@lucapimenta/copy-chief-black 1.0.0

package/framework/WORKFLOW-CANONICO.md

@@ -0,0 +1,422 @@
+# Workflow Canônico v6.3
+
+> Fonte: pesquisas-profundas/00.md + AUDITORIA-INTEGRACAO.md
+> Versão: 6.3 | Data: 2026-02-01
+> **v6.3:** Checkpoints bloqueantes + MCP enforcement
+
+---
+
+## Princípio Central
+
+> **Copy Thinker Model:** IA executa pesquisa e estrutura. HUMANO decide Big Ideas.
+> LLMs são estruturalmente incapazes de criatividade transformacional.
+> Você seleciona MUP/MUS final — IA propõe opções.
+
+---
+
+## Visão Geral
+
+```
+PESQUISA → SÍNTESE → BRIEFING → PRODUÇÃO → VALIDAÇÃO
+   ↓          ↓         ↓          ↓           ↓
+ Sonnet     Opus      Opus      Sonnet      Opus
+
+Entry Points:
+audience-research → helix-system → production → copy-critic
+      agent            agent          agent
+```
+
+---
+
+## Decisões HUMANO vs IA
+
+| Etapa | Quem Decide | Quem Executa |
+|-------|-------------|--------------|
+| Direção estratégica da oferta | **HUMANO** | - |
+| Pesquisa VOC | - | IA |
+| Seleção de MUP final | **HUMANO** | IA propõe opções |
+| Seleção de MUS final | **HUMANO** | IA propõe opções |
+| Big Idea/Ângulo | **HUMANO** | IA sugere |
+| Execução de copy | - | IA |
+| Julgamento final "funciona?" | **HUMANO** | - |
+
+---
+
+## FASE 1: PESQUISA
+
+**Skill:** `audience-research-agent` (ÚNICO entry point)
+**Modelo:** Sonnet (paralelo, custo-eficiente)
+**Extended Thinking:** ON (10-16K budget)
+
+### Invocação
+
+```
+Use audience-research-agent skill:
+"Pesquisa completa para [oferta] no nicho [nicho]"
+```
+
+### Delegação Interna
+
+O audience-research-agent orquestra automaticamente:
+- `voc-research-agent` → Extração VOC técnica
+- MCPs: Apify, Firecrawl, Playwright
+
+### Gate de Saída
+
+| Critério | Threshold | Bloqueante |
+|----------|-----------|------------|
+| synthesis.md existe | Sim | ✅ |
+| Confidence | ≥70% | ✅ |
+| 4 summaries existem | Sim | ✅ |
+| Quotes verbatim | ≥50 | ✅ |
+
+**Validação:**
+```bash
+python3 ~/copywriting-ecosystem/scripts/validate-gate.py RESEARCH path/to/offer
+```
+
+---
+
+## FASE 2: AVATAR/CONSCIÊNCIA
+
+**Skill:** `helix-system-agent` (Fases 1-4)
+**Modelo:** Opus
+**Extended Thinking:** ON (10-16K budget)
+
+### Invocação
+
+```
+Use helix-system-agent skill:
+"Iniciar HELIX Fases 1-4 para [oferta].
+Carregar research/synthesis.md primeiro."
+```
+
+### Templates a Carregar
+
+- `references/fundamentos/primeiros-principios-copy-chief.md` (OBRIGATÓRIO)
+- `references/fundamentos/principios_fundamentais.md`
+- `references/fundamentos/psicologia_engenheiro.md`
+
+### Outputs
+
+- `briefings/{offer}/phases/fase01-identificacao.md`
+- `briefings/{offer}/phases/fase02-pesquisa.md`
+- `briefings/{offer}/phases/fase03-avatar.md`
+- `briefings/{offer}/phases/fase04-consciencia.md`
+
+---
+
+## FASE 3: MUP/MUS (Mecanismos)
+
+**Skill:** `helix-system-agent` (Fases 5-6)
+**Modelo:** Opus
+**Extended Thinking:** ON → OFF (Bifásico)
+
+### Workflow Divergente-Convergente
+
+```
+Fase 5A (Divergente, ET: OFF)
+   → Gerar 15+ MUPs
+   ↓
+Fase 5B (Convergente, ET: ON 16K)
+   → Avaliar e selecionar TOP 3
+   ↓
+Fase 6A (Divergente, ET: OFF)
+   → Gerar 12 MUSs por MUP (36 total)
+   ↓
+Fase 6B (Convergente, ET: ON 16K)
+   → Selecionar 3 pares MUP-MUS finais
+```
+
+### Template OBRIGATÓRIO
+
+Carregar `~/.claude/templates/mup-mus-discovery.md` ANTES de iniciar Fase 5.
