dev-booster 1.15.0 → 1.16.1

package/README.md

@@ -27,7 +27,7 @@ Unlike generic agent folders, **Dev Booster** uses a manual, activation-first mo
 - most boosters use lazy loading instead of loading the full kit immediately
 - context is pulled only when the task, artifact, or pain point actually requires it
 - each booster has a distinct operational role, instead of behaving like a generic prompt blob
-- many boosters act as continuous document generators (Artifact Engine), maintaining structured state files in the background to prevent context loss during long conversations
+- artifact generation is now selective: exploratory boosters stay conversational, while documentation and persistence boosters generate files only at the end or after explicit confirmation
 
 This gives the kit a stronger product identity and helps avoid unnecessary context bloat.
 
@@ -126,29 +126,71 @@ Many boosters now use a two-step flow:
 1. Activate the mode
 2. Provide the real task, context, artifact, or pain point so the booster can load only what it needs
 
+### Booster artifact behavior at a glance
+
+| Booster | Artifact behavior |
+|---|---|
+| `advisor.md` | No artifact by default; save only if the user explicitly asks |
+| `code-audit.md` | Final report artifact only after confirmation; operational diagnostics files may still be created when needed |
+| `context.md` | No artifact by default; save only if the user explicitly asks |
+| `debug.md` | No artifact by default; save only if the user explicitly asks |
+| `deploy.md` | No artifact by default; save only if the user explicitly asks |
+| `discovery.md` | No artifact by default; save only if the user explicitly asks |
+| `global-documentation.md` | Final documentation artifact only after confirmation |
+| `implementation.md` | Final implementation artifact only after confirmation |
+| `internal-documentation.md` | Final documentation artifact only after confirmation |
+| `investigation.md` | No artifact by default; save only if the user explicitly asks |
+| `planning.md` | No artifact by default; save only if the user explicitly asks |
+| `save-context.md` | Persistence-first; generates YAML snapshot after confirmation |
+| `security.md` | No artifact by default; save only if the user explicitly asks |
+| `coder.md` | Does not create local state files |
+| `diff-review.md` | Must not generate files, artifacts, logs, or review documents |
+
 ---
 
 ## The Artifact Engine
 
-Dev Booster operates an internal **Artifact Engine** (Shadow Memory). As boosters execute, they automatically generate and update machine-readable `.md` files in the background to track history, audits, and architectural decisions. 
+Dev Booster operates an internal **Artifact Engine** (Shadow Memory), but artifact generation is no longer a continuous background behavior for every booster.
+
+### New default behavior
+- exploratory, advisory, and iterative boosters answer in chat first
+- they do **not** create artifacts during normal execution
+- if the result is stable, they may offer to save it at the end of the conversation
+- documentation and persistence boosters may generate a final file only after confirmation
+- no booster should silently keep updating artifact files in the background
+
+This keeps the conversation faster while still preserving the option to materialize important outputs in `@booster-generated/` when the user actually wants them.
+
+### Booster artifact policy
+
+#### 1. No artifact by default — only if the user explicitly asks
+- `advisor.md`
+- `context.md`
+- `debug.md`
+- `deploy.md`
+- `discovery.md`
+- `investigation.md`
+- `planning.md`
+- `security.md`
+
+#### 2. Final artifact only after confirmation
+- `code-audit.md`
+- `global-documentation.md`
+- `implementation.md`
+- `internal-documentation.md`
 
-This creates a persistent "paper trail" that ensures the AI never loses context, even if you continue the work in a brand new chat session.
+#### 3. Persistence-first booster
+- `save-context.md`
 
-Files are systematically organized in the `@booster-generated/` root directory, each booster writing to its own folder:
-- `@booster-generated/context/` (Context assimilation state)
-- `@booster-generated/planning/` (Implementation roadmaps and risk mapping)
-- `@booster-generated/debug/` (Systematic RCA and bug fix logs)
-- `@booster-generated/security/` (Security audit reports)
-- `@booster-generated/code-audit/` (Code audit and diagnostics)
-- `@booster-generated/saved-context/` (Conversation snapshots for chat continuity)
-- `@booster-generated/discovery/`, `@booster-generated/investigation/`, `@booster-generated/advisor/`, `@booster-generated/deploy/`, and more.
+### Artifact locations
+When a user explicitly asks to save or confirms final generation, artifacts are organized under `@booster-generated/`, with each booster writing to its own folder.
 
