krwhynot · krwhynot · Sep 2, 2026 · Sep 2, 2026 · Sep 2, 2026
diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json
@@ -7,7 +7,7 @@
   "plugins": [
     {
       "name": "deepgrade",
-      "description": "9-phase planning with an adversarial verifier-first audit gate, plan-linked troubleshooting, and documentation generation.",
+      "description": "Six-stage AI-Native SDLC planning (intent.md, spec.md, plan.md, review.md) with an adversarial verifier-first design gate, plan-linked troubleshooting, and documentation generation.",
       "category": "development",
       "tags": [
         "planning",

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,6 +2,32 @@
 
 ## Unreleased
 
+### BREAKING
+
+- **`/deepgrade:plan` runs Anthropic's AI-Native SDLC playbook.** Nine phases
+  become six stages, Plan, Design, Build, Test, Deploy, Maintain, each
+  committing one artifact the next stage reads: `intent.md`, `spec.md` (plus
+  `audit.md` from the verifier gate), `plan.md` (the build plan: files, order,
+  risks, proof, verification), `test-plan.md`, `review.md`, and a new
+  `intent.md` proposed from incidents. All artifacts live in the plan folder;
+  `docs/specs/{name}.md`, `brainstorm.md`, `approach.md`, and `confidence.md`
+  are no longer written (the confidence brief is spec.md's Evidence section).
+  `status.json` moves to schema 2 with the six stage keys and per-stage
+  `started`/`completed` timestamps; a schema-1 plan is migrated on resume by a
+  fixed name map and its old artifacts are read where they are. Anything that
+  parsed the old phase names or artifact names breaks.
+- **The audit score is gone.** The design gate keeps the canary, the evidence
+  validator, the criterion registry, and the rubric-free pass; the 8-dimension
+  1-5 score, `/40` totals, bands, `score_history`, and the score clause in the
+  review waiver are removed. plan-auditor returns criterion verdicts only.
+- New: `intent {name}` runs Stage 1 only and stops, so a non-engineer can
+  capture intent for a product owner to accept. Deploy adds a diff-versus-plan
+  check (unplanned and untouched files, intent constraints against the code)
+  that must be acknowledged in plan.md before release, and the skill never runs
+  a release command: it prepares and asks a named human. Troubleshoot proposes
+  a Draft intent for SEV1/SEV2 or recurring incidents linked to a plan.
+  plan-status prints intent-to-spec, spec-to-plan, plan-to-release elapsed.
+
 ### Changed
 - **`/deepgrade:plan` is a skill.** The 1,710-line command is now
   `skills/plan/SKILL.md` (a 319-line router) plus one file per phase under

diff --git a/README.md b/README.md
@@ -9,7 +9,7 @@ marketplace, one release, install any subset:
 
 | Plugin | What it does | Who installs it |
 | ------ | ------------ | --------------- |
-| [`deepgrade`](plugins/deepgrade/) | 9-phase planning with an adversarial verifier-first audit gate, plan-linked troubleshooting, documentation generation | Developers living in `docs/plans/` daily |
+| [`deepgrade`](plugins/deepgrade/) | Six-stage AI-Native SDLC planning (intent, spec, plan, test, release, maintain) with an adversarial verifier-first design gate, plan-linked troubleshooting, documentation generation | Developers living in `docs/plans/` daily |
 | [`deepgrade-readiness`](plugins/deepgrade-readiness/) | AI-readiness scan: 52 checks, 9 categories, composite letter grade A+ to F, generated scaffolding | Consultants and leads grading many repos |
 | [`deepgrade-audit`](plugins/deepgrade-audit/) | Severity-graded codebase audits, security scans, delta/KPI tracking, characterization tests, generated CI gates | Engineering managers doing due diligence |
 | [`deepgrade-guard`](plugins/deepgrade-guard/) | Always-on safety hooks: force-push and DB-deploy blocking, migration protection, change/test tracking, session summaries | Everyone — recommended universal co-install |

