@ancleto/spec 0.6.1 → 0.6.4

package/commands/{opsx-verify.md → cleto-verify.md}

@@ -4,7 +4,7 @@ description: Verify implementation matches change artifacts before archiving
 
 Verify that an implementation matches the change artifacts (specs, tasks, design).
 
-**Input**: Optionally specify a change name after `/opsx-verify` (e.g., `/opsx-verify add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+**Input**: Optionally specify a change name after `/cleto-verify` (e.g., `/cleto-verify add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
 
 **Steps**
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ancleto/spec",
-  "version": "0.6.1",
+  "version": "0.6.4",
   "description": "Orquestador SDD liviano con subagentes optimizados para costo/tokens",
   "type": "module",
   "bin": {

package/skills/{openspec-apply → ancleto-apply}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: openspec-apply
+name: ancleto-apply
 description: Implement tasks from a change step by step, tracking progress in tasks.md. Use when artifacts are ready and implementation should start. No external binaries required.
 license: MIT
 compatibility: No external binaries required. Works with any agent runtime.
@@ -78,7 +78,7 @@ For each pending task (`- [ ]`):
 **Change:** <change-name>
 **Progress:** N/N tasks complete ✓
 
-All tasks complete! You can archive this change with `openspec-archive`.
+All tasks complete! You can archive this change with `ancleto-archive`.
 ```
 
 **On pause:**

package/skills/{openspec-archive → ancleto-archive}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: openspec-archive
+name: ancleto-archive
 description: Archive a completed change, syncing delta specs first when needed. Use when implementation and verification are done. Captures lessons into persistent memory. No external binaries required.
 license: MIT
 compatibility: No external binaries required. Works with any agent runtime.

package/skills/{openspec-bulk-archive → ancleto-bulk-archive}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: openspec-bulk-archive
+name: ancleto-bulk-archive
 description: Archive multiple completed changes in one batch, resolving spec conflicts by checking the codebase. Use when several changes are done and should be archived together. No external binaries required.
 license: MIT
 compatibility: No external binaries required. Works with any agent runtime.

package/skills/{openspec-continue → ancleto-continue}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: openspec-continue
+name: ancleto-continue
 description: Continue working on an existing change by creating its next missing artifact. Use to resume artifact creation one step at a time. No external binaries required.
 license: MIT
 compatibility: No external binaries required. Works with any agent runtime.
@@ -29,7 +29,7 @@ Read `openspec/changes/<name>/` and check for artifact files in this fixed depen
 
 The first item in this order that is absent (or, for `specs/`, contains no `spec.md`) is the next artifact to create.
 
-- **If all four are present**: congratulate the user, show the status, and suggest "All artifacts created! You can now implement this change with `openspec-apply` or archive it with `openspec-archive`." STOP.
+- **If all four are present**: congratulate the user, show the status, and suggest "All artifacts created! You can now implement this change with `ancleto-apply` or archive it with `ancleto-archive`." STOP.
 - **If the change directory does not exist**: report it and stop.
 
 ### 2. Load context files
@@ -38,7 +38,7 @@ Read every artifact that IS present — they constrain what you write next. If a
 
 ### 3. Create exactly ONE artifact
 
-Draft the missing artifact using the same templates as `openspec-propose`:
+Draft the missing artifact using the same templates as `ancleto-propose`:
 
 - **proposal.md** (first artifact): problem statement, proposed change, scope, risks. If Work Item context is available, use its title/description as the problem statement, acceptance criteria as the requirements basis, and include a `## Related Work Item` section: `**#{id}** — {title} ({type}) · Project: {project}`.
 - **specs/\<capability\>/spec.md**: one spec file per capability the change touches, with `## ADDED Requirements` / `#### Scenario:` blocks in WHEN/THEN form.
@@ -54,7 +54,7 @@ Report:
 - Which artifact was created.
 - Current progress (N/4 complete).
 - What is unlocked next.
-- Prompt: "Run `openspec-continue` to create the next artifact."
+- Prompt: "Run `ancleto-continue` to create the next artifact."
 
 Create ONE artifact per invocation, then STOP.
 

package/skills/{openspec-explore → ancleto-explore}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: openspec-explore
+name: ancleto-explore
 description: Enter explore mode — think through ideas, investigate problems, and clarify requirements without implementing. Consults prior team memory first. No external binaries required.
 license: MIT
 compatibility: No external binaries required. Works with any agent runtime.

package/skills/{openspec-ff → ancleto-ff}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: openspec-ff
+name: ancleto-ff
 description: Fast-forward artifact creation — create a change and generate everything needed for implementation in one go. Use when the path is clear and no step-by-step guidance is wanted. No external binaries required.
 license: MIT
 compatibility: No external binaries required. Works with any agent runtime.
@@ -57,7 +57,7 @@ Summarize:
 - Change name and location
 - List of artifacts created with brief descriptions
 - What's ready: "All artifacts created! Ready for implementation."
-- Prompt: "Run `openspec-apply` to start implementing."
+- Prompt: "Run `ancleto-apply` to start implementing."
 
 ## Artifact Creation Guidelines
 

package/skills/{openspec-new → ancleto-new}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: openspec-new
+name: ancleto-new
 description: Start a new spec-driven change without external binaries. Use when the user wants to begin structured work on a feature, fix, or modification. Creates the change directory, recalls prior memory, and shows the first artifact template.
 license: MIT
 compatibility: No external binaries required. Works with any agent runtime.
@@ -84,7 +84,7 @@ After completing the steps, summarize:
 - Change name and location
