input. Work products born in the host conversation — an analysis reached with a host feature, a plan built in the host's plan mode, settled conclusions — are first-class flow input via **adoption**: transcribe with provenance (`## Origin` = adopted from the host conversation), verify like any other input (gate integrity), and never re-derive or re-ask what is already settled. Entry points: any loop start (adopted context — `loops/CHASSIS.md` § *Adopted context*), `plan-new` input mode 4 (adopt an external plan), and `/w:persist` (classify + persist finished work into `docs/`).
+
 ### The commands (`/w:` namespace)
 
 - `/w:workspace-init` — initializes the workspace.
@@ -100,17 +104,18 @@ It is the **inter-turn** face of the *persistent objective* (same `CHECKPOINT`+r
 - `/w:quick` — starts `quick-loop` (shortcut, no `docs/`; escalates live to SPEC when the objective exceeds a quick).
 - `/w:export-scripts` · `/w:export-manuals` · `/w:export-diagrams` · `/w:export-reports` — promote artifacts to `docs/`.
 
-### Transversal skills (no flow) — `/w:status` · `/w:fix-git` · `/w:generate-launch`
+### Transversal skills (no flow) — `/w:status` · `/w:fix-git` · `/w:generate-launch` · `/w:persist`
 
 **Flow-independent invocable** skills: triggered with `/w:` like any command, but they do **not** belong to SPEC/PLAN/QUICK, do **not** manage `docs/`, and do **not** count in **6 flow commands / 5 loops**. *(In the bundle they are packaged under `commands/` so `/w:` can invoke them; in the design they are the `workflow-skills/` category.)*
 
 - `/w:status` — read-only workspace dashboard (Done/Missing/Discarded, dates humanized in the user's language). Writes nothing; backed by `aw status`.
 - `/w:fix-git` — resolves an in-progress merge's conflicts in any repo (identifies origin↔destination, analyzes intent, *structured-choice* on ambiguity). No session, never touches `docs/`; git-safe; backed by `aw merge-state`.
 - `/w:generate-launch` — (re)generates the per-source launch scripts (`.workflow/launch/<alias>/`) by detecting each source's stack; idempotent (preserves hand-edited scripts, `--force` overwrites). Complements the launch flow's on-demand generation. No session, never touches `docs/`; backed by `aw generate-launch`.
+- `/w:persist` — persists work **already done in this conversation** (an analysis, conclusions, a plan) into `docs/`: classifies its shape and routes it — analysis/conclusions → `docs/research/` · requirement-shaped → spec draft (`spec-new` procedure) · plan-shaped → plan adoption (`plan-new` mode 4) — with `## Origin` + attribution (host · model · date) and the anti-duplicate check. Never creates sessions; the host→`docs/` counterpart of `export-*` (which stays the only session→`docs/` path).
 
 ### The loops (Layer 2)
 
-A loop is a skill that teaches the AI **how to iterate** to a deliverable: detect gaps, resolve them (human via structured-choice, inline research or a composed capability), integrate and repeat until convergence. The 5 loops run the same **common engine** — persistent objective + verification-first, gap-driven convergent, single session per run, structured-choice + `flow` control (`Compactar`/`Cerrar`), compact/resume, artifacts as a live log, convergence gate — whose canon lives in [`loops/CHASSIS.md`](loops/CHASSIS.md); each loop is an **heir** adding only its deltas.
+A loop is a skill that teaches the AI **how to iterate** to a deliverable: detect gaps, resolve them (human via structured-choice, inline research, a small probe/PoC or a composed capability), integrate and repeat until convergence. The 5 loops run the same **common engine** — persistent objective + verification-first, gap-driven convergent, single session per run, structured-choice + `flow` control (`Compactar`/`Cerrar`), compact/resume, artifacts as a live log, convergence gate — whose canon lives in [`loops/CHASSIS.md`](loops/CHASSIS.md); each loop is an **heir** adding only its deltas.
 
 The **code-editing** loops (`plan-exec-loop`, `quick-loop`) additionally apply the *code-editing loop policies*: safe git, DB scripts-only and the pre-commit **closing review gate** (nothing reaches a proposed commit unreviewed) — see [`loops/CODE-POLICIES.md`](loops/CODE-POLICIES.md) (the chassis' sibling doc; document loops do not load it).
 
@@ -154,7 +159,7 @@ Role catalog and defaults:
 | `diagrams` | `diagrams` | should | `export-diagrams` |
 | `overview` | `w` | should | anyone (orientation) |
 
-> **Ambient conventions (not roles):** code/testing/writing standards and `creating-tools` are standalone skills the host auto-discovers by `description` — the workflow neither binds nor depends on them. Full doctrine: [roles/README.md](roles/README.md).
+> **Ambient conventions (not roles):** code/testing/writing standards and `creating-tools` are standalone skills the host auto-discovers by `description` — Workline neither binds nor depends on them. Full doctrine: [roles/README.md](roles/README.md).
 
 The **loop chassis** is NOT bound: it is the common engine of the 5 loops ([`loops/CHASSIS.md`](loops/CHASSIS.md), a referenced doc), not a pluggable capability.
 
