godpowers 0.15.15 → 0.15.17

package/CHANGELOG.md

@@ -5,6 +5,41 @@ All notable changes to Godpowers will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.15.17] - 2026-05-12
+
+Greenfieldification release. Turns the brownfield and bluefield simulation
+audit into a controlled artifact migration instead of a passive report.
+
+### Added
+- Added `god-greenfieldifier`, a Tier 0 agent that writes
+  `.godpowers/audit/GREENFIELDIFY-PLAN.md`, classifies audit findings, pauses
+  before risky canonical artifact rewrites, and then updates affected artifacts
+  after approval.
+
+### Changed
+- Brownfield arc now runs greenfieldification after the greenfield simulation
+  audit and before steady-state handoff.
+- Bluefield arc now runs greenfieldification after the greenfield simulation
+  audit and before PRD.
+- `/god-mode`, `god-orchestrator`, and `/god-audit` now document that the
+  simulation audit must be acted on through a thorough, approval-gated artifact
+  migration.
+
+## [0.15.16] - 2026-05-11
+
+Greenfield simulation audit release. Adds a preparation audit to brownfield
+and bluefield arcs so they can compare existing evidence or org constraints
+against the canonical Godpowers greenfield process.
+
+### Changed
+- Brownfield arc now runs a greenfield simulation audit after archaeology,
+  reconstruction, debt assessment, and normal artifact audit.
+- Bluefield arc now runs a greenfield simulation audit after org-context and
+  before PRD so downstream planning can inherit org constraints intentionally.
+- `god-auditor` now documents `mode: greenfield-simulation`, writing
+  `.godpowers/audit/GREENFIELD-SIMULATION.md` without rewriting planning
+  artifacts.
+
 ## [0.15.15] - 2026-05-11
 
 Transcript hygiene release. Keeps God Mode orchestration scaffolding out of the

package/README.md

@@ -2,7 +2,7 @@
 
 [![CI](https://github.com/aihxp/godpowers/actions/workflows/ci.yml/badge.svg)](https://github.com/aihxp/godpowers/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
-[![Version](https://img.shields.io/badge/version-0.15.15-blue)](CHANGELOG.md)
+[![Version](https://img.shields.io/badge/version-0.15.17-blue)](CHANGELOG.md)
 [![npm](https://img.shields.io/npm/v/godpowers.svg)](https://www.npmjs.com/package/godpowers)
 
 **Ship fast. Ship right. Ship everything. Ship accountably.**
@@ -156,6 +156,12 @@ reported as the final result.
 If `.godpowers` state already exists, `/god-mode --yolo` resumes from disk
 instead of asking for the project description again.
 
+For existing codebases and org-constrained new projects, God Mode now runs a
+greenfield simulation audit and then actions it through a greenfieldification
+plan. It pauses before risky artifact rewrites because that process can change
+product scope, design direction, architecture, roadmap, stack, and shipping
+commitments.
+
 ## Architecture
 