 ### Manual & Shortcut Triggers
 
 You can take manual control of the kit's governance or instantly route behavior modes at any time using explicit Chat Triggers:
 
 #### 👥 Governance Triggers
-- **`@SaveContext`**: Compacta toda a conversa em YAML para continuar em um novo chat sem perda de contexto. Gera em `@booster-generated/saved-context/context-<slug>.yaml`.
+- **`@SaveContext`**: Compacta toda a conversa em YAML para continuar em um novo chat sem perda de contexto. Gera em `@booster-generated/saved-context/context-<slug>.yaml` após confirmação.
 - **`@SavePattern`**: Instructs the AI to extract a newly resolved technical rule or code pattern and persist it to `.devbooster/rules/USER_PREFERENCES.md`.
 - **`@LogTask`**: Tells the AI to capture a pending technical task and document it systematically in your backlog at `@booster-generated/tasks.md`.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dev-booster",
-  "version": "1.15.0",
+  "version": "1.16.1",
   "description": "Reusable AI development kit with manual boosters, governance, and project bootstrap",
   "type": "module",
   "scripts": {

package/template/.devbooster/MANIFEST.md

@@ -186,27 +186,38 @@ When the user asks "How can the kit help?", the Advisor MUST:
 ---
 
 ## 📂 7. ARTIFACT ENGINE (SHADOW MEMORY)
-Dev Booster acts as a continuous document generator. As boosters execute, they write their history, findings, audits, and implementation plans into structured, machine-readable files. This avoids context loss in long AI conversations and builds a tangible paper trail for the developer.
+Dev Booster no longer treats every booster as a continuous document generator. Artifact creation is now selective and user-controlled: exploratory boosters should stay fast and conversational, while documentation and persistence boosters may generate files only at the end of the flow or after explicit confirmation.
 
 **Target Root Path:** `@booster-generated/`
 
-### Artifact Mapping by Domain:
-- `@booster-generated/advisor/` → Managed by `advisor.md`
-- `@booster-generated/code-audit/` → Managed by `code-audit.md`
-- `@booster-generated/context/` → Managed by `context.md`
-- `@booster-generated/debug/` → Managed by `debug.md`
-- `@booster-generated/deploy/` → Managed by `deploy.md`
-- `@booster-generated/discovery/` → Managed by `discovery.md`
-- `@booster-generated/global-documentation/` → Managed by `global-documentation.md`
-- `@booster-generated/implementation/` → Managed by `implementation.md`
-- `@booster-generated/internal-documentation/` → Managed by `internal-documentation.md`
-- `@booster-generated/investigation/` → Managed by `investigation.md`
-- `@booster-generated/planning/` → Managed by `planning.md`
-- `@booster-generated/saved-context/` → Managed by `save-context.md`
-- `@booster-generated/security/` → Managed by `security.md`
+### Artifact Policy by Booster Type
+
+#### A. Optional only on explicit user request
+These boosters must answer in chat first and must NOT create artifacts during normal execution:
+- `advisor.md` → `@booster-generated/advisor/`
+- `context.md` → `@booster-generated/context/`
+- `debug.md` → `@booster-generated/debug/`
+- `deploy.md` → `@booster-generated/deploy/`
+- `discovery.md` → `@booster-generated/discovery/`
+- `investigation.md` → `@booster-generated/investigation/`
+- `planning.md` → `@booster-generated/planning/`
+- `security.md` → `@booster-generated/security/`
+
+#### B. Final artifact only after confirmation or explicit save intent
+These boosters may generate a final deliverable artifact, but only after the user confirms the final generation step:
+- `code-audit.md` → `@booster-generated/code-audit/`
+- `global-documentation.md` → `@booster-generated/global-documentation/`
+- `implementation.md` → `@booster-generated/implementation/`
+- `internal-documentation.md` → `@booster-generated/internal-documentation/`
+
+#### C. Persistence-first booster
+This booster exists specifically to persist context and may generate its artifact as its primary outcome after confirmation:
+- `save-context.md` → `@booster-generated/saved-context/`
 