@@ -185,7 +190,7 @@ One language per plane — never mix them:
 ### The 6 hard invariants
 
 1. **No auto-export** — loops never graduate/export to `docs/`. Only `export-*` does, explicitly.
-2. **Each flow touches only its `docs/` folders** — SPEC→`specs` · PLAN→`plans` · QUICK→none · rest→`export-*`. (`docs/tools` belongs to no flow: the ambient skill `creating-tools` writes it.)
+2. **Each flow touches only its `docs/` folders** — SPEC→`specs` · PLAN→`plans` · QUICK→none · rest→`export-*`. (`docs/tools` and `docs/research` belong to no flow: `docs/tools` is written by the ambient skill `creating-tools`; `docs/research` by `/w:persist` or direct no-flow authoring.)
 3. **The spec and the plan are documents** (`docs/`), not session artifacts. *(Not to be confused with the **design SPECs** `NNN-SPEC-<SLUG>.md`: **per-screen** UI design artifacts that PLAN sessions produce via the `ui-design` capability when the plan includes UI — see `artifacts/artifacts-design/` — they are not the requirement-spec.)*
 4. **DB scripts-only** — the AI never executes DML/DDL; migrations stay in `SCRIPTS.sql` and the user applies them. Only read-only reads via MCP.
 5. **Safe git** — expected branch verified before editing; proposed commits per source; never `push`/`--amend`/`--no-verify`.

package/skills/w/artifacts/README.md

@@ -1,6 +1,6 @@
 # workflow-artifacts — Artifact catalog (Layer 3)
 
-> Reference for the agent-workflow model (current, deployed). This folder contains the **artifact templates**: process files managed by **sessions** inside `.workflow/sessions/`.
+> Reference for the Workline model (current, deployed). This folder contains the **artifact templates**: process files managed by **sessions** inside `.workflow/sessions/`.
 > Siblings: [`../commands/`](../commands/) (Layer 1) · [`../loops/`](../loops/) (Layer 2) · [`../roles/`](../roles/) (pluggable skills).
 
 ---
@@ -15,11 +15,11 @@ Central distinction of the model:
 | Location | `.workflow/sessions/NNN-…/` | `docs/<category>/` |
 | Who manages it | a **loop**, through a **session** | produced by a loop/command at "save" time |
 | User-facing | No (internal) | Yes |
-| Examples | `CHECKPOINT`, `ANALYSIS-FILE`, `CONCLUSIONS`, `SCRIPTS.sql`, `TASKS`, `DECISION`, `NNN-SPEC-<SLUG>.md` | `specs`, `plans`, `manuals`, `scripts`, `diagrams`, `reports` |
+| Examples | `CHECKPOINT`, `ANALYSIS-FILE`, `CONCLUSIONS`, `SCRIPTS.sql`, `TASKS`, `DECISION`, `NNN-SPEC-<SLUG>.md` | `specs`, `plans`, `research`, `manuals`, `scripts`, `diagrams`, `reports` |
 
 > An artifact may be **promoted** to a `docs/` document (e.g. `SCRIPTS.sql` → `docs/scripts/`) — but **only via dedicated `export-*` skills**, **never** automatically by the loops. The spec and the plan **are not** artifacts: they are documents.
 
-> **Routing by operating context** (canonical rules: [`../SKILL.md`](../SKILL.md) § *Operating context*): inside a flow → the **active/continued** session (a prompt with no command edits the most recent session's artifacts); workspace without flow → `docs/` by convention + numbering; no workspace → vanilla. Session→`docs/` promotion is still **only** via `export-*`.
+> **Routing by operating context** (canonical rules: [`../SKILL.md`](../SKILL.md) § *Operating context*): inside a flow → the **active/continued** session (a prompt with no command edits the most recent session's artifacts); workspace without flow → `docs/` by convention + numbering (or explicitly via [`/w:persist`](../commands/persist.md), which classifies in-conversation work and routes it — `docs/research` · spec draft · plan adoption); no workspace → vanilla. Session→`docs/` promotion is still **only** via `export-*`; persist is the **host→`docs/`** path (it never reads sessions).
 
 ---
 

package/skills/w/commands/README.md

@@ -1,6 +1,6 @@
 # w — Command map (Layer 1)
 
-> README of the `/w:` namespace (`w` = *workflow*): everything listed here is the **only thing the user invokes** directly. Commands are **Layer 1** — single-pass or they start a loop; no iteration logic.
+> README of the `/w:` namespace (`w` = *workline*): everything listed here is the **only thing the user invokes** directly. Commands are **Layer 1** — single-pass or they start a loop; no iteration logic.
 >
 > **Canon**: the full model (3 layers + `docs/` zone, the 3 flows, hard invariants) lives in [`../SKILL.md`](../SKILL.md); the **loop engine** in [`../loops/CHASSIS.md`](../loops/CHASSIS.md). This README is only the folder index.
 
@@ -24,6 +24,7 @@
 | [`status`](status.md) | Read-only workspace dashboard | single-pass (transversal) |
 | [`fix-git`](fix-git.md) | Resolves an in-progress merge, git-safe | single-pass (transversal) |
 | [`generate-launch`](generate-launch.md) | (Re)generates the per-source launch scripts (`.workflow/launch/<alias>/`) | single-pass (transversal) |
+| [`persist`](persist.md) | Persists in-conversation work into `docs/` (classify → `research` · spec draft · plan adoption) | single-pass (transversal) |
 | [`export-scripts`](export-scripts.md) | Promotes session SQL migrations to `docs/scripts/` | single-pass, read-only |
 | [`export-manuals`](export-manuals.md) | Generates manuals in `docs/manuals/` | single-pass, read-only |
 | [`export-diagrams`](export-diagrams.md) | Generates C4/mermaid diagrams in `docs/diagrams/` | single-pass, read-only |
@@ -31,7 +32,7 @@
 
 > **Intentional asymmetry:** in SPEC, `spec-new` generates the draft single-pass (no loop) and the loop lives in `spec-refine`; in PLAN, all 3 commands start loops. Total: **6 flow commands / 5 loops**.
 >
-> **Transversal (no flow):** `status`, `fix-git` and `generate-launch` belong to no SPEC/PLAN/QUICK flow and do not count in 6/5. In the design they are their own category (`workflow-skills/`); here they are packaged under `commands/` so `/w:` can invoke them — see [`../harness/HARNESS.md`](../harness/HARNESS.md) § *Command packaging*.
+> **Transversal (no flow):** `status`, `fix-git`, `generate-launch` and `persist` belong to no SPEC/PLAN/QUICK flow and do not count in 6/5. In the design they are their own category (`workflow-skills/`); here they are packaged under `commands/` so `/w:` can invoke them — see [`../harness/HARNESS.md`](../harness/HARNESS.md) § *Command packaging*.
 