 ### Slash Command + Specialist Agent Pattern
@@ -200,9 +206,9 @@ Skill updates:   PROGRESS.md
 .godpowers/harden/FINDINGS.md  Security Findings
 ```
 
-## Quality Guarantees
+## Quality Guardrails
 
-Every artifact passes these mechanical checks:
+Every artifact passes these mechanical checks before it is treated as complete:
 
 | Check | What it catches |
 |---|---|
@@ -214,6 +220,26 @@ Every artifact passes these mechanical checks:
 | TDD enforcement | Code without tests |
 | Two-stage review | Code that passes tests but violates spec or quality |
 
+These checks are guardrails, not proof that the product is right. A PRD can
+pass the substitution test and still make the wrong product call. Godpowers
+uses mechanical checks to catch generic, missing, or untraceable work so the
+remaining judgment is visible to humans and reviewers.
+
+## Operational Reality
+
+Godpowers is pre-launch. See [USERS.md](USERS.md) for current adoption status.
+
+Full autonomous runs can be expensive because they spawn multiple fresh-context
+agents. The runtime records token and dollar estimates through `cost.recorded`
+events, and `/god-cost` reports spend, savings, live vs estimated token counts,
+and cache hits. `/god-budget` configures context caps, cache use, and model
+profiles. `/god-metrics` and `/god-trace` expose run duration, pauses, retries,
+and per-tier history from `.godpowers/runs/<id>/events.jsonl`.
+
+Treat a real `/god-mode` result as successful only when it produces shipped or
+ship-ready work on someone else's codebase, with validation results, cost, and
+wall-clock time visible.
+
 ## Pause Philosophy
 
 God Mode pauses only when:
@@ -237,7 +263,7 @@ Pi. T3 Code inherits from the underlying agent (Codex / Claude / OpenCode).
 
 - [Getting Started](docs/getting-started.md)
 - [Concepts](docs/concepts.md)
-- [Command reference (all 105 skills + 38 agents)](docs/reference.md)
+- [Command reference (all 105 skills + 39 agents)](docs/reference.md)
 - [Roadmap](docs/ROADMAP.md)
 - [Changelog](CHANGELOG.md)
 - [Inspiration](INSPIRATION.md)

package/agents/god-auditor.md

@@ -31,6 +31,9 @@ Score artifacts. Build nothing. Report what fails and why.
 4. If running for orchestrator gate check: return verdict only (any
    error from mechanical pass = FAIL; any critical interpretive = FAIL).
 5. If running for /god-audit: produce full report combining both passes.
+6. If running with `mode: greenfield-simulation`, do not build anything.
+   Simulate the canonical Godpowers greenfield arc and compare it against the
+   current project evidence or org constraints.
 
 ## Mechanical vs interpretive split
 
@@ -148,3 +151,61 @@ Overall: 85%
 
 For gate check (called by orchestrator): return PASS/FAIL with first failure
 only (orchestrator wants speed, not full report).
+
+For greenfield simulation audit, write
+`.godpowers/audit/GREENFIELD-SIMULATION.md`:
+
+```markdown
+# Greenfield Simulation Audit
+
+Date: [timestamp]
+Mode: [brownfield | bluefield]
+
+## Simulated Canonical Arc
+- PRD: [what a clean Godpowers PRD would need]
+- Design: [whether DESIGN.md should exist before ARCH]
+- ARCH: [expected architecture decisions]
+- ROADMAP: [expected sequencing]
+- STACK: [expected stack decision points]
+- REPO: [expected repo setup]
+- BUILD: [expected vertical-slice delivery]
+- DEPLOY: [expected deploy and rollback gates]
+- OBSERVE: [expected SLOs and runbooks]
+- HARDEN: [expected security gates]
+- LAUNCH: [expected launch readiness gates]
+
+## Evidence Compared
+- [source path or org-context source]
+
+## Alignment
+| Area | Greenfield Expectation | Existing Evidence | Status |
+|---|---|---|---|
+| PRD | [expectation] | [evidence] | aligned / gap / unknown |
+
+## Gaps To Carry Forward
+- [DECISION/HYPOTHESIS/OPEN QUESTION] [gap and where it should influence PRD, ARCH, ROADMAP, BUILD, or shipping]
+
+## Non-Goals
+- This audit does not rewrite artifacts.
+- This audit must be followed by `god-greenfieldifier` in brownfield and
+  bluefield workflows when the user wants the audit acted on.
+- This audit does not treat imported GSD, Superpowers, BMAD, or org context as
+  source of truth.
+- This audit does not block the arc unless it finds a Critical security or
+  impossible planning contradiction.
+```
+
+Greenfield simulation rules:
+- Brownfield: compare reconstructed artifacts, archaeology, debt assessment,
+  repo shape, tests, CI, deploy, observability, hardening, and launch evidence
+  against what the canonical greenfield arc would have created.
+- Bluefield: compare org context and constraints against the canonical
+  greenfield arc before PRD so downstream agents know which choices are
+  constrained, missing, or open.
+- Label every finding as DECISION, HYPOTHESIS, or OPEN QUESTION.
+- Do not invent missing intent. Mark unknowns as OPEN QUESTION.
+- Do not overwrite PRD, ARCH, ROADMAP, STACK, or shipping artifacts. This audit
+  is preparation context for downstream steps.
+- In brownfield and bluefield workflows, hand this audit to god-greenfieldifier
+  so it can produce `.godpowers/audit/GREENFIELDIFY-PLAN.md`, pause for
+  approval when needed, and then update the affected artifacts thoroughly.

package/agents/god-greenfieldifier.md

@@ -0,0 +1,159 @@
+---
+name: god-greenfieldifier
+description: |
+  Turns a greenfield simulation audit into a controlled artifact migration
+  plan for brownfield and bluefield projects. Requires user approval before
+  rewriting canonical Godpowers artifacts.
+
+  Spawned by: brownfield-arc, bluefield-arc, god-orchestrator
+tools: Read, Write, Edit, Bash, Grep, Glob
+---
+
+# God Greenfieldifier
+
+You action the greenfield simulation audit. Your job is to help an existing or
+org-constrained project receive the same thorough Godpowers preparation that a
+greenfield project would have received, without silently breaking project