 - Artifact sequence and current status (0/4 artifacts complete)
 - The template for the first artifact
-- Prompt: "Ready to create the first artifact? Run `openspec-propose` or just describe what this change is about and I'll draft it."
+- Prompt: "Ready to create the first artifact? Run `ancleto-propose` or just describe what this change is about and I'll draft it."
 
 ## Guardrails
 

package/skills/{openspec-onboard → ancleto-onboard}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: openspec-onboard
+name: ancleto-onboard
 description: Guided onboarding — walk through a complete spec-driven cycle (idea to archive) on a real small task, with narration. Use for a first-time user of the workflow. No external binaries required.
 license: MIT
 compatibility: No external binaries required. Works with any agent runtime.
@@ -119,16 +119,16 @@ Congratulate, recap the cycle (Explore → New → Proposal → Specs → Design
 
 | Command | What it does |
 |---------|--------------|
-| `openspec-propose` | Create a change and generate all artifacts |
-| `openspec-explore` | Think through problems before/during work |
-| `openspec-apply` | Implement tasks from a change |
-| `openspec-archive` | Archive a completed change |
-| `openspec-new` | Start a new change, step by step |
-| `openspec-continue` | Continue an existing change |
-| `openspec-ff` | Fast-forward: all artifacts at once |
-| `openspec-verify` | Verify implementation |
-
-**Graceful exits:** if the user wants to stop mid-way, point at the saved change directory and the resume skills (`openspec-continue`, `openspec-apply`). If they only want the reference, show the table and exit.
+| `ancleto-propose` | Create a change and generate all artifacts |
+| `ancleto-explore` | Think through problems before/during work |
+| `ancleto-apply` | Implement tasks from a change |
+| `ancleto-archive` | Archive a completed change |
+| `ancleto-new` | Start a new change, step by step |
+| `ancleto-continue` | Continue an existing change |
+| `ancleto-ff` | Fast-forward: all artifacts at once |
+| `ancleto-verify` | Verify implementation |
+
+**Graceful exits:** if the user wants to stop mid-way, point at the saved change directory and the resume skills (`ancleto-continue`, `ancleto-apply`). If they only want the reference, show the table and exit.
 
 ## Guardrails
 

package/skills/{openspec-propose → ancleto-propose}/SKILL.md

@@ -1,6 +1,6 @@
 ---
-name: openspec-propose
-description: Draft all artifacts for a change in one step (proposal, design, tasks, delta specs). Use after openspec-new, or directly with a change name or description. No external binaries required.
+name: ancleto-propose
+description: Draft all artifacts for a change in one step (proposal, design, tasks, delta specs). Use after ancleto-new, or directly with a change name or description. No external binaries required.
 license: MIT
 compatibility: No external binaries required. Works with any agent runtime.
 metadata:
@@ -18,7 +18,7 @@ Create a change and generate all its artifacts in one step, writing files direct
 
 ### 1. Resolve context and derive the change name
 
-Same as `openspec-new` step 1: use in-session Work Item context if available (record id/title/project for traceability, skip entirely when Azure DevOps is not configured), otherwise ask what the user wants to build and derive a kebab-case name.
+Same as `ancleto-new` step 1: use in-session Work Item context if available (record id/title/project for traceability, skip entirely when Azure DevOps is not configured), otherwise ask what the user wants to build and derive a kebab-case name.
 
 **IMPORTANT**: Do NOT proceed without a change name. If a change with that name already exists, ask whether to continue it or create a new one.
 
@@ -122,7 +122,7 @@ After completing all artifacts, summarize:
 - Change name and location
 - List of artifacts created with brief descriptions
 - What's ready: "All artifacts created! Ready for implementation."
-- Prompt: "Run `openspec-apply` to start implementing."
+- Prompt: "Run `ancleto-apply` to start implementing."
 
 ## Artifact Creation Guidelines
 

package/skills/{openspec-recall → ancleto-recall}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: openspec-recall
+name: ancleto-recall
 description: Recupera memoria episódica del proyecto (.ancleto/memory.db) para precargar contexto de changes anteriores. Se invoca al iniciar un change, antes de generar artifacts. Opcional y no bloqueante.
 license: MIT
 compatibility: Requires the memory engine configured in the repo. Optional — degrades silently when unavailable.
@@ -10,14 +10,14 @@ metadata:
 
 Retrieve shared episodic memory for this repository and inject it as starting context for a change.
 
-This skill is the **single source of truth** for the recall contract. The change-creation flows (`opsx-new`, `opsx-propose`, `opsx-ff`) carry this step inline; those inline blocks must stay in sync with this file.
+This skill is the **single source of truth** for the recall contract. The change-creation flows (`cleto-new`, `cleto-propose`, `cleto-ff`) carry this step inline; those inline blocks must stay in sync with this file.
 
 **Two invocation paths, one contract:**
 
 | Path | Trigger | On failure or empty result |
 | --- | --- | --- |
 | **Automatic** | Inside the change-creation flows, before generating artifacts | Silent — omit the section, never block |
-| **Manual** | The `/opsx-recall` command, invoked by the user | **Report it** — the user asked explicitly |
+| **Manual** | The `/cleto-recall` command, invoked by the user | **Report it** — the user asked explicitly |
 
 Steps 1 to 3 are identical for both. Only the failure behaviour differs, and it differs for a reason: silence is correct when nobody asked, and wrong when somebody did.
 

package/skills/{openspec-sync-specs → ancleto-sync-specs}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: openspec-sync-specs
+name: ancleto-sync-specs
 description: Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
 license: MIT
 compatibility: Requires openspec CLI.

package/skills/ancleto-upgrade/SKILL.md

@@ -431,7 +431,7 @@ build: sí/no | lint: sí/no | test: sí/no | test:ci: sí/no | typecheck: sí/n
 - tasks.md ✅ ({N} tareas en 6 fases)
 - design.md ✅
 
-Para implementar: /opsx-apply {CHANGE_NAME}
+Para implementar: /cleto-apply {CHANGE_NAME}
 ```
 
