@anhth2/spec-driven-dev-plugin 0.10.0 → 0.12.0

package/commands/debug.md

@@ -128,6 +128,8 @@ Read `.agent/project-context.yaml`. Extract and store:
 - `paths.specs_dir` → BDD specs root
 - `paths.prd_dir` → PRD documents root
 - `paths.refinement_dir` → findings/review output dir
+- `paths.qc_dir` → QC automation artifacts root (visible top-level, one subfolder per UC: `{qc_dir}/{UC-ID}/`)
+- `paths.qc_skills_dir` → where qc-* commands load QC skills from (default bundled `.agent/skills/qc`; override to the QC team's own repo/submodule so framework upgrade won't overwrite them)
 - `paths.product_definitions_dir` → product definitions root
 - `paths.domain_knowledge_dir` → domain knowledge root
 - `paths.business_dictionary` → path to business-dictionary.md
@@ -140,6 +142,8 @@ If `paths` section is absent, use these defaults:
 - `specs_dir` = `specs/bdd`
 - `prd_dir` = `specs/prd`
 - `refinement_dir` = `.agent/review`
+- `qc_dir` = `docs`
+- `qc_skills_dir` = `.agent/skills/qc`
 - `product_definitions_dir` = `specs/product-definition`
 - `domain_knowledge_dir` = `specs/domain-knowledge`
 - `business_dictionary` = `specs/domain-knowledge/business-dictionary.md`
@@ -184,6 +188,7 @@ If `services` section is present:
 - Override `paths.core_entities` → `{spec_source}/specs/domain-knowledge/core-entities.md`
 - Override `paths.bug_reports_dir` → `{spec_source}/feedback/bug-reports`
 - Override `paths.bdd_proposals_dir` → `{spec_source}/feedback/bdd-proposals`
+- Override `paths.prd_change_requests_dir` → `{spec_source}/feedback/prd-change-requests`
 
 > **Why under `spec_source`:** PRD, design-spec, domain knowledge, the **API contract (tech-docs)**, and tester feedback are all **cross-team artifacts** — they must live in the **shared spec repo** so every umbrella (FE/App/BE) reads the same source via `/sync`. Tech-docs specifically: BE authors the tech-design (API contract), commits + pushes it into the spec submodule (2-layer commit), and FE/App pull it on their next `/sync` to wire the real API in `/generate-code --phase=integration`. In single-service mode (no `spec_source`), these default under the repo root — still shared, same repo.
 
@@ -224,19 +229,41 @@ If the file does not exist → skip silently.
 
 ---
 
-## Step 3 — [CRITICAL] Load CLAUDE.md
+## Step 3 — [CRITICAL] Load CLAUDE.md (layered: root + service overlay)
 
 *This is the highest-priority context — it defines HOW to write code and documents for this project.*
 
-Read `CLAUDE.md`. Extract and store:
+CLAUDE.md is loaded in **two layers** so umbrella-wide rules and service-specific
+architecture/coding standards compose correctly. The agent always sits at the umbrella
+root, but the implementation code lives in a service submodule with its OWN stack,
+architecture, and conventions — so the service's CLAUDE.md must win for code generation.
+
+**Layer 1 — [BASE] Root CLAUDE.md (umbrella-wide).**
+Read `CLAUDE.md` at the repo root. Treat its contents as the **shared baseline** for the
+whole umbrella — git conventions, data-protection posture, cross-cutting rules, and (in
+single-service mode) the project's only architecture + coding standards.
+
+**Layer 2 — [OVERLAY] Service CLAUDE.md (umbrella mode only).**
+*Run only if `service_root` was set in Step 1.6 (i.e. a real service was routed to).*
+Read `{service_root}/CLAUDE.md`. This file defines the architecture + coding standards of
+the **actual stack being implemented** (e.g. `user-service` = java-spring, `web` = nextjs).
+Overlay it on top of Layer 1: **on any conflict, the service value WINS** for architecture,
+coding standards, and error handling. Layer-1 values that the service does not redefine
+(e.g. git conventions, banned patterns shared org-wide) remain in effect.
+
+From the **merged** result, extract and store:
 