+intent, architecture, delivery commitments, or org constraints.
+
+## Inputs
+
+- `.godpowers/audit/GREENFIELD-SIMULATION.md`
+- `.godpowers/prep/INITIAL-FINDINGS.md`, when present
+- `.godpowers/prep/IMPORTED-CONTEXT.md`, when present
+- Existing canonical artifacts:
+  - `.godpowers/prd/PRD.md`
+  - `.godpowers/design/DESIGN.md`
+  - `.godpowers/product/PRODUCT.md`
+  - `.godpowers/arch/ARCH.md`
+  - `.godpowers/roadmap/ROADMAP.md`
+  - `.godpowers/stack/DECISION.md`
+  - `.godpowers/repo/AUDIT.md`
+  - `.godpowers/build/STATE.md`
+  - `.godpowers/deploy/STATE.md`
+  - `.godpowers/observe/STATE.md`
+  - `.godpowers/launch/STATE.md`
+  - `.godpowers/harden/FINDINGS.md`
+- Source evidence from code, org context, and imported planning systems.
+
+## Process
+
+### 1. Read Before Acting
+
+Read the audit and every existing canonical artifact before recommending any
+rewrite. Disk state is authoritative. Conversation memory is not.
+
+### 2. Classify Each Finding
+
+For every gap in the audit, classify it as exactly one:
+
+- `preserve`: existing artifact is better than canonical greenfield default.
+- `carry-forward`: useful context, but no rewrite yet.
+- `rewrite-candidate`: likely artifact update.
+- `requires-user-approval`: could change product scope, system shape, roadmap,
+  security posture, launch posture, budget, provider, hosting, or org policy.
+- `blocked`: missing evidence prevents a safe rewrite.
+
+### 3. Write The Plan First
+
+Write `.godpowers/audit/GREENFIELDIFY-PLAN.md` before editing canonical
+artifacts.
+
+The plan must include:
+
+- DECISION: Which findings are safe to action.
+- DECISION: Which artifacts would change.
+- HYPOTHESIS: Why each change better matches the canonical greenfield arc.
+- OPEN QUESTION: Any product, org, risk, or architecture choice that needs the
+  user.
+- A per-artifact impact table for PRD, DESIGN, PRODUCT, ARCH, ROADMAP, STACK,
+  REPO, BUILD, DEPLOY, OBSERVE, LAUNCH, and HARDEN.
+- A rollback note describing how to undo the planned artifact changes.
+
+### 4. Pause Before Risky Rewrites
+
+Do not rewrite canonical artifacts when any planned change is classified as
+`requires-user-approval` or `blocked`.
+
+Pause with:
+
+```markdown
+PAUSE: Approve greenfieldification plan?
+
+Why only you can answer: The plan may change product scope, architecture,
+roadmap, stack, or shipping commitments.
+
+| Option | Tradeoff |
+|--------|----------|
+| A: approve | Apply the plan to the listed artifacts. |
+| B: revise | Provide corrections before any artifact rewrite. |
+| C: preserve | Keep the current artifacts and carry the audit forward as prep context. |
+
+Default: If you say "go", I will pick C unless `--yolo` explicitly permits
+artifact rewrites and every change is classified as `rewrite-candidate`.
+```
+
+Under `--yolo`, you may only apply changes without a pause when every change is
+classified as `rewrite-candidate`, no product or org intent changes, and no
+canonical artifact loses existing concrete evidence.
+
+### 5. Apply Approved Changes Thoroughly
+
+When approved, update all affected artifacts, not just the first one:
+
+- PRD: product goals, requirements, metrics, no-gos, open questions.
+- DESIGN: product experience, UI surface, accessibility, workflow, brand.
+- PRODUCT: screens, journeys, user promises, operational UX.
+- ARCH: components, trust boundaries, ADRs, NFR mappings.
+- ROADMAP: sequence, gates, dependencies, delivery increments.
+- STACK: decisions, flip points, org constraints, incompatibilities.
+- REPO: repository shape, CI, tests, security docs, install docs.
+- BUILD: build state, test expectations, review gates.
+- DEPLOY: environment model, deploy checks, rollback.
+- OBSERVE: SLOs, dashboards, alerts, runbooks.
+- LAUNCH: launch gates, copy scope, channel readiness.
+- HARDEN: security findings, auth boundaries, severity.
+
+### 6. Sync State
+
+After approved rewrites:
+
+- Update `.godpowers/SYNC-LOG.md`.
+- Update `.godpowers/PROGRESS.md`.
+- Update `.godpowers/state.json` with:
+  - `greenfieldification.status`
+  - `greenfieldification.plan`
+  - `greenfieldification.approved`
+  - `greenfieldification.updatedArtifacts`
+- Mark unresolved items as open questions, not completed work.
+
+## Rules
+
+- Imported GSD, Superpowers, BMAD, org context, and reconstructed artifacts are
+  evidence, not source of truth.
+- Never erase existing specific evidence to replace it with a generic
+  greenfield default.
+- Never silently change product scope, stack, architecture, launch posture, or
+  security posture.
+- Label every sentence written to Godpowers artifacts as DECISION, HYPOTHESIS,
+  or OPEN QUESTION unless the target artifact has a stricter existing format.
+- If the audit is too shallow to act on, improve the plan with open questions
+  and stop before rewriting artifacts.
+
+## Output
+
+Always write `.godpowers/audit/GREENFIELDIFY-PLAN.md`.
+
+If user approval is required, return the PAUSE block.
+
+If changes are approved and applied, return:
+
+```json
+{
+  "status": "greenfieldified",
+  "plan": ".godpowers/audit/GREENFIELDIFY-PLAN.md",
+  "updatedArtifacts": [],
+  "openQuestions": [],
+  "validation": []
+}
+```

package/agents/god-orchestrator.md

@@ -808,7 +808,9 @@ in a parent suite. The human-friendly label is what the user sees.
 ### Mode B: Brownfield / Gap-fill (auto-detected)
 - Existing code OR partial `.godpowers/` artifacts present
 - May or may not have org context
-- Default path: archaeology -> reconstruct -> debt-assess -> proceed
+- Default path: archaeology -> reconstruct -> debt-assess -> greenfield
+  simulation audit -> greenfieldify plan and approved artifact updates ->
+  proceed
 
 **Detection logic (run this on every Mode B invocation)**:
 
@@ -843,6 +845,27 @@ Report findings to user before running any tier:
    Repo imported (CI present), Build in progress. Resuming from Build."
 ```
 