 ---
@@ -439,7 +439,7 @@ Para implementar: /opsx-apply {CHANGE_NAME}
 ## Guardrails
 
 Este skill solo genera artefactos OpenSpec — no modifica ningún archivo del repo.
-Todo cambio real lo ejecuta el desarrollador con `/opsx-apply`, que tiene su propio
+Todo cambio real lo ejecuta el desarrollador con `/cleto-apply`, que tiene su propio
 ciclo de revisión. Modificar el repo desde este skill saltearía ese control.
 
 - No tocar archivos fuera de `openspec/changes/{CHANGE_NAME}/`

package/skills/{openspec-verify → ancleto-verify}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: openspec-verify
+name: ancleto-verify
 description: Verify an implementation against its change artifacts (completeness, correctness, coherence). Use before archiving a change. Captures architectural findings into persistent memory. No external binaries required.
 license: MIT
 compatibility: No external binaries required. Works with any agent runtime.

package/skills/{openspec-workflow → ancleto-workflow}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: openspec-workflow
+name: ancleto-workflow
 description: Router for the spec-driven lifecycle — know which stage you're in and which skill runs next. Use when unsure where a request fits, or to explain the full cycle. No external binaries required.
 license: MIT
 compatibility: No external binaries required. Works with any agent runtime.
@@ -28,28 +28,28 @@ explore → new/propose/ff → continue* → apply → verify → archive
 