diff --git a/interop.md b/interop.md
@@ -27,9 +27,9 @@ Format rules (the sweep depends on them):
 | docs/audit/readability/readability-report.md | plugins/deepgrade-readiness/agents/readiness-report-generator.md | plugins/deepgrade-audit/commands/codebase-audit.md, plugins/deepgrade-audit/agents/delta-scanner.md, plugins/deepgrade/skills/documentation/references/spec-template.md |
 | docs/audit/deepgrade-report.md | plugins/deepgrade-audit/agents/deepgrade-report-generator.md | plugins/deepgrade/scripts/dg-session-start.js |
 | docs/audit/risk-assessment.md | plugins/deepgrade-audit/agents/risk-assessor.md | plugins/deepgrade/agents/plan-scaffolder.md, plugins/deepgrade/agents/plan-auditor.md, plugins/deepgrade/commands/quick-plan.md, plugins/deepgrade/skills/documentation/SKILL.md, plugins/deepgrade/skills/documentation/references/spec-template.md |
-| docs/audit/dependency-map.md | plugins/deepgrade-audit/agents/dependency-mapper.md | plugins/deepgrade/agents/plan-scaffolder.md, plugins/deepgrade/agents/plan-auditor.md, plugins/deepgrade/commands/quick-plan.md, plugins/deepgrade/skills/plan/phases/phase-7-impact-review.md, plugins/deepgrade/skills/documentation/references/spec-template.md |
+| docs/audit/dependency-map.md | plugins/deepgrade-audit/agents/dependency-mapper.md | plugins/deepgrade/agents/plan-scaffolder.md, plugins/deepgrade/agents/plan-auditor.md, plugins/deepgrade/commands/quick-plan.md, plugins/deepgrade/skills/plan/stages/stage-3-build.md, plugins/deepgrade/skills/documentation/references/spec-template.md |
 | docs/audit/feature-inventory.md | plugins/deepgrade-audit/agents/feature-scanner.md | plugins/deepgrade/commands/quick-plan.md, plugins/deepgrade/skills/documentation/SKILL.md, plugins/deepgrade/skills/documentation/references/spec-template.md |
-| docs/audit/integration-scan.md | plugins/deepgrade-audit/agents/integration-scanner.md | plugins/deepgrade/agents/plan-auditor.md, plugins/deepgrade/commands/quick-plan.md, plugins/deepgrade/skills/plan/phases/phase-7-impact-review.md, plugins/deepgrade/skills/documentation/references/spec-template.md |
+| docs/audit/integration-scan.md | plugins/deepgrade-audit/agents/integration-scanner.md | plugins/deepgrade/agents/plan-auditor.md, plugins/deepgrade/commands/quick-plan.md, plugins/deepgrade/skills/plan/stages/stage-3-build.md, plugins/deepgrade/skills/documentation/references/spec-template.md |
 | docs/audit/audit-progress.md | plugins/deepgrade-audit/commands/codebase-audit.md | plugins/deepgrade-readiness/agents/baseline-scanner.md |
 
 ## The readability-score.json schema

diff --git a/plugins/deepgrade/.claude-plugin/plugin.json b/plugins/deepgrade/.claude-plugin/plugin.json
@@ -1,7 +1,7 @@
 {
   "name": "deepgrade",
   "version": "7.1.0",
-  "description": "DeepGrade planning: 9-phase idea-to-handoff planning with an adversarial verifier-first audit gate, plan-linked troubleshooting, and documentation generation. Stack-agnostic.",
+  "description": "DeepGrade planning: six-stage AI-Native SDLC planning (intent, spec, plan, test, release, maintain) with an adversarial verifier-first design gate, plan-linked troubleshooting, and documentation generation. Stack-agnostic.",
   "author": {
     "name": "Kyle Whynot",
     "url": "https://github.com/krwhynot"

diff --git a/plugins/deepgrade/GUIDE.md b/plugins/deepgrade/GUIDE.md
@@ -12,8 +12,9 @@
 
 > A reference for the deepgrade planning plugin: structured planning with an adversarial audit gate, plan-linked troubleshooting, and documentation generation.
 