 ## Schema of each command file
 

package/skills/w/commands/fix-git.md

@@ -1,5 +1,5 @@
 ---
-description: Resolves the conflicts of an in-progress merge for a given or detected source. Identifies origin (theirs) and destination (ours), analyzes both sides' intent and resolves; asks (structured-choice) on ambiguity or incoherence. Git-safe — proposes the merge commit, never push/--amend/--no-verify. Transversal (not a flow), no loop, no session, never touches docs/. Works in any git repo, no initialized workspace required.
+description: Use when a merge or rebase left conflicts to resolve. Resolves the conflicts of an in-progress merge for a given or detected source. Identifies origin (theirs) and destination (ours), analyzes both sides' intent and resolves; asks (structured-choice) on ambiguity or incoherence. Git-safe — proposes the merge commit, never push/--amend/--no-verify. Transversal (not a flow), no loop, no session, never touches docs/. Works in any git repo, no initialized workspace required.
 argument-hint: "[<source path | alias>]"
 allowed-tools:
   [

package/skills/w/commands/persist.md

@@ -0,0 +1,101 @@
+---
+description: Use when work already produced in this conversation (analysis, conclusions, a plan) should be saved into docs/ — classifies its shape and routes it. analysis → docs/research/ · requirement → spec draft (docs/specs) · plan → plan adoption (docs/plans). Transversal (no flow, no loop, no session); records ## Origin + attribution (host · model · date); anti-duplicate aware (update vs sibling perspective). The host→docs/ counterpart of export-*.
+argument-hint: [what to persist — empty = the conversation's latest finished deliverable]
+allowed-tools:
+  [
+    "Bash",
+    "Read",
+    "Write",
+    "Edit",
+  ]
+---
+
+# persist — persist in-conversation work into `docs/`
+
+Captures **work already produced in this conversation** — with or without host-native features (a `/goal` run, plan mode, plain chat analysis) — and persists it into `docs/`, classified by shape. It is the explicit form of *direct no-flow authoring* (`../SKILL.md` § *Operating context*, row 3) and the doctrinal entry for **host as producer** (`../loops/CHASSIS.md` § *Adopted context*).
+
+> **Hard floor — applies even if you read nothing beyond this file:**
+>
+> 1. **Adopt, don't re-derive** — single pass, **NO RESEARCH**: transcribe/organize what the conversation already established. New investigation is flow work (`spec-refine`, `quick`), never this command's.
+> 2. **Confirm before writing** — classification and destination go through **structured-choice** (recommendation first). Never write `docs/` silently.
+> 3. **Numbering via `aw next-number docs/<category>`** (it creates the folder when missing) — never invent numbers. **Never creates sessions** (sessions are loop-created only).
+> 4. **Language** — headings in English (parse contract); content in the **user's language**.
+
+## Input
+
+`$ARGUMENTS` names what to persist (or is empty → the conversation's most recent finished deliverable). The **source is the conversation itself**: what was analyzed, concluded, designed or planned up to this point. If nothing persistable exists yet, say so and stop — do not manufacture content.
+
+## Classification → routing
+
+Classify the content by **shape**, recommend the route, confirm via structured-choice:
+
+| Shape | Signals | Route |
+|---|---|---|
+| **Analysis / conclusions / design notes** | findings, comparisons, diagnoses, adjudications, recommendations | `docs/research/NNN-research-<slug>.md` (schema below) |
+| **Requirement** | describes a *wish*: what should exist/change, acceptance criteria derivable | **spec draft** via the [`spec-new`](spec-new.md) procedure (same schema, same NO RESEARCH), `## Origin` = "adopted from host conversation" → offer `/w:spec-refine` |
+| **Plan** | already answers the *how*: phases/tasks/solution — e.g. the host plan-mode output | **plan adoption** via [`plan-new`](plan-new.md) § *Input resolution* mode 4 (`docs/plans/PPP-plan-<slug>.md`) → offer `/w:plan-refine` / `/w:plan-exec` |
+| Mixed / ambiguous | e.g. analysis that ends in a requirement | structured-choice between the candidate routes (split is a valid option: research doc + spec draft referencing it) |
+
+Requires a **workspace** (`docs/` is the managed surface). Without one → degrade: propose `/w:workspace-init` or ask for an explicit destination path.
+
+## `docs/research/` — the analysis home (owned by this command)
+
+`docs/research` hosts standalone analyses: neither spec nor plan, but worth keeping. Written by this command (or by direct no-flow authoring following this same schema). Belongs to **no flow**; `export-*` never writes it; loops never read it implicitly (a flow uses it by **reference** — e.g. cited in a spec's `## Origin` or a quick prompt).
+
+```markdown
+# Research NNN — <slug>
+
+## Origin
+adopted from host conversation — <host> · <model> · <YYYY-MM-DD>
+(what prompted the analysis: goal, prior doc, question)
+
+## Objective
+The question/situation the analysis addresses. In the user's language.
+
+## Analysis
+The analysis, transcribed/organized (not re-derived).
+
+## Conclusions
+The settled conclusions — actionable, falsifiable where possible.
+
+## Perspectives        (opt. — multi-agent)
+### <host · model · YYYY-MM-DD>
+An additional agent's view on the same objective (see below).
+
+## Sources             (opt.)
+Docs / repos / prior research docs referenced (for a synthesis: the N crossed docs).
+
+## Open questions      (opt.)
+```
+
+## Anti-duplicate → update vs sibling perspective
+
+Before writing, scan `docs/research/*-research-*.md` for a doc whose `## Origin`/`## Objective` matches this objective. If one exists, **never** silently create a second: structured-choice —
+
+- **`Actualizar`** *(recommended when it is the same line of thought)* — correct/extend the existing doc in place (confirmation to overwrite).
+- **`Agregar perspectiva`** — append a `### <host · model · date>` subsection under `## Perspectives`: same objective, **different agent's view** (this is intentional and legitimate — the multi-host pattern below).
+- **`Documento nuevo`** — only if the objective genuinely differs.
+
+## Multi-host cross-analysis (the docs-mediated pattern)
+
+`docs/research` is git-shareable — unlike sessions (gitignored, machine-local, loop-owned). That makes it the exchange surface for **N agents analyzing the same situation**:
+
+1. **Each host** analyzes in-conversation, then runs `/w:persist` → first agent creates the research doc; the rest **add perspectives** (or sibling docs), always attributed (host · model · date).
+2. **The final cross**: the user picks the strongest host; its input is the N research docs/perspectives (referenced explicitly in the prompt or via this command's argument). The synthesis persists as a **new research doc** whose `## Origin` states "synthesis" and whose `## Sources` lists every doc/perspective crossed — attribution lets it weigh who concluded what.
+3. Sessions stay **out** of the exchange path — no concurrent-session doctrine is needed; hosts meet only in `docs/`.
+
+## What this command is NOT
+
+- **Not export-*** — it never reads sessions; `export-*` remains the only session→`docs/` path.
+- **Not a flow** — no loop, no session, no `CHECKPOINT`; single pass.
+- **Not research** — it investigates nothing (NO RESEARCH); it persists what already exists.
+
+## Plan mode
+
+Classifies the content, resolves `NNN`/destination (`aw next-number --dry-run`) and describes the doc it would write (or the update/perspective it would append) without writing anything.
+
+## Resources
+
+- Adopted-context doctrine: `../loops/CHASSIS.md` § *Adopted context* · `../SKILL.md` § *Host as producer*
+- Spec-draft procedure: [`spec-new.md`](spec-new.md) · Plan adoption: [`plan-new.md`](plan-new.md) § *Input resolution* (mode 4)
+- Session→docs counterpart: [`../exports/README.md`](../exports/README.md)