 | User wants to… | Run |
 |---|---|
-| Think through an idea or problem, no commitment yet | `openspec-explore` |
-| Start structured work on something new | `openspec-new` (step by step) or `openspec-propose` (all artifacts at once) |
-| Skip straight to a full draft when the path is clear | `openspec-ff` |
-| Resume a change with missing artifacts | `openspec-continue` (repeat until complete) |
-| Implement tasks from ready artifacts | `openspec-apply` |
-| Check implementation against artifacts before closing | `openspec-verify` |
-| Close one finished change (syncing its specs) | `openspec-archive` |
-| Close several finished changes at once | `openspec-bulk-archive` |
-| Learn the whole cycle hands-on | `openspec-onboard` |
+| Think through an idea or problem, no commitment yet | `ancleto-explore` |
+| Start structured work on something new | `ancleto-new` (step by step) or `ancleto-propose` (all artifacts at once) |
+| Skip straight to a full draft when the path is clear | `ancleto-ff` |
+| Resume a change with missing artifacts | `ancleto-continue` (repeat until complete) |
+| Implement tasks from ready artifacts | `ancleto-apply` |
+| Check implementation against artifacts before closing | `ancleto-verify` |
+| Close one finished change (syncing its specs) | `ancleto-archive` |
+| Close several finished changes at once | `ancleto-bulk-archive` |
+| Learn the whole cycle hands-on | `ancleto-onboard` |
 | Recall what the team learned about a topic | `searchMemory` directly (or the recall contract) |
 
 **By change state** (read `openspec/changes/<name>/`):
 
 | State | Run |
 |---|---|
-| Directory missing → nothing to continue | `openspec-new` (or propose/ff) |
-| `proposal.md` missing | `openspec-continue` |
-| `specs/` or `design.md` missing | `openspec-continue` |
-| `tasks.md` missing | `openspec-continue` |
-| All artifacts present, tasks unchecked | `openspec-apply` |
-| All tasks checked | `openspec-verify`, then `openspec-archive` |
-| Several changes complete | `openspec-bulk-archive` |
+| Directory missing → nothing to continue | `ancleto-new` (or propose/ff) |
+| `proposal.md` missing | `ancleto-continue` |
+| `specs/` or `design.md` missing | `ancleto-continue` |
+| `tasks.md` missing | `ancleto-continue` |
+| All artifacts present, tasks unchecked | `ancleto-apply` |
+| All tasks checked | `ancleto-verify`, then `ancleto-archive` |
+| Several changes complete | `ancleto-bulk-archive` |
 
 ## Handoff Contract
 

package/skills/triage-clarifier/SKILL.md

@@ -96,6 +96,6 @@ If option 4 happened and the answer still does not remove the main ambiguity, cl
 ## What not to do
 
 - do not create specs, design, tasks, or proposals
-- do not trigger opsx or any workflow handoff
+- do not trigger cleto or any workflow handoff
 - do not ask more than one clarification question
 - do not replace the orchestrator's final responsibility for classification

package/src/cli/index.js

@@ -1,4 +1,5 @@
 #!/usr/bin/env node
+import { existsSync } from 'node:fs'
 import { cp, mkdir, access, writeFile, readFile, readdir } from 'node:fs/promises'
 import { spawnSync } from 'node:child_process'
 import { createHash } from 'node:crypto'
@@ -10,6 +11,7 @@ import { createMemoryEngine, defaultMemoryDbPath } from '../core/memory/engine.j
 import { memoryDoctor } from '../core/memory/doctor.js'
 import { writeDiscoveryMap } from '../core/discovery.js'
 import { readProjectTier, buildRepomixArgs, tierTokenBudget } from '../core/repomix-tier.js'
+import { showBanner, selectOption, stopBanner } from './ui.js'
 
 const __dirname = dirname(fileURLToPath(import.meta.url))
 const ROOT = join(__dirname, '..', '..')
@@ -29,9 +31,9 @@ Uso:
   ancleto install --agent <nombre>    opencode | vscode | antigravity | cursor | roo (pregunta si no esta guardado)
   ancleto update [--project <dir>]    Alias de install (re-instala sobre lo existente)
   ancleto upgrade [--agent <nombre>]  Re-aplica templates (LOCKED) y skills sobre el proyecto actual
-  ancleto init [--with-azure] [--agent <nombre>]
+  ancleto init [--with-azure] [--agent <nombre>] [--tier <nivel>]
                                     Crea .ancletorc en el repositorio actual
-                                    (Azure desactivado por defecto, agente: opencode)
+                                    (interactivo en TTY: banner + menu; Azure desactivado por defecto)
   ancleto discovery --check           Estado del seed (READY/STALE/PARTIAL/MISSING)
   ancleto discovery [--compress] [--include G] [--ignore G] [--token-budget N]
                                    Empaca el repo con Repomix y guarda estado
@@ -85,17 +87,21 @@ function globalConfigDir() {
     : join(homedir(), '.config', 'opencode')
 }
 