 ### Behavior Rules:
 - Each booster writes to its own folder — no overlapping paths.
+- Artifacts are never written silently in the background.
 - Files are never overwritten: if a slug already exists, a variation is generated.
-- The AI must notify the user after writing: 📝 Registo em `@booster-generated/<booster>/<slug>.md`
-- No silent background updates — the user is always informed.
+- When an artifact is written, the AI must notify the user after writing.
+- Exploratory and advisory boosters should prefer chat output over file generation.
+- Documentation and persistence boosters should treat artifact creation as a finalization step, not as a continuous side effect.

package/template/.devbooster/boosters/advisor.md

@@ -66,12 +66,11 @@ Analyze the user's request or the current task and recommend only the best boost
 - Do NOT expose skills, personas, or agents in the user-facing answer.
 - Do NOT execute any plan, only advise.
 
-## ARTIFACT GENERATION
-During your execution, create a state file at `@booster-generated/advisor/<slug>.md` tracking the history, decisions, rules, and outcomes in dense, non-conversational format.
-
-- **Uniqueness rule:** If the slug already exists in `@booster-generated/advisor/`, generate a new variation of the name instead of overwriting
-- **Notification rule:** After writing, notify the user with: 📝 Registo em `@booster-generated/advisor/<slug>.md`
-
-Do NOT update this file silently in the background.
-
-**Reply:** On activation only, use the armed-mode banner above, always following the global language configured for the active LLM/environment. When the user shares an idea or task, read the manifest, classify the need, and recommend the best booster path without executing it.
+## ARTIFACT POLICY
+- Do NOT create local state files or artifacts during normal advisory execution.
+- Deliver the recommendation directly in chat first.
+- Only if the user explicitly asks to persist the result, generate a summary artifact at `@booster-generated/advisor/<slug>.md`.
+- Never create or update this artifact silently in the background.
+- If the advisory result is stable and the conversation turn is complete, you may end with one short optional offer such as: `If you want, I can save this recommendation as an artifact.`
+
+**Reply:** On activation only, use the armed-mode banner above, always following the global language configured for the active LLM/environment. When the user shares an idea or task, read the manifest, classify the need, and recommend the best booster path without executing it. Do not generate artifacts unless the user explicitly asks for one.

package/template/.devbooster/boosters/code-audit.md

@@ -78,12 +78,14 @@ Your response MUST be an **Audit Report**:
 - [Explicitly state that the full line-by-line list of all warnings/errors is available in `@booster-generated/code-audit/diagnostics-<task-slug>.json` for manual review]
 - [Waiting for user permission to apply fixes]
 
-## ARTIFACT GENERATION
-During your execution, create a state file at `@booster-generated/code-audit/<slug>.md` tracking the history, decisions, rules, and outcomes in dense, non-conversational format.
-
-- **Uniqueness rule:** If the slug already exists in `@booster-generated/code-audit/`, generate a new variation of the name instead of overwriting
-- **Notification rule:** After writing, notify the user with: 📝 Registo em `@booster-generated/code-audit/<slug>.md`
-
-Do NOT update this file silently in the background.
-
-**Reply:** On activation only, use the armed-mode banner above and ask for the commit scope. After the user provides the scope, load the necessary scripts, perform the audit, and answer in the global language configured for the active LLM/environment.
+## ARTIFACT POLICY
+- This booster may generate a final audit artifact, but not during activation or before the audit result is presented.
+- Deliver the audit report in chat first.
+- If React/Next.js diagnostics are relevant, the temporary diagnostics JSON at `@booster-generated/code-audit/diagnostics-<task-slug>.json` may still be generated as an operational working file for the audit flow.
+- Only if the user explicitly asks to persist the final audit summary, generate a report artifact at `@booster-generated/code-audit/<slug>.md`.
+- Do not create or update the final audit artifact silently in the background.
+- **Uniqueness rule:** If the slug already exists in `@booster-generated/code-audit/`, generate a new variation of the name instead of overwriting.
+- **Notification rule:** After writing the final audit artifact, notify the user with: 📝 Registo em `@booster-generated/code-audit/<slug>.md`.
+- After presenting a stable audit result, you may end with one short optional offer such as: `If you want, I can save this audit summary as an artifact.`
+
+**Reply:** On activation only, use the armed-mode banner above and ask for the commit scope. After the user provides the scope, load the necessary scripts, perform the audit, and answer in the global language configured for the active LLM/environment. Do not generate the final audit artifact unless the user explicitly asks for one.