package/skills/w/commands/plan-exec.md

@@ -1,5 +1,5 @@
 ---
-description: Starts or resumes the execution loop (plan-exec-loop) over an existing plan. The real work happens here - code edits, proposed SQL scripts, created tools. Git-safe.
+description: Use when a plan is ready to implement — this is where the real work happens: code edits, proposed SQL scripts, created tools. Starts or resumes the execution loop (plan-exec-loop) over an existing plan. Git-safe (proposes commits, never push/--amend/--no-verify). Not for creating or refining the plan (plan-new / plan-refine).
 argument-hint: <docs/plans/PPP-plan-<slug>.md>
 allowed-tools:
   [
@@ -34,8 +34,9 @@ Starts or resumes `plan-exec-loop` (Layer 2), which executes the real work phase
 
 - Reads and updates `docs/plans/PPP-plan-<slug>.md` (living doc: phase/task state).
 - Edits code in the workspace sources (a single execution session per run; execution is still phase by phase, there is just no session per phase).
-- If it creates a tool/utility, the ambient `creating-tools` skill documents it in `docs/tools/` (auto-discovered; the workflow does not bind it).
+- If it creates a tool/utility, the ambient `creating-tools` skill documents it in `docs/tools/` (auto-discovered; Workline does not bind it).
 - **Closing review gate** at every phase boundary, **before proposing the commits**: re-reads the diff (independent pass) applying the **installed ambient conventions** and fixes or defers findings — nothing reaches a commit unreviewed (see `../loops/plan-exec-loop/LOOP.md` § *Delta 5*).
+- **Probe (PoC) tasks** run as throwaway code in the session folder — never committed; verdict recorded (`CONCLUSIONS`/`DECISION`), failed probes surface to the human (see `../loops/plan-exec-loop/LOOP.md` § *Delta 7*).
 - Proposes commits per source (git-safe: verifies the branch, proposes, never push/--amend/--no-verify).
 - Generates session artifacts (`DECISION`, `SCRIPTS.sql`) under `.workflow/sessions/`.
 - **Never exports** to `docs/scripts`, `docs/manuals`, `docs/diagrams`, `docs/reports` — the `export-*` do that as a separate step.