 - **§1 Project Overview** → project name, language, framework, build/test commands, domains
-- **§2 Architecture** → layer order (e.g., Controller → Facade → Service → Repository), architectural rules
-- **§3 Coding Standards** → naming conventions (classes, methods), response wrapper type, forbidden patterns
-- **§5 Error Handling** → exception types, HTTP status code mapping, not-found exception class name
-- **§7 Git Conventions** → branch naming pattern, commit message format
+- **§2 Architecture** → layer order (e.g., Controller → Facade → Service → Repository), architectural rules — *service overlay wins*
+- **§3 Coding Standards** → naming conventions (classes, methods), response wrapper type, forbidden patterns — *service overlay wins*
+- **§5 Error Handling** → exception types, HTTP status code mapping, not-found exception class name — *service overlay wins*
+- **§7 Git Conventions** → branch naming pattern, commit message format — *root baseline unless service redefines*
 
-If `CLAUDE.md` does not exist → note it as missing and continue with project-context.yaml data only.
+**Resolution rules:**
+- If both layers exist → merge as above; record `claude_md_source = root + {service_root}`.
+- If only the service overlay exists (no root CLAUDE.md) → use the service file alone; `claude_md_source = {service_root}`.
+- If `service_root` is set but `{service_root}/CLAUDE.md` is **missing** → fall back to root CLAUDE.md and flag ⚠️ in the Step 7 recap (the service has no architecture/coding-standards definition — code generation will use umbrella defaults, which may be the wrong stack).
+- If neither exists → note CLAUDE.md as missing and continue with project-context.yaml data only.
 
 ---
 
@@ -336,7 +363,8 @@ Output exactly this block:
 [CTX LOADED]
 Stack     : {language} / {framework} / {database}
 Platform  : {active_module} ({platform_type})
-Layers    : {layer order from CLAUDE.md §2, e.g., Controller → Facade → Service → Repository}
+Layers    : {layer order from merged CLAUDE.md §2, e.g., Controller → Facade → Service → Repository}
+CLAUDE.md : {root + {service_root} | {service_root} only | root only | ⚠️ service overlay MISSING — using root | missing}
 Ticket    : {ticket_prefix}-
 Dict      : {loaded — N canonical terms, M banned terms | missing}
 Entities  : {loaded — EntityA, EntityB, EntityC | missing}
@@ -604,6 +632,13 @@ Suggest the logical next command based on workflow phase:
 | /generate-design-spec   | Designer review → Figma links confirmed → PO + Designer sign-off → `/generate-bdd {prd-file}` |
 | /generate-bdd           | `/review-context {feature-file}` to verify coverage |
 | /review-context (BDD)   | `/generate-tech-docs {UC-ID}` if APPROVED; regenerate if NEEDS_FIX |
+| /qc-analyze             | `/qc-plan {UC-ID}` (resolve 🔴 blocker gaps first) |
+| /qc-plan                | `/qc-design-test {UC-ID}`                     |
+| /qc-design-test         | `/qc-review {UC-ID}` (test-case review)       |
+| /qc-review (test-case)  | `/qc-run-test {UC-ID}` if APPROVED; fix TCs if NEEDS_FIX |
+| /qc-run-test            | `/qc-report {UC-ID}` then `/qc-review {UC-ID}` (script review) |
+| /qc-review (script)     | `/qc-report {UC-ID}` then create PR if APPROVED |
+| /qc-report              | `/validate-traces {UC-ID}` to refresh Living Docs (qc_status) |
 | /generate-tech-docs     | `/review-tech-docs {tech-design-file}`        |
 | /review-tech-docs       | `/generate-code {feature-file}` if APPROVED; fix doc if NEEDS_FIX |
 | /generate-code          | First gen → `/review-code {UC-ID}`; re-gen → `/dev-gen-test {UC-ID}` |