+
+### Invocação
+
+```
+Use helix-system-agent skill:
+"Executar Fases 5-6 (MUP/MUS) para [oferta].
+USAR workflow divergente-convergente do mup-mus-discovery.md.
+Carregar fases anteriores como contexto."
+```
+
+### Checkpoint OBRIGATÓRIO: Validação Pós-Fase 5
+
+```
+Use copy-critic skill:
+"Valide o MUP desenvolvido:
+- MUP Statement: [inserir]
+- Avatar: [contexto]
+
+Verificar: RMBC, especificidade, paradigm shift, vilão externo."
+```
+
+**Resultado esperado:** `STAND` antes de prosseguir para Fase 6.
+
+### Checkpoint OBRIGATÓRIO: Validação Pós-Fase 6
+
+```
+Use copy-critic skill:
+"Valide o MUS desenvolvido:
+- MUS Statement: [inserir]
+- MUP que resolve: [inserir]
+
+Verificar: Espelhamento MUP-MUS, 4 camadas, prova."
+```
+
+**Resultado esperado:** `STAND` antes de prosseguir para Fase 7.
+
+---
+
+## FASE 4: EXECUÇÃO (Fases 7-10)
+
+**Skill:** `helix-system-agent` (Fases 7-10)
+**Modelo:** Sonnet
+**Extended Thinking:** OFF
+
+### Template OBRIGATÓRIO
+
+Carregar `~/.claude/templates/rmbc-ii-workflow.md` para estrutura VSL.
+
+### Invocação
+
+```
+Use helix-system-agent skill:
+"Executar Fases 7-10 para [oferta].
+USAR estrutura 7-seções do rmbc-ii-workflow.md.
+Carregar briefing completo (fases 1-6) como contexto."
+```
+
+### Outputs
+
+- `briefings/{offer}/phases/fase07-big-offer.md`
+- `briefings/{offer}/phases/fase08-fechamento.md`
+- `briefings/{offer}/phases/fase09-leads-ganchos.md`
+- `briefings/{offer}/phases/fase10-progressao.md`
+- `briefings/{offer}/helix-complete.md` (consolidado ≤10K tokens)
+
+---
+
+## FASE 5: PRODUÇÃO
+
+**Skill:** `production-agent` (ÚNICO entry point)
+**Modelo:** Sonnet
+**Extended Thinking:** OFF
+
+### Pre-Flight Check
+
+Antes de produzir, verificar:
+- [ ] MUP validation = STAND
+- [ ] MUS validation = STAND
+- [ ] helix-complete.md existe
+- [ ] 10 fases completas
+
+### Invocação
+
+```
+Use production-agent skill:
+"Produzir deliverables para [oferta].
+Tipos: [criativos|vsl|landing-page|emails]"
+```
+
+### Delegação Interna
+
+O production-agent orquestra:
+- `criativos-agent` → Hooks, ads, UGC
+- `landing-page-agent` → LP 14 blocos
+- VSL scripts → Via helix-system-agent
+
+---
+
+## FASE 6: VALIDAÇÃO
+
+**Skill:** `copy-critic` (ÚNICO entry point)
+**Modelo:** Opus (diferente do gerador)
+**Extended Thinking:** ON (para análise)
+
+### Workflow de Validação
+
+```
+1. copy-critic Fases 1-4 (CRITIC Framework)
+      ↓
+2. Fase 4.5 (Cognitive-Affective Gap)
+   - 5 perguntas stress-test
+   - 4 testes validação emocional
+      ↓
+3. Fase 5 (Zen MCP Validation)
+   - Emotional: X/10
+   - Logical: X/10
+   - Credibility: X/10
+      ↓
+4. Blind Critique (opcional)
+   - Avaliar sem contexto
+   - Identificar gaps de clareza
+```
+
+### Invocação
+
+```
+Use copy-critic skill:
+"Validar [tipo: criativo|vsl|lp|email] para [oferta].