package/skills/w/commands/plan-new.md

@@ -1,5 +1,5 @@
 ---
-description: Starts or resumes the planning loop (plan-new-loop) from a spec. Turns the "what" (spec) into the "how" (plan). Ideal input: an already refined docs/specs/NNN-spec-<slug>.md.
+description: Use when a spec is ready to become an executable plan — not to refine an existing plan (plan-refine) nor execute one (plan-exec). Starts or resumes the planning loop (plan-new-loop) from a spec. Turns the "what" (spec) into the "how" (plan). Ideal input: an already refined docs/specs/NNN-spec-<slug>.md. Also adopts an externally-built plan (host plan mode, hand-written, another agent) as the plan-doc — mode 4 of its input resolution.
 argument-hint: <docs/specs/NNN-spec-<slug>.md | prompt>
 allowed-tools:
   [
@@ -28,6 +28,9 @@ The skill evaluates `$ARGUMENTS` (specs live in place — `docs/specs/NNN-spec-<
 1. **Refined spec** (`docs/specs/NNN-spec-<slug>.md` that **already has** `## Refinement decisions` / `## Q&A traceability`) → ideal. Proceed straight to `plan-new-loop`.
 2. **Draft spec** (same file, but **without** those two sections) → **soft-suggest** running `/w:spec-refine` first; planning over a solid spec produces better plans (the user may proceed anyway).
 3. **prompt** (no spec referenced) → propose using the SPEC flow; **by default launch `/w:spec-new`** with that prompt to create the draft, and continue the natural flow from there.
+4. **External plan content** — the argument/conversation carries an **already-built plan** (host plan mode output, hand-written, another agent's) → **adopt it**. Single pass, **NO RESEARCH**: materialize as `docs/plans/PPP-plan-<slug>.md` (`aw next-number docs/plans`), normalized to the rich-plan schema (`../loops/plan-new-loop/LOOP.md` § *Delta 1*) with only what the source provides. `## Origin` = "adopted from <source>" + attribution (host · model · date). Then offer `/w:plan-refine` (closes schema gaps) or `/w:plan-exec`. Anti-duplicate: a plan whose `## Origin` matches this objective → recommend resuming it, never a second one. Adoption **never regenerates over** an existing plan-doc.
+
+> **Mode 3 vs 4:** a prompt that *describes a wish* → SPEC (mode 3); content that *already is a plan* → adopt (mode 4). Doctrine: `../loops/CHASSIS.md` § *Adopted context*.
 
 > **Refined vs draft** is distinguished by the **presence** of `## Refinement decisions` / `## Q&A traceability` in the spec, never by the filename (there is no `-refined` anymore).
 
@@ -36,7 +39,7 @@ The skill evaluates `$ARGUMENTS` (specs live in place — `docs/specs/NNN-spec-<
 `plan-new-loop` is **not** a skill invocable by name — it is this command's operating manual (a sibling doc in the bundle). **Load it and execute it end to end**:
 
 1. **Read** `../loops/plan-new-loop/LOOP.md` (inside the installed `w` skill — e.g. `~/.claude/skills/w/loops/…`).
-2. **Follow** its instructions taking `$ARGUMENTS` as input (resolved per the 3 rules above): it detects state/resume, runs the gap-driven engine, creates and manages sessions, converges and reports.
+2. **Follow** its instructions taking `$ARGUMENTS` as input (resolved per the 4 rules above): it detects state/resume, runs the gap-driven engine, creates and manages sessions, converges and reports. *(Mode 4 — adoption — is single-pass: materialize + offer the next step; no loop is started.)*
 
 > Do not try `Skill: plan-new-loop` — it is not registered as a skill. The command **is** the entry; the loop is its body.
 
@@ -48,9 +51,13 @@ The plan is named `docs/plans/PPP-plan-<slug>.md`. `aw next-number docs/plans` r
 
 If the plan **includes UI**, the loop composes the `ui-design` capability and produces per-screen **design SPECs** (`NNN-SPEC-<SLUG>.md`) as artifacts of its session — the plan's UI Tasks reference them (see `../loops/plan-new-loop/LOOP.md` § *Delta 4* and `../artifacts/artifacts-design/SPEC.md`).
 
+## Risky assumptions → probe (PoC) tasks
+
+When the plan rests on a runnable unknown (external connection, SDK, UI behavior), the loop encodes an **early probe task** — or runs an inline probe if the solution itself depends on the answer (see `../loops/plan-new-loop/LOOP.md` § *Delta 5*; doctrine: `../loops/CHASSIS.md` § *Proof of concept*).
+
 ## Plan mode
 
-The skill resolves the input per the 3 rules above and describes the loop actions it would run, without starting the iteration.
+The skill resolves the input per the 4 rules above and describes the loop actions it would run (mode 4: the plan-doc it would materialize), without starting the iteration or writing files.
 
 ## Resources
 

package/skills/w/commands/plan-refine.md

@@ -1,5 +1,5 @@
 ---
-description: Starts or resumes the plan refinement loop (plan-refine-loop). An auxiliary, NOT mandatory step of the PLAN flow — refines an existing plan in place before executing it. Ideal input: a docs/plans/PPP-plan-<slug>.md already generated by plan-new.
+description: Use when an existing plan needs changes before executing — new requirements, scope tweaks — not to generate one (plan-new) nor execute it (plan-exec). Starts or resumes the plan refinement loop (plan-refine-loop). An auxiliary, NOT mandatory step of the PLAN flow — refines an existing plan in place. Input: a docs/plans/PPP-plan-<slug>.md — generated by plan-new, hand-written, or adopted from a host planner (plan-new mode 4 / persist).
 argument-hint: <docs/plans/PPP-plan-<slug>.md>
 allowed-tools:
   [
@@ -24,12 +24,14 @@ This command does not refine the plan itself: it delegates to `plan-refine-loop`
 > 4. **Language** — everything user-facing (questions, option labels, the plan's content) goes in the **user's language**.
 
 > **Not mandatory.** `plan-exec` runs **any** plan, refined or not — no gate requires passing through here. Use it only when the plan needs adjustments before executing.
+>
+> **Spec-less plans (hand-written / adopted).** A plan with no source spec is legitimate input. The coherence gate **degrades gracefully**: criteria trace to the plan's own `## Final behavior` / acceptance criteria instead of spec criteria — the "spec criteria uncovered" gap does not apply (see `../loops/plan-refine-loop/LOOP.md`).
 