-DeepGrade's planning core walks an idea through nine phases from brainstorm to
-handoff, with an adversarial audit gate in the middle: a fresh, isolated
+DeepGrade's planning core walks an idea through the six stages of Anthropic's
+AI-Native SDLC playbook, Plan, Design, Build, Test, Deploy, Maintain, each
+committing one artifact the next stage reads, with an adversarial design gate: a fresh, isolated
 plan-auditor judges every plan against falsifiable criteria, its evidence is
 re-validated byte-for-byte by `scripts/dg-evidence-validate.js`, and a seeded
 canary defect (`scripts/dg-canary.js`) proves the audit can actually see
@@ -45,9 +46,9 @@ methodology reference lives in the monorepo's
 ---
 
 ### `/deepgrade:plan`
-**What it does:** Walks you through a 9-phase guided planning workflow: Brainstorm, Research, Pre-Plan, Plan, Audit, Build, Impact Review, Test, and Handoff.
+**What it does:** Walks you through the six-stage playbook: Plan (intent.md), Design (spec.md plus the verifier gate), Build (plan.md, code, impact review), Test, Deploy (review.md, release authorization), Maintain (incidents become new intents). `intent {name}` captures intent only and stops.
 **When to use it:** For any significant initiative -- migrations, new features, refactoring projects. This is the full workflow.
-**What it produces:** `docs/plans/YYYY-MM-DD-{name}/` folder with manifest, status, brainstorm, approach, research, audit, specs, and more.
+**What it produces:** `docs/plans/YYYY-MM-DD-{name}/` with manifest, status, intent.md, research, spec.md, audit.md, plan.md, impact-review.md, test-plan.md, review.md.
 **Example:**
 ```
 /deepgrade:plan worldpay-canada
@@ -58,7 +59,7 @@ methodology reference lives in the monorepo's
 
 ### `/deepgrade:quick-plan`
 **What it does:** One-shot plan generation from a vague objective. Analyzes the codebase and produces a phased technical plan targeting 32+/40 on audit dimensions.
-**When to use it:** For smaller changes where the full 9-phase workflow is overkill.
+**When to use it:** For smaller changes where the full six-stage workflow is overkill.
 **What it produces:** `docs/specs/{plan-name}.md`
 **Example:**
 ```
@@ -165,7 +166,7 @@ methodology reference lives in the monorepo's
 
 Skills are persistent knowledge that loads automatically when relevant — reference books the plugin carries in its back pocket.
 
-**plan** -- The `/deepgrade:plan` workflow itself. `SKILL.md` is a router (identity, lifecycle, workspace layout, Step 0 intent detection) and each of the nine phases lives in its own file under `phases/`, read when the phase is entered. Split this way so the later phases survive context compaction in long planning sessions instead of being silently dropped with the rest of a 1,700-line command.
+**plan** -- The `/deepgrade:plan` workflow itself. `SKILL.md` is a router (identity, lifecycle, workspace layout, Step 0 intent detection and schema migration) and each of the six stages lives in its own file under `stages/`, with artifact templates under `templates/`, read when the phase is entered. Split this way so the later phases survive context compaction in long planning sessions instead of being silently dropped with the rest of a 1,700-line command.
 
 **troubleshoot** -- The `/deepgrade:troubleshoot` workflow: a router holding identity, timeline logging, plan detection, and Step 0 knowledge-base lookup, with the incident pre-flow, the four phases, multi-agent mode, and the knowledge-base write-back in one file each under `phases/`, read on entry.
 

diff --git a/plugins/deepgrade/README.md b/plugins/deepgrade/README.md
@@ -1,7 +1,8 @@
 # DeepGrade (planning core)
 
-DeepGrade's planning plugin: a 9-phase idea-to-handoff planning workflow with an
-adversarial, verifier-first audit gate, plan-linked troubleshooting, and
+DeepGrade's planning plugin: a six-stage idea-to-release workflow on Anthropic's
+AI-Native SDLC playbook (intent.md, spec.md, plan.md, review.md) with an
+adversarial, verifier-first design gate, plan-linked troubleshooting, and
 documentation generation. Stack-agnostic. Works on any codebase.
 
 This is one of four DeepGrade plugins in the
@@ -30,7 +31,7 @@ Verify inside a Claude Code session:
 
 | Command | Description |
 | ------- | ----------- |
-| `/deepgrade:plan` | 9-phase structured planning workflow |
+| `/deepgrade:plan` | Six-stage playbook workflow: Plan, Design, Build, Test, Deploy, Maintain |
 | `/deepgrade:quick-plan` | Lightweight plan for small changes |
 | `/deepgrade:plan-status` | Check plan progress and phase status |
 | `/deepgrade:plan-export` | Export a plan as a portable package |