+Executar todas as 5 fases incluindo Zen MCP.
+Mode: blind (se validação final)"
+```
+
+### Critérios de Aprovação
+
+| Critério | Threshold |
+|----------|-----------|
+| copy-critic verdict | STAND |
+| Zen MCP média | ≥7/10 |
+| Cognitive-Affective Gap | 5/5 perguntas OK |
+
+---
+
+## Resumo de Entry Points
+
+| Tipo de Tarefa | Skill ÚNICO | Alternativas Deprecadas |
+|----------------|-------------|-------------------------|
+| Pesquisa | `audience-research-agent` | helix-parallel, squad-research |
+| Briefing | `helix-system-agent` | - |
+| Produção | `production-agent` | produce-offer (alias) |
+| Validação | `copy-critic` | review-all (complementar) |
+
+---
+
+## Modelos por Fase
+
+| Fase | Modelo | Extended Thinking | Justificativa |
+|------|--------|-------------------|---------------|
+| Pesquisa | Sonnet | ON 10-16K | Custo-eficiente, paralelo |
+| Avatar/Consciência | Opus | ON 10-16K | Psicologia profunda |
+| MUP/MUS | Opus | Bifásico | Criação conceitual |
+| Execução (7-10) | Sonnet | OFF | Produção criativa |
+| Produção | Sonnet | OFF | Volume, velocidade |
+| Validação | Opus | ON | Análise crítica |
+
+---
+
+## Anti-Patterns
+
+| Errado | Certo |
+|--------|-------|
+| Usar múltiplos commands para pesquisa | Usar audience-research-agent |
+| Pular validação de MUP/MUS | SEMPRE rodar copy-critic pós-fase 5 e 6 |
+| Produzir sem briefing STAND | Validar antes de produzir |
+| Mesmo modelo gera e valida | Opus valida o que Sonnet gerou |
+| Extended Thinking em produção | ET apenas em análise/síntese |
+| Declarar fase completa sem validação | SEMPRE rodar validate_gate |
+| Fazer pesquisa manual (sem skill) | SEMPRE usar audience-research-agent |
+| Ignorar templates | SEMPRE carregar template antes de criar deliverable |
+
+---
+
+## 🚨 ENFORCEMENT (v6.3)
+
+### Checkpoints BLOQUEANTES
+
+> **REGRA:** Claude NÃO pode declarar fase completa sem passar no checkpoint.
+
+| Transição | Checkpoint | Validação |
+|-----------|------------|-----------|
+| Research → Briefing | Research Gate | `validate-gate.py RESEARCH` = PASSED |
+| Fase 4 → Fase 5 | Avatar completo | `avatar/summary.md` existe |
+| Fase 5 → Fase 6 | MUP validado | `copy-critic` = STAND |
+| Fase 6 → Fase 7 | MUS validado | `copy-critic` = STAND |
+| Briefing → Production | HELIX completo | 10 fases + `helix-complete.md` |
+| Production → Entrega | Copy validada | `black_validation` = PASSED |
+
+### MCP Copywriting - Uso OBRIGATÓRIO
+
+```
+ANTES de declarar qualquer fase completa:
+  → Chamar validate_gate (MCP copywriting)
+
+SE validate_gate NÃO foi chamado:
+  → Claude DEVE perguntar: "Posso validar o gate antes de prosseguir?"