 ## Input resolution
 
 The skill evaluates `$ARGUMENTS` (plans live in place — `docs/plans/PPP-plan-<slug>.md`; locate via the `docs/plans/PPP-plan-*.md` glob or the exact path):
 
-1. **Existing plan** (`docs/plans/PPP-plan-<slug>.md`) → proceed to `plan-refine-loop`.
+1. **Existing plan** (`docs/plans/PPP-plan-<slug>.md`) → proceed to `plan-refine-loop` — **regardless of provenance**: generated by `plan-new`, hand-written, or adopted from a host planner (existence is the only requirement).
 2. **No plan** (the arg references no plan, or none exists) → **soft-suggest** running `/w:plan-new` first (there is nothing to refine yet); the user decides.
 
 ## Run the loop

package/skills/w/commands/quick.md

@@ -1,5 +1,5 @@
 ---
-description: Lightweight shortcut for scoped work (fix, tweak, chore) that warrants no spec or plan. Starts quick-loop. Never touches docs/. If the objective exceeds a quick or the task grows, it escalates — to SPEC live (with consent), to PLAN deferred.
+description: Use when the user asks for a scoped, direct task — a fix, tweak, chore or small change that warrants no spec or plan (e.g. "fix this bug", "rename X", "tidy up Y"). Starts quick-loop with minimal ceremony; never touches docs/. If the objective exceeds a quick or the task grows, it escalates — to SPEC live (with consent), to PLAN deferred.
 argument-hint: <prompt with the scoped task>
 allowed-tools:
   [
@@ -33,6 +33,7 @@ For scoped, direct tasks that do not justify going through SPEC or PLAN. Creates
 ## What the loop does
 
 - Edits code in the workspace sources.
+- **Adopts prior context**: analysis/conclusions already established in this conversation (e.g. via a host-native feature) are **input** — seeded into the session with `## Origin` = adopted, never re-derived or re-asked (chassis § *Adopted context*).
 - Minimal session artifacts (lazy DECISION, proposed commit).
 - **Proportional closing review gate** before proposing the single commit: re-reads the diff applying the installed ambient conventions and fixes or defers (see `../loops/quick-loop/LOOP.md` § *Sequence*).
 - **Never touches `docs/`** and exports nothing.

package/skills/w/commands/spec-new.md

@@ -1,5 +1,5 @@
 ---
-description: Generates a specification draft (docs/specs/NNN-spec-<slug>.md) from a prompt, in a single pass. Step 1 of the SPEC flow; starts no loop.
+description: Use when the user wants to capture a NEW requirement, idea or wish as a spec — not to refine an existing draft (that's spec-refine). Generates a specification draft (docs/specs/NNN-spec-<slug>.md) from a prompt, in a single pass. Step 1 of the SPEC flow; starts no loop.
 argument-hint: <prompt with the requirement or idea>
 allowed-tools:
   [
@@ -34,7 +34,8 @@ Generates `docs/specs/NNN-spec-<slug>.md` in a single pass from the prompt in `$
 # Spec NNN — <slug>
 
 ## Origin            (opt.)
-Original prompt / prior doc / reference that originated the spec.
+Original prompt / prior doc / reference that originated the spec
+(e.g. "adopted from host conversation" when it captures an analysis already established there).
 
 ## Requirement
 The what + why (brief). In the user's language.
@@ -47,9 +48,19 @@ Systems / components / sources involved. Known constraints.
 - Out: what is NOT included
 
 ## Acceptance criteria
-- [ ] verifiable criterion 1 (EARS / Given-When-Then style recommended)
+- [ ] verifiable criterion 1 (EARS style recommended; behavioral ones expand in ## Scenarios)
 - [ ] verifiable criterion 2
 
+## Scenarios         (opt.)
+Behavior made concrete — GIVEN/WHEN/THEN/AND blocks; each traces to ≥1 acceptance criterion.
+
+### Scenario: <name>
+GIVEN <precondition>
+  AND <precondition>
+WHEN <action>
+THEN <observable outcome>
+  AND <outcome>
+
 ## Assumptions       (opt.)
 Assumed facts.
 
@@ -65,11 +76,14 @@ Pending doubts. ← the spec-refine-loop closes them.
 - No `Type` field — `plan-new` infers the how.
 - `Scope` always carries `Out` (what stays out).
 - **Acceptance criteria = static testable criteria** (the "what"): `plan-exec` validates them, but progress is tracked in the PLAN (its Tasks), never by ticking these `- [ ]` in the spec; the spec never mutates by execution, only by a re-refine.
+- **Scenarios = behavior made concrete** (uppercase GIVEN/WHEN/THEN/AND): draft them only when the prompt already describes behavior — deriving the rest is spec-refine work, not this command's.
 - If **UI** is involved, mention it in `Requirement`/`Context`; the `## UI spec` is authored in `spec-refine` (via the `ui-design` capability). "UI unspecified" is a first-class refinement gap.
 - The **gaps** the loop detects = weak sections of the schema (vague Requirement, Scope without `Out`, untestable criteria, open questions, undeclared assumptions, contradictions) **+ UI unspecified** when the requirement involves UI.
 - Equivalent alternative: the user creates the draft by hand. Both paths produce the same `docs/specs/NNN-spec-<slug>.md`.
 
 > **Reuse by escalation:** the live escalation from `/w:quick` (see [`../loops/quick-loop/LOOP.md`](../loops/quick-loop/LOOP.md) § *QUICK delta*) materializes its draft following **this same procedure** (steps 1-3: same schema, same NO RESEARCH single-pass hard rule), with `## Origin` = "escalated from `/w:quick`" + the original prompt. No need to type `/w:spec-new`: the consent in the structured-choice equals invoking it.
+>
+> **Reuse by adoption:** [`/w:persist`](persist.md) (requirement-shaped content) materializes its spec draft with this same procedure, with `## Origin` = "adopted from host conversation" + attribution. Paraphrasing conclusions **already established in this conversation** is still single-pass — adoption is transcription, not investigation (chassis § *Adopted context*).
 