package/template/.devbooster/boosters/context.md

@@ -43,22 +43,22 @@ When the first real assimilation request arrives:
 - **NO UNSOLICITED ADVICE:** You MUST NOT suggest refactorings, point out technical debt, or critique the existing architecture/clean code patterns.
 - **ZERO CODE OUTPUT:** Your role is purely receptive and structural.
 - **MEMORIZATION ONLY:** Read the files, map their imports, trace the data flow (inputs, outputs, side effects, APIs), and store this representation in your active context memory.
-## ARTIFACT GENERATION
-During your execution, create a state file at `@booster-generated/context/<slug>.md` tracking the history, decisions, rules, and outcomes in dense, non-conversational format.
-
-- **Uniqueness rule:** If the slug already exists in `@booster-generated/context/`, generate a new variation of the name instead of overwriting
-- **Notification rule:** After writing, notify the user with: 📝 Registo em `@booster-generated/context/<slug>.md`
-
-Do NOT update this file silently in the background.
+## ARTIFACT POLICY
+- Do NOT create local state files or artifacts during normal context assimilation.
+- Keep the mapped context in active memory and acknowledge completion in chat only.
+- Only if the user explicitly asks to persist the mapped context, generate a summary artifact at `@booster-generated/context/<slug>.md`.
+- Never create or update this artifact silently in the background.
+- If the mapping is complete and stable, you may end with one short optional offer such as: `If you want, I can save this mapped context as an artifact.`
 
 ## 3. CONFIRMATION PROTOCOL
-Once you have fully read, parsed, mapped the flow, AND updated the state backup file:
+Once you have fully read, parsed, and mapped the flow:
 1. Clear your output of any technical jargon, file contents, code snippets, or rules explanations.
 2. Respond with an ultra-short, highly professional 1-to-2 line acknowledgment in the user's active conversation language.
-3. Confirm that the context is fully mapped with the artifact available at the registered path.
-4. **NO PROACTIVITY:** Do NOT ask follow-up questions, do NOT suggest next steps, and do NOT ask what to do next. Simply state that the context has been absorbed and wait silently for the user's next command.
+3. Confirm that the context is fully mapped and retained in active memory.
+4. You MAY add one short optional artifact offer, but only after the acknowledgment and only if the mapping is stable.
+5. **NO PROACTIVITY:** Do NOT suggest next steps and do NOT ask what to do next. Apart from the optional artifact offer, simply state that the context has been absorbed and wait silently for the user's next command.
 
 Example response:
-> *"Fluxo mapeado com sucesso. O contexto técnico está armazenado na memória e registado em `@booster-generated/context/<slug>.md`."*
+> *"Fluxo mapeado com sucesso. O contexto técnico está retido na memória ativa. Se quiser, posso salvar esse mapeamento como artefato."*
 
-**Reply:** On activation only, use the armed-mode banner above. On the first real task, load the allowed personas silently, read the files, create/update the context backup file, map the flow internally, and reply with the non-proactive, ultra-short acknowledgment protocol.
+**Reply:** On activation only, use the armed-mode banner above. On the first real task, load the allowed personas silently, read the files, map the flow internally, and reply with the ultra-short acknowledgment protocol. Do not generate artifacts unless the user explicitly asks for one.

package/template/.devbooster/boosters/debug.md

@@ -53,11 +53,11 @@ Your response MUST use this exact format:
 ---
 
 **Response: "Elite Debugger Mode Activated. Diagnostic tools and Hypothesis engine online. Please provide the error logs and where it's happening."**
-## ARTIFACT GENERATION
-During your execution, create a state file at `@booster-generated/debug/<slug>.md` tracking the history, decisions, rules, and outcomes in dense, non-conversational format.
 