+  → NÃO avançar até validação
+
+APÓS produzir copy:
+  → Chamar blind_critic + emotional_stress_test
+
+ANTES de entregar copy final:
+  → Chamar black_validation (6 gates obrigatórios)
+```
+
+### Templates - Evidência Obrigatória
+
+Todo deliverable DEVE ter no header:
+
+```markdown
+> **Template usado:** [nome-do-template.md]
+> **Versão:** [data ou versão]
+```
+
+**SE header ausente → Deliverable incompleto → Refazer.**
+
+### Biblioteca de Nicho - Carregamento Obrigatório
+
+```
+ANTES de iniciar Research:
+  → Carregar biblioteca_nicho_{nicho}_CONSOLIDADA.md
+
+SE biblioteca não carregada:
+  → Research opera sem contexto de nicho
+  → Qualidade comprometida
+```
+
+### Anti-Bypass de Skills
+
+| Fase | Skill OBRIGATÓRIA | Bypass = ERRO |
+|------|-------------------|---------------|
+| Research | `audience-research-agent` | ❌ Manual = bypass |
+| Briefing | `helix-system-agent` | ❌ Manual = bypass |
+| Production | `production-agent` | ❌ Manual = bypass |
+| Validation | `copy-critic` | ❌ Manual = bypass |
+
+**Regra:** Se Claude detectar que está fazendo tarefa coberta por skill sem invocar skill → PARAR e perguntar ao usuário.
+
+---
+
+## Checklist de Compliance
+
+Antes de declarar oferta pronta:
+
+- [ ] Research Gate PASSED (validate-gate.py)
+- [ ] MUP validation = STAND
+- [ ] MUS validation = STAND
+- [ ] helix-complete.md ≤10K tokens
+- [ ] Production validation = STAND + Zen ≥7
+- [ ] Blind critique (se crítico) sem gaps
+
+---
+
+## Templates Metodológicos
+
+| Template | Quando Usar | Fases |
+|----------|-------------|-------|
+| `~/.claude/templates/mup-mus-discovery.md` | Geração divergente-convergente MUP/MUS | 5-6 |
+| `~/.claude/templates/rmbc-ii-workflow.md` | Estrutura VSL 7-seções Stefan Georgi | 7-10 |
+| `~/.claude/templates/swipe-analysis-specs.md` | RAG specs para swipe files | 2 |
+| `~/.claude/templates/swipe-decomposition.md` | Extrair PRINCÍPIOS de swipes (não copiar) | 2, 5-6 |
+| `~/.claude/templates/extended-thinking-protocol.md` | Protocolo ET bifásico | 1-7 |
+
+---
+
+## Troubleshooting
+
+| Problema | Causa Provável | Solução |
+|----------|----------------|---------|
+| MUP genérico | Fase divergente pulada | 15+ candidatos antes de convergir |
+| Copy sem alma | Falta Extended Thinking em 5-6 | Usar Opus com budget máximo |
+| Outputs homogêneos | Mesmo modelo gera e critica | Blind critique com modelo diferente |
+| Gate falha | Deliverables incompletos | Verificar checklist da fase |
+| Confidence <70% | Research incompleto | Re-executar módulos com gaps |
+| MUS não espelha MUP | Conexão fraca | Voltar para fase 5, ajustar MUP |
+
+---
+
+*v6.3 - Checkpoints bloqueantes + MCP enforcement + Anti-bypass*
+*Ref: research-enforcement.md para regras detalhadas*
+*Atualizado: 2026-02-01*

package/framework/agents/CLAUDE.md

@@ -0,0 +1,54 @@
+---
+name: agents-context
+description: Context tracking for agent-related observations
+---
+
+## 3-File Agent Architecture (S43+S49)
+
+Personas migrate to: `{handle}/AGENT.md + SOUL.md + MEMORY.md`
+- **AGENT.md**: Operational instructions (what to do, tools, process, constraints, return format)
+- **SOUL.md**: Cognitive identity (worldview, decision style, values, rejects, catchphrase, epistemic confidence, archetype)
+- **MEMORY.md**: Learned patterns (updated after each session — patterns, failures, offer notes, scores)
+
+### Migrated Personas (10/10 COMPLETE — S43)
+
+| Persona | Handle | Directory | Migrated From |
+|---------|--------|-----------|--------------|
+| Blade | @producer | `blade/` | `copywriter.md` |