package/commands/define-product.md

@@ -125,6 +125,8 @@ Read `.agent/project-context.yaml`. Extract and store:
 - `paths.specs_dir` → BDD specs root
 - `paths.prd_dir` → PRD documents root
 - `paths.refinement_dir` → findings/review output dir
+- `paths.qc_dir` → QC automation artifacts root (visible top-level, one subfolder per UC: `{qc_dir}/{UC-ID}/`)
+- `paths.qc_skills_dir` → where qc-* commands load QC skills from (default bundled `.agent/skills/qc`; override to the QC team's own repo/submodule so framework upgrade won't overwrite them)
 - `paths.product_definitions_dir` → product definitions root
 - `paths.domain_knowledge_dir` → domain knowledge root
 - `paths.business_dictionary` → path to business-dictionary.md
@@ -137,6 +139,8 @@ If `paths` section is absent, use these defaults:
 - `specs_dir` = `specs/bdd`
 - `prd_dir` = `specs/prd`
 - `refinement_dir` = `.agent/review`
+- `qc_dir` = `docs`
+- `qc_skills_dir` = `.agent/skills/qc`
 - `product_definitions_dir` = `specs/product-definition`
 - `domain_knowledge_dir` = `specs/domain-knowledge`
 - `business_dictionary` = `specs/domain-knowledge/business-dictionary.md`
@@ -181,6 +185,7 @@ If `services` section is present:
 - Override `paths.core_entities` → `{spec_source}/specs/domain-knowledge/core-entities.md`
 - Override `paths.bug_reports_dir` → `{spec_source}/feedback/bug-reports`
 - Override `paths.bdd_proposals_dir` → `{spec_source}/feedback/bdd-proposals`
+- Override `paths.prd_change_requests_dir` → `{spec_source}/feedback/prd-change-requests`
 
 > **Why under `spec_source`:** PRD, design-spec, domain knowledge, the **API contract (tech-docs)**, and tester feedback are all **cross-team artifacts** — they must live in the **shared spec repo** so every umbrella (FE/App/BE) reads the same source via `/sync`. Tech-docs specifically: BE authors the tech-design (API contract), commits + pushes it into the spec submodule (2-layer commit), and FE/App pull it on their next `/sync` to wire the real API in `/generate-code --phase=integration`. In single-service mode (no `spec_source`), these default under the repo root — still shared, same repo.
 
@@ -221,19 +226,41 @@ If the file does not exist → skip silently.
 
 ---
 
-## Step 3 — [CRITICAL] Load CLAUDE.md
+## Step 3 — [CRITICAL] Load CLAUDE.md (layered: root + service overlay)
 
 *This is the highest-priority context — it defines HOW to write code and documents for this project.*
 
-Read `CLAUDE.md`. Extract and store:
+CLAUDE.md is loaded in **two layers** so umbrella-wide rules and service-specific
+architecture/coding standards compose correctly. The agent always sits at the umbrella
+root, but the implementation code lives in a service submodule with its OWN stack,
+architecture, and conventions — so the service's CLAUDE.md must win for code generation.
+
+**Layer 1 — [BASE] Root CLAUDE.md (umbrella-wide).**
+Read `CLAUDE.md` at the repo root. Treat its contents as the **shared baseline** for the
+whole umbrella — git conventions, data-protection posture, cross-cutting rules, and (in
+single-service mode) the project's only architecture + coding standards.
+
+**Layer 2 — [OVERLAY] Service CLAUDE.md (umbrella mode only).**
+*Run only if `service_root` was set in Step 1.6 (i.e. a real service was routed to).*
+Read `{service_root}/CLAUDE.md`. This file defines the architecture + coding standards of
+the **actual stack being implemented** (e.g. `user-service` = java-spring, `web` = nextjs).
+Overlay it on top of Layer 1: **on any conflict, the service value WINS** for architecture,
+coding standards, and error handling. Layer-1 values that the service does not redefine
+(e.g. git conventions, banned patterns shared org-wide) remain in effect.
+
+From the **merged** result, extract and store:
 