-- **Uniqueness rule:** If the slug already exists in `@booster-generated/debug/`, generate a new variation of the name instead of overwriting
-- **Notification rule:** After writing, notify the user with: 📝 Registo em `@booster-generated/debug/<slug>.md`
-
-Do NOT update this file silently in the background.
+## ARTIFACT POLICY
+- Do NOT create local state files or artifacts during normal debug execution.
+- Keep the debugging loop focused on reproducing, isolating, and fixing the issue.
+- Only if the user explicitly asks to persist the result, generate a summary artifact at `@booster-generated/debug/<slug>.md`.
+- Never create or update this artifact silently in the background.
+- After the root cause and fix are stable, you may end with one short optional offer such as: `If you want, I can save this debug report as an artifact.`
 

package/template/.devbooster/boosters/deploy.md

@@ -1,5 +1,25 @@
-# 🚀 BOOSTER: DEPLOY & DEVOPS
-Activating Infrastructure and Continuous Delivery Specialist.
+# 🚀 BOOSTER: DEPLOY AUDIT & DEVOPS
+Activating Infrastructure and Delivery Audit Specialist.
+
+## 0. HARD SAFETY RULE
+This booster is strictly audit-only.
+
+It MUST NOT:
+- run deploy commands
+- trigger production, preview, staging, or infrastructure changes
+- execute `vercel`, `netlify`, `firebase deploy`, `gcloud app deploy`, `gcloud run deploy`, `kubectl apply`, `helm upgrade`, `docker compose up`, `docker stack deploy`, `pm2 deploy`, `ssh` deployment flows, or any equivalent command
+- publish packages, release artifacts, or promote builds
+- restart services, mutate servers, or apply infra changes in VPS, cloud, containers, CI/CD, or hosting platforms
+
+Even if the user is discussing Vercel, VPS, GCP, AWS, Docker, Kubernetes, CI/CD, or any other platform, this booster must remain in audit mode only.
+
+It MAY:
+- inspect configuration files
+- review deploy scripts and CI/CD workflows
+- audit environment assumptions, secrets usage, and rollout risks
+- validate readiness checklists
+- point out missing steps, risky commands, or unsafe rollout patterns
+- suggest the exact commands the user should run manually, without executing them
 
 ## 1. MANDATORY CONTEXT LOADING
 - `.devbooster/hub/personas/agent_devops-engineer.md`
@@ -8,12 +28,21 @@ Activating Infrastructure and Continuous Delivery Specialist.
 - `.devbooster/hub/personas/skill_bash-linux.md`
 - `.devbooster/hub/personas/skill_server-management.md`
 
-**Reply: "Deploy & DevOps Mode Activated. Production launch or infra maintenance? What do we need to run?"**
-## ARTIFACT GENERATION
-During your execution, create a state file at `@booster-generated/deploy/<slug>.md` tracking the history, decisions, rules, and outcomes in dense, non-conversational format.
+## 2. OPERATING MODE
+When activated:
+- inspect the relevant deploy configuration, scripts, workflows, or infra files
+- act as a pre-flight auditor only
+- return risks, missing checks, and recommended manual next steps
+- never execute the deploy path itself
+
+## 3. ARTIFACT POLICY
+- Do NOT create local state files or artifacts during normal deploy auditing.
+- Deliver the readiness audit directly in chat first.
+- Only if the user explicitly asks to persist the result, generate a deploy audit artifact at `@booster-generated/deploy/<slug>.md`.
+- Do not create or update this artifact silently in the background.
+- After presenting a stable deploy audit, you may end with one short optional offer such as: `If you want, I can save this deploy audit as an artifact.`
+
+**Reply: "Deploy Audit Mode Activated. I can audit readiness, scripts, infra, and rollout risks, but I will not run any deployment command. I will not generate artifacts unless you ask me to save the final audit."**
 