 ## Plan mode
 

package/skills/w/commands/spec-refine.md

@@ -1,5 +1,5 @@
 ---
-description: Starts or resumes the specification refinement loop (spec-refine-loop). Input: docs/specs/NNN-spec-<slug>.md (a draft — from spec-new, hand-written, or materialized by the quick escalation). Updates docs/specs/NNN-spec-<slug>.md in place.
+description: Use when a spec draft exists and needs disambiguating or completing before planning (close open questions, sharpen criteria) — not for the first draft (that's spec-new). Starts or resumes the specification refinement loop (spec-refine-loop). Input: docs/specs/NNN-spec-<slug>.md (from spec-new, hand-written, or the quick escalation). Updates it in place.
 argument-hint: <docs/specs/NNN-spec-<slug>.md>
 allowed-tools:
   [

package/skills/w/commands/status.md

@@ -1,5 +1,5 @@
 ---
-description: Read-only workspace dashboard — what got done / what is missing / what was discarded, with dates humanized in the user's language. Backed by `aw status`. Transversal command (not a flow); writes nothing.
+description: Use when the user asks "what's the state", "what got done", or "where are we". Read-only workspace dashboard — what got done / what is missing / what was discarded, with dates humanized in the user's language. Backed by `aw status`. Transversal command (not a flow); writes nothing.
 argument-hint: (no arguments)
 allowed-tools:
   [

package/skills/w/commands/workspace-init.md

@@ -1,5 +1,5 @@
 ---
-description: Turns the current folder into an agent-workflow workspace (minimal scaffold — .workflow/sessions + skills.toml + WORKSPACE block + CLI-owned .gitignore; docs/ folders are born on demand). Replaces hub-init + project-init — no project/hub distinction. Run once before any flow; idempotent, re-running reconciles (prunes legacy empty scaffold).
+description: Use when starting Workline in a folder that has no workspace yet. Turns the current folder into an agent-workflow workspace (minimal scaffold — .workflow/sessions + skills.toml + WORKSPACE block + CLI-owned .gitignore; docs/ folders are born on demand). Replaces hub-init + project-init — no project/hub distinction. Run once before any flow; idempotent, re-running reconciles (prunes legacy empty scaffold).
 argument-hint: --source alias:path[:branch] [--proyecto <name>] [--main-branch <branch>] [--dry-run]
 allowed-tools:
   [
@@ -12,7 +12,7 @@ allowed-tools:
 