+function binName(base) {
+  return process.platform === 'win32' ? `${base}.exe` : base
+}
+
 function resolveBin(name, fallbacks = []) {
   const probe = process.platform === 'win32' ? 'where' : 'which'
   const r = spawnSync(probe, [name], { encoding: 'utf8' })
   if (r.status === 0 && r.stdout) {
-    const first = r.stdout.split(/\r?\n/)
-      .map((s) => s.trim())
-      .find((s) => s && !/^informacion:/i.test(s))
-    if (first) return first
+    for (const line of r.stdout.split(/\r?\n/)) {
+      const candidate = line.trim()
+      if (candidate && !/^informacion:/i.test(candidate)) return candidate
+    }
   }
   for (const fb of fallbacks) {
-    if (fb) return fb
+    if (fb && existsSync(fb)) return fb
   }
   return null
 }
@@ -103,16 +109,21 @@ function resolveBin(name, fallbacks = []) {
 function buildDefaultMcp() {
   const mcp = {}
 
-  const engramBin = resolveBin('engram', [join(homedir(), 'go', 'bin', 'engram.exe')])
+  const engramFallbacks = [
+    join(homedir(), 'go', 'bin', binName('engram')),
+    join(homedir(), '.local', 'bin', binName('engram'))
+  ]
+  const engramBin = resolveBin('engram', engramFallbacks)
   if (engramBin) {
     mcp.engram = { type: 'local', enabled: true, command: [engramBin, 'mcp', '--tools=agent'] }
   } else {
     console.warn('ancleto: no se encontro engram (memoria) en PATH; se omitio su MCP')
   }
 
-  const cavemanBin = resolveBin('caveman-mcp', [
-    join(homedir(), '.caveman', 'bin', 'caveman-mcp.exe')
-  ])
+  const cavemanFallbacks = [
+    join(homedir(), '.caveman', 'bin', binName('caveman-mcp'))
+  ]
+  const cavemanBin = resolveBin('caveman-mcp', cavemanFallbacks)
   if (cavemanBin) {
     mcp.caveman = { type: 'local', enabled: true, command: [cavemanBin] }
   } else {
@@ -201,18 +212,31 @@ function askAgent() {
   })
 }
 
-async function resolveAgent(args, existing) {
-  const ai = args.indexOf('--agent')
-  if (ai >= 0) {
-    const name = args[ai + 1]
-    if (!SUPPORTED_AGENTS.includes(name)) {
-      console.error(`ancleto: agente invalido: ${name} (${SUPPORTED_AGENTS.join('/')})`)
-      process.exit(1)
-    }
-    return name
+function scanAgentFlag(args) {
+  const name = flagValue(args, '--agent')
+  if (!name) return null
+  if (!SUPPORTED_AGENTS.includes(name)) {
+    console.error(`ancleto: agente invalido: ${name} (${SUPPORTED_AGENTS.join('/')})`)
+    process.exit(1)
   }
+  return name
+}
+
+function scanTierFlag(args) {
+  const t = flagValue(args, '--tier')
+  if (!t) return null
+  if (!TIERS[t]) {
+    console.error(`ancleto: tier invalido: ${t} (normal|minimo|gratis)`)
+    process.exit(1)
+  }
+  return t
+}
+
+async function resolveAgent(args, existing, allowAsk = Boolean(process.stdin.isTTY)) {
+  const flag = scanAgentFlag(args)
+  if (flag) return flag
   if (existing && SUPPORTED_AGENTS.includes(existing)) return existing
-  if (process.stdin.isTTY) return askAgent()
+  if (allowAsk) return askAgent()
   return DEFAULT_AGENT
 }
 
@@ -266,13 +290,13 @@ const AGENT_SKILLS_DIR = {
   roo: '.roo/skills'
 }
 
-const OPENSPEC_SKILLS = ['openspec-new', 'openspec-propose', 'openspec-apply', 'openspec-verify', 'openspec-archive', 'openspec-bulk-archive', 'openspec-continue', 'openspec-explore', 'openspec-ff', 'openspec-onboard', 'openspec-workflow']
+const ANCLETO_SKILLS = ['ancleto-new', 'ancleto-propose', 'ancleto-apply', 'ancleto-verify', 'ancleto-archive', 'ancleto-bulk-archive', 'ancleto-continue', 'ancleto-explore', 'ancleto-ff', 'ancleto-onboard', 'ancleto-workflow']
 
 async function installAgentSkills(projectDir, agent) {
   const dir = AGENT_SKILLS_DIR[agent] || AGENT_SKILLS_DIR.opencode
   const dest = join(projectDir, dir)
   await mkdir(dest, { recursive: true })
-  for (const name of OPENSPEC_SKILLS) {
+  for (const name of ANCLETO_SKILLS) {
     const src = join(ROOT, 'skills', name)
     if (!(await exists(src))) {
       console.warn(`ancleto: skill no encontrada en el paquete: ${name}`)
@@ -354,12 +378,7 @@ async function install(args) {
   const withMcp = !args.includes('--no-mcp')
   let mcpMap = withMcp ? buildDefaultMcp() : {}
 