-- **Uniqueness rule:** If the slug already exists in `@booster-generated/deploy/`, generate a new variation of the name instead of overwriting
-- **Notification rule:** After writing, notify the user with: 📝 Registo em `@booster-generated/deploy/<slug>.md`
 
-Do NOT update this file silently in the background.
 

package/template/.devbooster/boosters/discovery.md

@@ -72,12 +72,11 @@ After presenting the options, ask the user:
 1. Which direction aligns best with your current priority?
 2. Are there any specific constraints we should consider for the chosen path?
 
-## ARTIFACT GENERATION
-During your execution, create a state file at `@booster-generated/discovery/<slug>.md` tracking the history, decisions, rules, and outcomes in dense, non-conversational format.
-
-- **Uniqueness rule:** If the slug already exists in `@booster-generated/discovery/`, generate a new variation of the name instead of overwriting
-- **Notification rule:** After writing, notify the user with: 📝 Registo em `@booster-generated/discovery/<slug>.md`
-
-Do NOT update this file silently in the background.
-
-**Reply:** On activation only, use the armed-mode banner above and open the conversation. After the first real idea arrives, load the minimum required discovery context and continue with the discovery flow in the global language configured for the active LLM/environment.
+## ARTIFACT POLICY
+- Do NOT create local state files or artifacts during normal discovery execution.
+- Keep brainstorming fast and conversational.
+- Only if the user explicitly asks to persist the result, generate a summary artifact at `@booster-generated/discovery/<slug>.md`.
+- Never create or update this artifact silently in the background.
+- After presenting a stable discovery result, you may end with one short optional offer such as: `If you want, I can consolidate this discovery into an artifact.`
+
+**Reply:** On activation only, use the armed-mode banner above and open the conversation. After the first real idea arrives, load the minimum required discovery context and continue with the discovery flow in the global language configured for the active LLM/environment. Do not generate artifacts unless the user explicitly asks for one.

package/template/.devbooster/boosters/global-documentation.md

@@ -103,10 +103,13 @@ Use these 17 sections in this exact order:
 - If the context is ambiguous, state the ambiguity before writing.
 - Do NOT invent flows, contracts, or business rules that were not established.
 
-## ARTIFACT GENERATION
-After generating the documentation, a state file is created at `@booster-generated/global-documentation/<feature-context>-global-documentation.md`.
-
-- **Uniqueness rule:** If a file with the same slug already exists in `@booster-generated/global-documentation/`, generate a new variation of the name instead of overwriting
-- **Notification rule:** After writing, notify the user with: 📝 Documento criado em `@booster-generated/global-documentation/<feature-context>-global-documentation.md`
+## ARTIFACT POLICY
+- This booster may generate a final documentation artifact, but never during the initial synthesis or confirmation phase.
+- First, summarize the current context in chat and confirm scope with the user.
+- After the user confirms documentation generation, produce the final artifact at `@booster-generated/global-documentation/<feature-context>-global-documentation.md`.
+- Do not create or update this artifact silently in the background.
+- **Uniqueness rule:** If a file with the same slug already exists in `@booster-generated/global-documentation/`, generate a new variation of the name instead of overwriting.
+- **Notification rule:** After writing, notify the user with: 📝 Documento criado em `@booster-generated/global-documentation/<feature-context>-global-documentation.md`.
+- If the documentation was discussed in chat but not yet generated as a file, end with a short confirmation prompt asking whether the user wants the artifact generated now.
 
 **Reply:** On activation only, review the current conversation context, summarize it, and ask if you may proceed with the documentation. After explicit confirmation, generate the documentation in the global language configured for the active LLM/environment.

package/template/.devbooster/boosters/implementation.md

@@ -79,10 +79,13 @@ Evaluate the task complexity and select the corresponding template file:
 3. **Load Template:** After confirmation, read the full content of the selected template file.
 4. **Generate:** Apply the loaded template rules to the current context and produce the final plan.
 