+### Greenfieldification checkpoint for Mode B and Mode E
+
+The greenfield simulation audit is not enough by itself. It identifies gaps;
+god-greenfieldifier actions those gaps through a controlled artifact migration.
+
+Required sequence:
+
+1. Run greenfield simulation audit.
+2. Spawn god-greenfieldifier.
+3. Write `.godpowers/audit/GREENFIELDIFY-PLAN.md`.
+4. If the plan can change product scope, design direction, architecture,
+   roadmap, stack, deploy, observe, launch, harden, org policy, or user
+   commitments, pause for user approval before rewriting canonical artifacts.
+5. After approval, update every affected artifact, not just the first artifact
+   where the gap appears.
+6. Run sync so PROGRESS.md, state.json, and SYNC-LOG.md reflect what changed.
+
+Under `--yolo`, do not bypass this checkpoint for risky changes. YOLO may only
+auto-apply greenfieldification when every planned change is a non-destructive
+rewrite-candidate and no concrete existing evidence is removed.
+
 ### Mode C: Audit
 - Triggered explicitly with --audit flag
 - Build nothing
@@ -877,6 +900,10 @@ Report findings to user before running any tier:
 - BUT org-context.yaml found (in current dir, parent, or grandparent)
 - Run full arc with all decisions constrained by org context
 - Spawn god-org-context-loader first to load constraints
+- Run greenfield simulation audit after org-context, then run
+  god-greenfieldifier so the arc has an approved artifact plan before PRD.
+  The plan explains where canonical Godpowers defaults align with, conflict
+  with, or are constrained by org standards.
 - All downstream agents (god-stack-selector, god-architect, god-deploy-engineer,
   god-observability-engineer, god-harden-auditor) receive the org-context
   and respect it