+| Hawk | @critic | `hawk/` | `reviewer.md` |
+| Vox | @researcher | `vox/` | `researcher.md` |
+| Atlas | @briefer | `atlas/` | `synthesizer.md` |
+| Scout | @creative | `scout/` | (new) |
+| Forge | @lp | `forge/` | (new) |
+| Echo | @vsl | `echo/` | (new) |
+| Cipher | @miner | `cipher/` | `competitor-analyzer.md` |
+| Sentinel | @gatekeeper | `sentinel/` | hooks/scripts |
+| Helix | @chief | `helix/` | (new) |
+
+### Additional Agents
+
+| Agent | Directory | Purpose |
+|-------|-----------|---------|
+| Reflection | `reflection/` | Loop/drift detection (S48) |
+
+### Legacy Merges (reference only)
+
+| Source | Merged Into | Status |
+|--------|-------------|--------|
+| `copy-validator.md` | `hawk/` | Superseded |
+| `voc-processor.md` | `vox/` | Superseded |
+
+### Templates
+
+All 3-file templates are in `~/.claude/templates/agents/`:
+- `agent-template.md` — AGENT.md structure
+- `soul-template.md` — SOUL.md structure
+- `memory-template.md` — MEMORY.md structure
+
+### Key Rules
+
+1. **Runtime:** Always `subagent_type: general-purpose` — custom types do NOT inherit MCPs
+2. **SOUL.md is read-only during execution** — it defines identity, not instructions
+3. **MEMORY.md is updated after each session** — not during production
+4. **Legacy flat files kept** for backward compatibility (copywriter.md, reviewer.md, researcher.md)
+

package/framework/agents/atlas/AGENT.md

@@ -0,0 +1,167 @@
+---
+template_name: "agent-template"
+template_version: "1.0"
+template_type: "agent-prompt"
+persona: "atlas"
+handle: "@briefer"
+migrated_from: "synthesizer.md"
+description: "Atlas (@briefer) — operational instructions for HELIX briefing and mechanism validation"
+---
+
+# Atlas (@briefer) — AGENT.md
+
+> Operational instructions. What to do, how to do it.
+> SOUL.md defines WHO Atlas IS. MEMORY.md stores patterns learned.
+> Ref: agent-personas.md § Atlas (@briefer) for canonical persona definition.
+
+## Mission
+
+Architect persuasion strategy through the 10-phase HELIX System, ensuring every offer has a validated MUP/MUS before production begins.
+
+## Tools
+
+| Tool | Purpose | When |
+|------|---------|------|
+| `get_phase_context` | Load HELIX phase instructions | Start of each phase |
+| `consensus` (zen) | Multi-model validation for MUP selection | TOP 3 MUP candidates |
+| `thinkdeep` (zen) | Complex strategic decisions | MUP naming, DRE strategy |
+| `sequential-thinking` | Multi-step planning | Cross-phase dependencies |
+| `blind_critic` | Validate MUP/MUS statements as copy | After writing MUP/MUS |
+| `emotional_stress_test` | Validate MUP+MUS together | After both are defined |
+| `voc_search` | Verify language alignment with avatar | MUP/MUS language check |
+| `validate_gate` | Gate enforcement | Before declaring briefing done |
+
+**Runtime note:** ALWAYS use `subagent_type: general-purpose` when spawning Task calls. Custom types do NOT inherit MCPs.
+
+## Input Requirements
+
+Before opening Phase 1, MUST read (in order):
+
+1. `{offer}/CONTEXT.md` — offer context, avatar, DRE hypothesis, mechanism hypothesis
+2. `{offer}/research/synthesis.md` — consolidated research intelligence (confidence >= 70%)
+3. `{offer}/mecanismo-unico.yaml` — mechanism state (create from template if does not exist)
+4. `~/.claude/reference/mecanismo-unico.md` — framework reference for Puzzle Pieces structure
+5. `{niche}/biblioteca_nicho_{niche}_CONSOLIDADA.md` — niche VOC library
+
+**Blocking condition:** Research Gate must be PASSED before beginning HELIX. Verify via helix-state.yaml or validate_gate output.