-## ARTIFACT GENERATION
-After generating the implementation plan, a state file is created at `@booster-generated/implementation/<task>-implementation.md`.
-
-- **Uniqueness rule:** If a file with the same slug already exists in `@booster-generated/implementation/`, generate a new variation of the name instead of overwriting
-- **Notification rule:** After writing, notify the user with: 📝 Plano criado em `@booster-generated/implementation/<task>-implementation.md`
+## ARTIFACT POLICY
+- This booster may generate a final implementation artifact, but never during the exploratory or sizing phase.
+- First, deliver the context summary, selected template, and rationale in chat.
+- After the user confirms the plan generation, produce the final artifact at `@booster-generated/implementation/<task>-implementation.md`.
+- Do not create or update this artifact silently in the background.
+- **Uniqueness rule:** If a file with the same slug already exists in `@booster-generated/implementation/`, generate a new variation of the name instead of overwriting.
+- **Notification rule:** After writing, notify the user with: 📝 Plano criado em `@booster-generated/implementation/<task>-implementation.md`.
+- If the implementation plan was discussed in chat but not yet generated as a file, end with a short confirmation prompt asking whether the user wants the artifact generated now.
 
 **Reply:** On activation only, review the current conversation context, summarize it, select `simple`, `standard`, or `heavy`, explain why, and ask if you may proceed. After explicit confirmation, load the selected template and generate the implementation plan in the global language configured for the active LLM/environment.

package/template/.devbooster/boosters/internal-documentation.md

@@ -141,10 +141,13 @@ The result of this booster should be:
 - A repository-specific internal documentation file.
 - A concise completion report in chat with the artifact path and any unresolved gaps.
 
-## ARTIFACT GENERATION
-After generating the documentation, a state file is created at `@booster-generated/internal-documentation/internal-project-documentation.md`.
-
-- **Uniqueness rule:** If a file with the same slug already exists in `@booster-generated/internal-documentation/`, generate a new variation of the name instead of overwriting
-- **Notification rule:** After writing, notify the user with: 📝 Documento criado em `@booster-generated/internal-documentation/internal-project-documentation.md`
+## ARTIFACT POLICY
+- This booster may generate a final internal documentation artifact, but never during the initial review or confirmation phase.
+- First, summarize the current context, scope, and gaps in chat.
+- After the user confirms documentation generation, produce the final artifact at `@booster-generated/internal-documentation/internal-project-documentation.md`.
+- Do not create or update this artifact silently in the background.
+- **Uniqueness rule:** If a file with the same slug already exists in `@booster-generated/internal-documentation/`, generate a new variation of the name instead of overwriting.
+- **Notification rule:** After writing, notify the user with: 📝 Documento criado em `@booster-generated/internal-documentation/internal-project-documentation.md`.
+- If the documentation was discussed in chat but not yet generated as a file, end with a short confirmation prompt asking whether the user wants the artifact generated now.
 
 **Reply:** On activation only, review the current conversation context, summarize it, identify scope and gaps, and ask if you may proceed with internal documentation. After explicit confirmation, scan the repository and generate the documentation in the global language configured for the active LLM/environment.

package/template/.devbooster/boosters/investigation.md

@@ -93,12 +93,11 @@ Organize your response as follows:
 - Initially, analyze ONLY the `package.json` to understand the project structure and stack.
 - Do NOT be proactive in execution. Your goal is certainty and lack of ambiguity.
 
-## ARTIFACT GENERATION
-During your execution, create a state file at `@booster-generated/investigation/<slug>.md` tracking the history, decisions, rules, and outcomes in dense, non-conversational format.
-
-- **Uniqueness rule:** If the slug already exists in `@booster-generated/investigation/`, generate a new variation of the name instead of overwriting
-- **Notification rule:** After writing, notify the user with: 📝 Registo em `@booster-generated/investigation/<slug>.md`
-
-Do NOT update this file silently in the background.
-
-**Reply:** On activation only, use the armed-mode banner above with a professional investigation opening. After the first real request arrives, load the minimum required investigation context and continue in the global language configured for the active LLM/environment.
+## ARTIFACT POLICY
+- Do NOT create local state files or artifacts during normal investigation execution.
+- Deliver the investigation findings directly in chat first.
+- Only if the user explicitly asks to persist the result, generate a summary artifact at `@booster-generated/investigation/<slug>.md`.
+- Never create or update this artifact silently in the background.
+- After a stable investigation result, you may end with one short optional offer such as: `If you want, I can save this investigation as an artifact.`
+
+**Reply:** On activation only, use the armed-mode banner above with a professional investigation opening. After the first real request arrives, load the minimum required investigation context and continue in the global language configured for the active LLM/environment. Do not generate artifacts unless the user explicitly asks for one.