package/package.json

@@ -1,14 +1,15 @@
 {
   "name": "godpowers",
-  "version": "0.15.15",
-  "description": "AI-powered development system: 104 slash commands and 38 specialist agents that take a project from raw idea to hardened production. Runs inside Claude Code, Codex, Cursor, Windsurf, Gemini, and 10+ other AI coding tools.",
+  "version": "0.15.17",
+  "description": "AI-powered development system: 105 slash commands and 39 specialist agents that take a project from raw idea to hardened production. Runs inside Claude Code, Codex, Cursor, Windsurf, Gemini, and 10+ other AI coding tools.",
   "bin": {
     "godpowers": "./bin/install.js"
   },
   "scripts": {
-    "test": "node scripts/validate-skills.js && bash scripts/smoke.sh && node scripts/test-runtime.js && node scripts/test-router.js && node scripts/test-recipes.js && node scripts/test-context-writer.js && node scripts/test-artifact-linter.js && node scripts/test-artifact-diff.js && node scripts/test-design-foundation.js && node scripts/test-linkage.js && node scripts/test-impact.js && node scripts/test-reverse-sync.js && node scripts/test-integration.js && node scripts/test-cross-artifact.js && node scripts/test-awesome-design.js && node scripts/test-skillui-bridge.js && node scripts/test-runtime-verification.js && node scripts/test-agent-browser.js && node scripts/test-mode-d.js && node scripts/test-runtime-heuristics.js && node scripts/test-agent-validator.js && node scripts/test-story-validator.js && node scripts/test-state.js && node scripts/test-intent.js && node scripts/test-events.js && node scripts/test-golden-artifacts.js && node scripts/test-install-smoke.js && node scripts/test-checkpoint.js && node scripts/test-extensions.js && node scripts/test-event-reader.js && node scripts/test-state-lock.js && node scripts/test-cost-saver.js && node scripts/test-budget-onoff.js && node scripts/test-workflow-runner.js && node scripts/test-otel-exporter.js && node scripts/test-extensions-publish.js",
+    "test": "node scripts/validate-skills.js && node scripts/test-doc-surface-counts.js && bash scripts/smoke.sh && node scripts/test-runtime.js && node scripts/test-router.js && node scripts/test-recipes.js && node scripts/test-context-writer.js && node scripts/test-artifact-linter.js && node scripts/test-artifact-diff.js && node scripts/test-design-foundation.js && node scripts/test-linkage.js && node scripts/test-impact.js && node scripts/test-reverse-sync.js && node scripts/test-integration.js && node scripts/test-cross-artifact.js && node scripts/test-awesome-design.js && node scripts/test-skillui-bridge.js && node scripts/test-runtime-verification.js && node scripts/test-agent-browser.js && node scripts/test-mode-d.js && node scripts/test-runtime-heuristics.js && node scripts/test-agent-validator.js && node scripts/test-story-validator.js && node scripts/test-state.js && node scripts/test-intent.js && node scripts/test-events.js && node scripts/test-golden-artifacts.js && node scripts/test-install-smoke.js && node scripts/test-checkpoint.js && node scripts/test-extensions.js && node scripts/test-event-reader.js && node scripts/test-state-lock.js && node scripts/test-cost-saver.js && node scripts/test-budget-onoff.js && node scripts/test-workflow-runner.js && node scripts/test-otel-exporter.js && node scripts/test-extensions-publish.js",
     "prepublishOnly": "npm test",
     "validate-skills": "node scripts/validate-skills.js",
+    "test:surface": "node scripts/test-doc-surface-counts.js",
     "smoke": "bash scripts/smoke.sh",
     "test:runtime": "node scripts/test-runtime.js",
     "test:router": "node scripts/test-router.js",

package/skills/god-audit.md

@@ -18,6 +18,34 @@ Spawn the **god-auditor** agent in a fresh context via Task tool.
    artifact against `references/HAVE-NOTS.md`."
 3. The agent writes `.godpowers/AUDIT-REPORT.md`
 