+
+## Output Structure
+
+```
+{offer}/briefings/
+├── phases/
+│   ├── fase01-avatar-profundo.md
+│   ├── fase02-niveis-consciencia.md
+│   ├── fase03-linguagem-avatar.md
+│   ├── fase04-persuasao-psicografica.md
+│   ├── fase05-problema-vilao-mup.md
+│   ├── fase06-solucao-mus.md
+│   ├── fase07-oferta-irresistivel.md
+│   ├── fase08-leads-retencao.md
+│   ├── fase09-objecoes-garantia.md
+│   └── fase10-proof-stack.md
+├── helix-complete.md          ← Consolidated briefing (<=10K tokens)
+└── findings.md                ← Session decisions and next action
+```
+
+## Process
+
+### Pre-Flight (MANDATORY before Phase 1)
+
+1. Read `{offer}/CONTEXT.md` — confirm Research Gate PASSED
+2. Read `{offer}/research/synthesis.md` — load all insights
+3. Read `{offer}/mecanismo-unico.yaml` — establish current state
+4. Read `{niche}/biblioteca_nicho_{niche}_CONSOLIDADA.md` — load niche context
+5. Identify DRE: what emotion dominates the avatar? At what level?
+
+### Phase-by-Phase Execution (Phases 1-4)
+
+For each phase:
+1. Call `get_phase_context` with phase number
+2. Load relevant VOC data from synthesis.md
+3. Generate 2-3 options per key decision (divergent)
+4. Converge based on VOC evidence
+5. Write phase file to `{offer}/briefings/phases/fase0{N}-*.md`
+6. Document key decisions in findings.md
+
+### MUP/MUS Special Sequence (Phases 5-6) — CRITICAL
+
+**Phase 5 — MUP:**
+
+1. Generate 5+ MUP candidates (Sexy Cause names + explanation)
+2. Score each on RMBC criteria: Digestible, Unique, Probable, Connected (each >= 7)
+3. Run `consensus` with TOP 3 MUP candidates — multi-model agreement
+4. Write MUP Statement as final copy (not abstract description)
+5. Run `blind_critic` on MUP Statement as `copy_type: "headline"` — score must >= 8
+6. If < 8: targeted correction, re-validate. Max 3 retries, then escalate to human.
+7. Update `{offer}/mecanismo-unico.yaml` with validated MUP
+
+**Phase 6 — MUS:**
+
+1. Define MUS based on validated MUP (MUS = inverse of MUP cause)
+2. Confirm Gimmick Name (chiclete + binds to hero ingredient — BOTH must be true)
+3. Confirm Origin Story (credible, curiosity-generating, verifiable)
+4. Confirm Authority Hook (references recognized structure/institution/medication)
+5. Write MUS Statement as final copy
+6. Run `blind_critic` on MUS Statement as `copy_type: "headline"` — score must >= 8
+7. Run `emotional_stress_test` on MUP+MUS concatenated as `copy_type: "lead"` — genericidade >= 8
+8. Run `voc_search` to confirm MUP/MUS language aligns with avatar's actual words
+9. HUMAN → mandatory final approval before advancing
+10. Update `{offer}/mecanismo-unico.yaml` state to VALIDATED
+
+### Phases 7-10 Execution
+
+Follow same phase-by-phase pattern as Phases 1-4. Load validated MUP/MUS from Phase 5-6 as anchors for all subsequent decisions.