-  const ti = args.indexOf('--tier')
-  let tier = ti >= 0 ? args[ti + 1] : null
-  if (tier && !TIERS[tier]) {
-    console.error(`ancleto: tier invalido: ${tier} (normal|minimo|gratis)`)
-    process.exit(1)
-  }
+  let tier = scanTierFlag(args)
 
   if (project) {
     const dir = resolve(project)
@@ -441,22 +460,50 @@ async function upgradeCmd(args) {
   })
   console.log(`ancleto: upgrade completo (v${manifest.version}, agente: ${agent})`)
   console.log('  ✔ templates re-aplicados (bloques LOCKED actualizados, EXTENSIBLE intacto)')
-  console.log(`  ✔ skills actualizadas en ${agentSkillsDir} (${OPENSPEC_SKILLS.length} skills)`)
+  console.log(`  ✔ skills actualizadas en ${agentSkillsDir} (${ANCLETO_SKILLS.length} skills)`)
   console.log('  ✔ manifiesto .ancletorc actualizado')
 }
 
 async function initProject(args) {
-  const withAzure = args.includes('--with-azure')
   const projectDir = process.cwd()
+  const withAzure = args.includes('--with-azure')
+  const agentFlag = scanAgentFlag(args)
+  const tierFlag = scanTierFlag(args)
   const existing = await readAncletorc(projectDir)
   const azure = existing?.azure ?? { enabled: false }
-  if (withAzure) azure.enabled = true
   const discovery = existing?.discovery ?? { outputDir: 'docs/technical-discovery', exclude: [] }
-  const agent = await resolveAgent(args, existing?.agent)
+  const tierFile = join(projectDir, '.opencode', '.ancleto-tier')
+
+  let agent, tier
+  const isInteractive = Boolean(process.stdout.isTTY) && (!agentFlag || !tierFlag)
+  if (isInteractive) {
+    await showBanner()
+    const agentIdx = Math.max(0, SUPPORTED_AGENTS.indexOf(existing?.agent))
+    const storedTier = (await exists(tierFile)) ? (await readFile(tierFile, 'utf8')).trim() : null
+    const tierIdx = Math.max(0, Object.keys(TIERS).indexOf(TIERS[storedTier] ? storedTier : ''))
+    agent = agentFlag || await selectOption('Agente/IDE', SUPPORTED_AGENTS, agentIdx)
+    tier = tierFlag || await selectOption('Tier de costo', Object.keys(TIERS), tierIdx)
+    if (withAzure) {
+      azure.enabled = true
+    } else {
+      azure.enabled = (await selectOption('Habilitar Azure DevOps', ['No', 'Si'], azure.enabled ? 1 : 0)) === 'Si'
+    }
+    stopBanner()
+  } else {
+    agent = await resolveAgent(args, existing?.agent, false)
+    tier = tierFlag
+    if (withAzure) azure.enabled = true
+  }
+
+  if (tier) {
+    await mkdir(join(projectDir, '.opencode'), { recursive: true })
+    await writeFile(tierFile, tier + '\n')
+  }
+
   const manifest = await writeManifest(projectDir, { azure, discovery, agent })
   await scaffoldOpenSpec(projectDir)
   if (azure.enabled) console.log(AZURE_MCP_NOTICE)
-  console.log(`ancleto: .ancletorc actualizado en ${projectDir} (v${manifest.version})${azure.enabled ? ' (Azure habilitado)' : ' (Azure desactivado)'} (Agente: ${agent})`)
+  console.log(`ancleto: .ancletorc actualizado en ${projectDir} (v${manifest.version})${azure.enabled ? ' (Azure habilitado)' : ' (Azure desactivado)'} (Agente: ${agent})${tier ? ` (Tier: ${tier})` : ''}`)
 }
 
 const DEFAULT_IGNORES = ['node_modules', '.git', 'dist']