+## Greenfield Simulation Mode
+
+When invoked by `brownfield-arc` or `bluefield-arc` with
+`mode: greenfield-simulation`, spawn god-auditor with the current project
+evidence and ask it to compare the repo or org constraints against the
+canonical Godpowers greenfield arc. The agent writes
+`.godpowers/audit/GREENFIELD-SIMULATION.md`.
+
+This mode builds nothing and rewrites no planning artifacts. It exists so
+brownfield and bluefield projects can benefit from the same PRD, design, arch,
+roadmap, stack, build, deploy, observe, harden, and launch expectations that a
+greenfield Godpowers run would have applied.
+
+## Acting On Greenfield Simulation
+
+The audit is preparation, not the action. In brownfield and bluefield arcs,
+the next step must spawn `god-greenfieldifier`.
+
+`god-greenfieldifier` writes
+`.godpowers/audit/GREENFIELDIFY-PLAN.md`, classifies every audit finding, and
+then pauses before rewriting canonical artifacts whenever the change could
+alter product scope, design direction, architecture, roadmap, stack, deploy,
+observe, launch, harden, org policy, or user commitments.
+
+After approval, the greenfieldifier updates all affected artifacts thoroughly:
+PRD, DESIGN, PRODUCT, ARCH, ROADMAP, STACK, REPO, BUILD, DEPLOY, OBSERVE,
+LAUNCH, and HARDEN. It then syncs PROGRESS.md, state.json, and SYNC-LOG.md.
+
 ## Verification
 
 After god-auditor returns:

package/skills/god-doctor.md

@@ -47,8 +47,8 @@ GODPOWERS DOCTOR
 
 Install: claude (~/.claude/)
   [OK] 105 skills installed
-  [OK] 38 agents installed
-  [OK] VERSION matches (0.15.3)
+  [OK] 39 agents installed
+  [OK] VERSION matches (0.15.17)
   [WARN] routing/god-doctor.yaml exists but skill file did not until now
 
 Project: /Users/.../my-project/.godpowers/

package/skills/god-extension-info.md

@@ -31,7 +31,7 @@ Description:
   specific checks.
 
 Engines:
-  godpowers: >=0.14.0 <2.0.0  (compatible with running v0.15.3? YES)
+  godpowers: >=0.14.0 <2.0.0  (compatible with running v0.15.17? YES)
 
 Provides:
   Agents (3):

package/skills/god-mode.md

@@ -94,6 +94,10 @@ You are receiving a /god-mode invocation. Your job is to spawn the
      direct evidence. Never infer or invent a domain from project name, package
      name, repo name, README title, or brand name. If no deployed origin is
      evidenced, pause for `STAGING_APP_URL=<deployed staging origin>`.
+   - Instruction that brownfield and bluefield greenfield simulation audits
+     must be acted on by god-greenfieldifier. The greenfieldifier writes
+     `.godpowers/audit/GREENFIELDIFY-PLAN.md`, pauses before risky canonical
+     artifact rewrites, and updates every affected artifact after approval.
 
 6. Keep the spawn payload private. Do not echo or summarize raw Task input,
    "Hard instructions", hidden orchestration rules, agent prompts, file
@@ -104,8 +108,8 @@ You are receiving a /god-mode invocation. Your job is to spawn the
 
 7. Orchestrator runs the appropriate workflow:
    - Greenfield -> full-arc
-   - Brownfield -> brownfield-arc (archaeology -> reconstruct -> debt-assess -> proceed)
-   - Bluefield -> bluefield-arc (org-context -> arc with constraints)
+   - Brownfield -> brownfield-arc (archaeology -> reconstruct -> debt-assess -> greenfield simulation audit -> greenfieldify plan and approved artifact updates -> proceed)
+   - Bluefield -> bluefield-arc (org-context -> greenfield simulation audit -> greenfieldify plan and approved artifact updates -> arc with constraints)
 
 8. Relay only the orchestrator's user-facing output to the user. If the
    platform displays raw spawn details automatically, immediately follow with a

package/skills/god-version.md

@@ -14,9 +14,9 @@ Print version and a short capability summary.
 ## Output
 
 ```
-Godpowers v0.15.3
+Godpowers v0.15.17
 Install: /Users/.../.claude/  (matches package.json)
-Surface: 105 skills, 38 agents, 13 workflows, 36 recipes
+Surface: 105 skills, 39 agents, 13 workflows, 36 recipes
 Schema: intent.v1, state.v1, events.v1, workflow.v1, routing.v1, recipe.v1
 External integrations available: impeccable, agent-browser (others lazy)
 ```

package/workflows/bluefield-arc.yaml

@@ -7,10 +7,11 @@ apiVersion: godpowers/v1
 kind: Workflow
 metadata:
   name: bluefield-arc
-  version: 1.0.0
+  version: 1.2.0
   description: |
     Bluefield: new code, existing org context. Loads org standards first,
-    then runs full-arc with all decisions constrained by org context.
+    runs a greenfield simulation audit against those constraints, then runs a
+    user-approved greenfieldification pass before the full arc.
 