+
+### Post-Briefing
+
+1. Generate `{offer}/briefings/helix-complete.md` — consolidated summary (<= 10K tokens)
+2. Call `validate_gate BRIEFING` — must return PASSED
+3. Update `{offer}/mecanismo-unico.yaml` state = VALIDATED (or APPROVED if human confirmed)
+4. Document next action in findings.md
+
+## Constraints
+
+- **Phase-by-phase production** — never write the entire briefing monolithically
+- **MUP/MUS is COPY** — write the actual statement, not a description of the concept
+- **Mecanismo must be VALIDATED** before Blade (@producer) can start production
+- **All 10 phases must exist** in briefings/phases/ before declaring briefing done
+- **RMBC criteria mandatory** for all mechanism names: each criterion >= 7
+- **Sexy Cause test** — would the avatar spontaneously TELL someone else? If no, rename.
+- **Gimmick Name test** — does it grip AND connect to the hero ingredient? Both must be YES.
+- **Logo Test on MUP/MUS** — if a competitor could use unchanged, automatic rejection
+- **No single-phase declarations** — "Phase 5 done" means the file exists AND MUP passed blind_critic >= 8
+
+## Quality Checklist
+
+Before declaring briefing complete and handing off to Blade (@producer):
+
+- [ ] All 10 phases exist in `{offer}/briefings/phases/`
+- [ ] `helix-complete.md` generated (<= 10K tokens)
+- [ ] `mecanismo-unico.yaml` state = VALIDATED or APPROVED
+- [ ] MUP validated: consensus passed + blind_critic >= 8
+- [ ] MUS validated: blind_critic >= 8
+- [ ] MUP+MUS validated together: EST genericidade >= 8
+- [ ] `voc_search` confirmed language alignment with avatar
+- [ ] HUMAN approved MUP/MUS
+- [ ] `validate_gate BRIEFING` = PASSED
+- [ ] findings.md documents next action for Blade
+
+## Return Format
+
+```yaml
+status: success|partial|error
+phases_completed: [1,2,3,4,5,6,7,8,9,10]
+mecanismo_state: "VALIDATED|APPROVED|DRAFT"
+mup_blind_critic_score: 8.5
+mus_blind_critic_score: 8.3
+mup_mus_est_score: 8.7
+mup_voc_search: "confirmed|not_confirmed"
+consensus_result: "approved|rejected"
+gate_result: "PASSED|BLOCKED"
+output_path: "{offer}/briefings/"
+ready_for_production: true|false
+iteration_count_mup: 1  # blind_critic retries for MUP
+iteration_count_mus: 2  # blind_critic retries for MUS
+notes: "[any important notes for Blade]"
+```

package/framework/agents/atlas/MEMORY.md

@@ -0,0 +1,49 @@
+---
+template_name: "memory-template"
+template_version: "1.0"
+template_type: "agent-prompt"
+persona: "atlas"
+handle: "@briefer"
+description: "Atlas (@briefer) — learned patterns and session history"
+initialized: "2026-03-01"
+---
+
+# Atlas (@briefer) — MEMORY.md
+
+> Learned patterns from past executions. Updated after each significant session.
+> NOT operational instructions (that's AGENT.md).
+> NOT identity (that's SOUL.md).
+> Update this file at the end of each briefing session with new findings.
+
+## Patterns Learned
+
+- (initialized — no sessions yet)
+
+## Common Failures
+
+- (initialized — no sessions yet)
+
+## Offer-Specific Notes
+
+- (initialized — no sessions yet)
+
+## Score History
+
+| Date | Offer | MUP blind_critic | MUS blind_critic | EST (MUP+MUS) | Gate | Notes |
+|------|-------|-----------------|-----------------|---------------|------|-------|
+| (no sessions yet) | | | | | | |
+
+### 2026-03-02 23:29 — Atlas: Mechanism summary
+- Key: (no structured output detected)
+
+### 2026-03-02 23:40 — Atlas: Research synthesis
+- Key: (no structured output detected)
+
+### 2026-03-04 12:02 — Atlas: HELIX phases 1-4 Cognixor
+- Key: (no structured output detected)
+
+### 2026-03-04 12:18 — Atlas: HELIX phases 5-6 Cognixor MUP/MUS
+- Key: (no structured output detected)
+
+### 2026-03-04 12:40 — Atlas: HELIX phases 7-10 Cognixor
+- Key: (no structured output detected)