package/template/.devbooster/boosters/planning.md

@@ -89,12 +89,11 @@ On activation only:
 
 Only after the user confirms should this booster continue the alignment process and determine whether the task is ready for implementation.
 
-## ARTIFACT GENERATION
-During your execution, create a state file at `@booster-generated/planning/<slug>.md` tracking the history, decisions, rules, and outcomes in dense, non-conversational format.
-
-- **Uniqueness rule:** If the slug already exists in `@booster-generated/planning/`, generate a new variation of the name instead of overwriting
-- **Notification rule:** After writing, notify the user with: 📝 Registo em `@booster-generated/planning/<slug>.md`
-
-Do NOT update this file silently in the background.
-
-**Reply:** On activation only, review the current conversation context, summarize what is already defined, identify risks and gaps, and ask whether the user wants to proceed with planner alignment. Do not emit the final readiness verdict until the user confirms. Always answer in the global language configured for the active LLM/environment.
+## ARTIFACT POLICY
+- Do NOT create local state files or artifacts during normal planning alignment.
+- Deliver the readiness analysis directly in chat first.
+- Only if the user explicitly asks to persist the result, generate a summary artifact at `@booster-generated/planning/<slug>.md`.
+- Never create or update this artifact silently in the background.
+- After a stable readiness conclusion, you may end with one short optional offer such as: `If you want, I can save this planning analysis as an artifact.`
+
+**Reply:** On activation only, review the current conversation context, summarize what is already defined, identify risks and gaps, and ask whether the user wants to proceed with planner alignment. Do not emit the final readiness verdict until the user confirms. Always answer in the global language configured for the active LLM/environment. Do not generate artifacts unless the user explicitly asks for one.

package/template/.devbooster/boosters/security.md

@@ -57,12 +57,13 @@ Rules:
 - `.devbooster/hub/skills/vulnerability-scanner/SKILL.md`
 - `.devbooster/hub/skills/red-team-tactics/SKILL.md`
 
-## ARTIFACT GENERATION
-During your execution, create a state file at `@booster-generated/security/<slug>.md` tracking the history, decisions, rules, and outcomes in dense, non-conversational format.
-
-- **Uniqueness rule:** If the slug already exists in `@booster-generated/security/`, generate a new variation of the name instead of overwriting
-- **Notification rule:** After writing, notify the user with: 📝 Registo em `@booster-generated/security/<slug>.md`
-
-Do NOT update this file silently in the background.
-
-**Reply:** On activation only, use the armed-mode banner above. On the first real task, load the minimum required security context based on the user's pain, then execute.
+## ARTIFACT POLICY
+- Do NOT create local state files or artifacts during the initial security analysis.
+- Deliver the security findings directly in chat first.
+- Only if the user explicitly asks to persist the result, generate a security report artifact at `@booster-generated/security/<slug>.md`.
+- Do not create or update this artifact silently in the background.
+- After presenting a stable security result, you may end with one short optional offer such as: `If you want, I can save this security report as an artifact.`
+- **Uniqueness rule:** If the slug already exists in `@booster-generated/security/`, generate a new variation of the name instead of overwriting.
+- **Notification rule:** After writing, notify the user with: 📝 Registo em `@booster-generated/security/<slug>.md`.
+
+**Reply:** On activation only, use the armed-mode banner above. On the first real task, load the minimum required security context based on the user's pain, then execute. Do not generate artifacts unless the user explicitly asks for one.