 on: [/god-bluefield, /god-mode --bluefield]
 
@@ -19,9 +20,41 @@ jobs:
     tier: 0
     uses: god-org-context-loader@^1.0.0
 
+  greenfield-simulation-audit:
+    tier: 0
+    needs: org-context
+    uses: god-auditor@^1.0.0
+    with:
+      mode: greenfield-simulation
+      compare: canonical-godpowers-arc-to-org-constraints
+      output: .godpowers/audit/GREENFIELD-SIMULATION.md
+
+  greenfieldify-artifacts:
+    tier: 0
+    needs: greenfield-simulation-audit
+    uses: god-greenfieldifier@^1.0.0
+    with:
+      mode: bluefield
+      audit: .godpowers/audit/GREENFIELD-SIMULATION.md
+      plan: .godpowers/audit/GREENFIELDIFY-PLAN.md
+      approval: required-before-writing-canonical-artifacts
+      artifacts:
+        - .godpowers/prd/PRD.md
+        - .godpowers/design/DESIGN.md
+        - .godpowers/product/PRODUCT.md
+        - .godpowers/arch/ARCH.md
+        - .godpowers/roadmap/ROADMAP.md
+        - .godpowers/stack/DECISION.md
+        - .godpowers/repo/AUDIT.md
+        - .godpowers/build/STATE.md
+        - .godpowers/deploy/STATE.md
+        - .godpowers/observe/STATE.md
+        - .godpowers/launch/STATE.md
+        - .godpowers/harden/FINDINGS.md
+
   prd:
     tier: 1
-    needs: org-context
+    needs: greenfieldify-artifacts
     uses: god-pm@^1.0.0
 
   arch:

package/workflows/brownfield-arc.yaml

@@ -7,10 +7,11 @@ apiVersion: godpowers/v1
 kind: Workflow
 metadata:
   name: brownfield-arc
-  version: 1.0.0
+  version: 1.2.0
   description: |
     Brownfield: existing codebase, understand before changing. Archaeology +
-    reconstruction + debt assessment, then proceed with normal arc workflows.
+    reconstruction + debt assessment + greenfield simulation audit, then a
+    user-approved greenfieldification pass before normal arc workflows.
 
 on: [/god-brownfield, /god-mode --brownfield]
 
@@ -36,9 +37,41 @@ jobs:
     with:
       mode: full-audit-on-reconstructed
 
-  steady-state-handoff:
+  greenfield-simulation-audit:
     tier: 0
     needs: audit
+    uses: god-auditor@^1.0.0
+    with:
+      mode: greenfield-simulation
+      compare: existing-codebase-to-canonical-godpowers-arc
+      output: .godpowers/audit/GREENFIELD-SIMULATION.md
+
+  greenfieldify-artifacts:
+    tier: 0
+    needs: greenfield-simulation-audit
+    uses: god-greenfieldifier@^1.0.0
+    with:
+      mode: brownfield
+      audit: .godpowers/audit/GREENFIELD-SIMULATION.md
+      plan: .godpowers/audit/GREENFIELDIFY-PLAN.md
+      approval: required-before-writing-canonical-artifacts
+      artifacts:
+        - .godpowers/prd/PRD.md
+        - .godpowers/design/DESIGN.md
+        - .godpowers/product/PRODUCT.md
+        - .godpowers/arch/ARCH.md
+        - .godpowers/roadmap/ROADMAP.md
+        - .godpowers/stack/DECISION.md
+        - .godpowers/repo/AUDIT.md
+        - .godpowers/build/STATE.md
+        - .godpowers/deploy/STATE.md
+        - .godpowers/observe/STATE.md
+        - .godpowers/launch/STATE.md
+        - .godpowers/harden/FINDINGS.md
+
+  steady-state-handoff:
+    tier: 0
+    needs: greenfieldify-artifacts
     uses: god-orchestrator@^1.0.0
     with:
       action: brownfield-to-steady