 # workspace-init — workspace bootstrap
 
-Runs `aw workspace-init` to turn the current folder into an agent-workflow workspace. A workspace has **1+ sources** (repos); "standalone" = a single source. There are no project/hub modes — the model is unified.
+Runs `aw workspace-init` to turn the current folder into a Workline workspace. A workspace has **1+ sources** (repos); "standalone" = a single source. There are no project/hub modes — the model is unified.
 
 ```bash
 aw workspace-init --source alias:path[:branch] [--proyecto <name>] [--main-branch <branch>] [--dry-run]

package/skills/w/exports/README.md

@@ -1,6 +1,6 @@
 # exports — `export-*` family (Layer 1)
 
-> This is the **bundle README** for the `export-*` family: the **only** path that promotes session artifacts to permanent `docs/` documents. Each export is invoked by the **user** (never by a loop) as a separate, explicit step.
+> This is the **bundle README** for the `export-*` family: the **only** path that promotes session artifacts to permanent `docs/` documents. Each export is invoked by the **user** (never by a loop) as a separate, explicit step. *(Host→`docs/` ingestion is a different plane: [`/w:persist`](../commands/persist.md) persists in-conversation work — it reads the conversation, never sessions, and owns `docs/research`.)*
 > Related layers: [`../commands/`](../commands/) (Layer 1 flows) · [`../loops/`](../loops/) (Layer 2, AI-driven) · artifacts live in `.workflow/sessions/` (Layer 3). Design reference: `docs/referencias/workflow-exports/`.
 >
 > **Namespace:** each export body is an **operating manual** (`EXPORT.md` — deliberately not a `SKILL.md`, so no host indexes it as a standalone skill). The user-invocable surface is the `/w:export-*` commands authored under [`../commands/`](../commands/), which read-and-follow the sibling `EXPORT.md` (per-host wrapper: see [`../harness/HARNESS.md`](../harness/HARNESS.md) § *Command packaging*).

package/skills/w/harness/HARNESS.md

@@ -1,10 +1,10 @@
 ---
 name: harness
 description: >-
-  Harness-agnostic capability layer for agent-workflow. Read-and-follow doc (not
+  Harness-agnostic capability layer for Workline. Read-and-follow doc (not
   invocable by name): defines the contract that keeps the tool harness-agnostic
   (Claude Code, Codex, Gemini/Antigravity, OpenCode, Crush, Warp/Oz, generic) without
-  giving up each harness's rich capabilities. Catalogs the capabilities the workflow
+  giving up each harness's rich capabilities. Catalogs the capabilities Workline
   depends on, binds each to the concrete mechanism of every harness (binding matrix),
   and fixes the two principles (capability-not-tool · progressive-enhancement).
   Referenced from SKILL.md (overview) and the loops when they name structured-choice /
@@ -13,7 +13,7 @@ description: >-
 
 # harness — harness-agnostic capability layer (cross-cutting)
 
-**Read-and-follow** doc (never invoked by name). Here lives the contract that keeps agent-workflow **harness-agnostic** (Claude Code, Codex, opencode, Gemini CLI, …) without giving up each harness's rich capabilities. Referenced from `../SKILL.md` (overview) and from the loops when they name a capability (`structured-choice`, `compaction`, …).
+**Read-and-follow** doc (never invoked by name). Here lives the contract that keeps Workline **harness-agnostic** (Claude Code, Codex, opencode, Gemini CLI, …) without giving up each harness's rich capabilities. Referenced from `../SKILL.md` (overview) and from the loops when they name a capability (`structured-choice`, `compaction`, …).
 
 ## The problem
 
@@ -30,7 +30,7 @@ The doctrine (commands + loops + artifacts) describes **what** the AI does, neve
 
 The capabilities the harness layer depends on, with their universal fallback (what is used when the harness offers nothing better):
 
-| Capability | What the workflow needs | Universal fallback (lowest common) |
+| Capability | What Workline needs | Universal fallback (lowest common) |
 |---|---|---|
 | **command-invocation** | the user triggers a flow by name (`spec-new`, `plan-exec`, …) | the user writes "run the `<cmd>` procedure" and the AI reads its doc |
 | **procedure-loading** | load a loop's/command's doctrine | the AI **reads the `.md`** of the loop and follows it (read-and-follow) |
@@ -59,7 +59,7 @@ Concrete mechanism per harness (**Jul-2026**, verified against official docs; `~
 | **enforcement (deny tool)** | `PreToolUse` → `permissionDecision:deny` / exit 2 | `PreToolUse` (**≈same protocol**) | `BeforeTool` → `decision:deny` / exit 2 | plugin `tool.execute.before` (`throw`) | `allowed_tools` (+ preliminary hooks) | allow/deny lists (**coarse**) | doctrine (git-safe #5) |
 | plugin / dist | `.claude-plugin` + marketplace | `.codex-plugin` + `/plugins` marketplace | Extension `gemini-extension.json` | JS/TS plugin (npm) | MCP + skills + config | Warp Drive | — |
 
-> **Notes (field research Jul-2026):** **`SKILL.md` skills** are the **universal** portable unit — **all six** harnesses support them (Codex added them Dec-2025; **`.agents/skills` is the cross-host anchor**, read by Codex/OpenCode/Crush/Warp). **Structured choice** (`AskUserQuestion`) remains **Claude Code / main-agent only** → elsewhere `structured-choice` degrades to numbered markdown. The **enforcement layer** (new row) is **NO longer Claude-exclusive**: Codex + Gemini use a near-identical protocol (`permissionDecision:deny` / exit 2) and OpenCode blocks via `throw` in a JS plugin; Crush/Warp only offer **coarse** allow/deny (no custom per-command logic) → there, conventions stay **advisory** + allow/deny lists. Enforced **plan mode** is never trusted for safety; git-safe (invariant #5) is our own. **MCP** is universal (each host its file/key). The **guaranteed floor** (last column) runs the full model.
+> **Notes (field research Jul-2026):** **`SKILL.md` skills** are the **universal** portable unit — **all six** harnesses support them (Codex added them Dec-2025; **`.agents/skills` is the cross-host anchor**, read by Codex/OpenCode/Crush/Warp). **Structured choice** (`AskUserQuestion`) remains **Claude Code / main-agent only** → elsewhere `structured-choice` degrades to numbered markdown. The **enforcement layer** (new row) is **NO longer Claude-exclusive**: Codex + Gemini use a near-identical protocol (`permissionDecision:deny` / exit 2) and OpenCode blocks via `throw` in a JS plugin; Crush/Warp only offer **coarse** allow/deny (no custom per-command logic) → there, conventions stay **advisory** + allow/deny lists. Enforced **plan mode** is never trusted for safety; git-safe (invariant #5) is our own — though a host-planner's *output* (the plan it built) is adoptable input (`../commands/plan-new.md` § *Input resolution*, mode 4). **MCP** is universal (each host its file/key). The **guaranteed floor** (last column) runs the full model.
 
 > **Oz (Warp's cloud sibling).** `oz agent run` is a cloud agent orchestrator that **reuses Warp's surfaces**: same skills (`.agents/skills`, top-level dirs like Warp) and `AGENTS.md`, with `structured-choice` equally degraded to numbered markdown. It differs in three points: **detection** via `OZ_RUN_ID` (takes priority over Warp when both markers coexist); **MCP without a config file** — the JSON is passed via the `--mcp` flag of `oz agent run` (or the `OZ_MCP_CONFIG` env), it never writes `.warp/.mcp.json`; and **no plugin or hooks** (advisory enforcement, like Warp). Hence it shares the **Warp / Oz** column with that MCP caveat.
 
@@ -78,7 +78,7 @@ Concrete mechanism per harness (**Jul-2026**, verified against official docs; `~
 
 ## Distribution (install-time)
 
-Proven pattern (Spec Kit, 30+ agents): **one canonical source** + generate/symlink into the per-harness dirs at install (`.claude/`, `.codex/`, `.gemini/`, …). agent-workflow already does this via `aw self install-skill`. Recommended convention: **canonical `AGENTS.md` + `CLAUDE.md` symlink** (Claude Code does not read `AGENTS.md` natively; the rest do).
+Proven pattern (Spec Kit, 30+ agents): **one canonical source** + generate/symlink into the per-harness dirs at install (`.claude/`, `.codex/`, `.gemini/`, …). Workline already does this via `aw self install-skill`. Recommended convention: **canonical `AGENTS.md` + `CLAUDE.md` symlink** (Claude Code does not read `AGENTS.md` natively; the rest do).
 
 ## Command packaging (harness-specific)