 - **§1 Project Overview** → project name, language, framework, build/test commands, domains
-- **§2 Architecture** → layer order (e.g., Controller → Facade → Service → Repository), architectural rules
-- **§3 Coding Standards** → naming conventions (classes, methods), response wrapper type, forbidden patterns
-- **§5 Error Handling** → exception types, HTTP status code mapping, not-found exception class name
-- **§7 Git Conventions** → branch naming pattern, commit message format
+- **§2 Architecture** → layer order (e.g., Controller → Facade → Service → Repository), architectural rules — *service overlay wins*
+- **§3 Coding Standards** → naming conventions (classes, methods), response wrapper type, forbidden patterns — *service overlay wins*
+- **§5 Error Handling** → exception types, HTTP status code mapping, not-found exception class name — *service overlay wins*
+- **§7 Git Conventions** → branch naming pattern, commit message format — *root baseline unless service redefines*
 
-If `CLAUDE.md` does not exist → note it as missing and continue with project-context.yaml data only.
+**Resolution rules:**
+- If both layers exist → merge as above; record `claude_md_source = root + {service_root}`.
+- If only the service overlay exists (no root CLAUDE.md) → use the service file alone; `claude_md_source = {service_root}`.
+- If `service_root` is set but `{service_root}/CLAUDE.md` is **missing** → fall back to root CLAUDE.md and flag ⚠️ in the Step 7 recap (the service has no architecture/coding-standards definition — code generation will use umbrella defaults, which may be the wrong stack).
+- If neither exists → note CLAUDE.md as missing and continue with project-context.yaml data only.
 
 ---
 
@@ -333,7 +360,8 @@ Output exactly this block:
 [CTX LOADED]
 Stack     : {language} / {framework} / {database}
 Platform  : {active_module} ({platform_type})
-Layers    : {layer order from CLAUDE.md §2, e.g., Controller → Facade → Service → Repository}
+Layers    : {layer order from merged CLAUDE.md §2, e.g., Controller → Facade → Service → Repository}
+CLAUDE.md : {root + {service_root} | {service_root} only | root only | ⚠️ service overlay MISSING — using root | missing}
 Ticket    : {ticket_prefix}-
 Dict      : {loaded — N canonical terms, M banned terms | missing}
 Entities  : {loaded — EntityA, EntityB, EntityC | missing}
@@ -538,6 +566,13 @@ Suggest the logical next command based on workflow phase:
 | /generate-design-spec   | Designer review → Figma links confirmed → PO + Designer sign-off → `/generate-bdd {prd-file}` |
 | /generate-bdd           | `/review-context {feature-file}` to verify coverage |
 | /review-context (BDD)   | `/generate-tech-docs {UC-ID}` if APPROVED; regenerate if NEEDS_FIX |
+| /qc-analyze             | `/qc-plan {UC-ID}` (resolve 🔴 blocker gaps first) |
+| /qc-plan                | `/qc-design-test {UC-ID}`                     |
+| /qc-design-test         | `/qc-review {UC-ID}` (test-case review)       |
+| /qc-review (test-case)  | `/qc-run-test {UC-ID}` if APPROVED; fix TCs if NEEDS_FIX |
+| /qc-run-test            | `/qc-report {UC-ID}` then `/qc-review {UC-ID}` (script review) |
+| /qc-review (script)     | `/qc-report {UC-ID}` then create PR if APPROVED |
+| /qc-report              | `/validate-traces {UC-ID}` to refresh Living Docs (qc_status) |
 | /generate-tech-docs     | `/review-tech-docs {tech-design-file}`        |
 | /review-tech-docs       | `/generate-code {feature-file}` if APPROVED; fix doc if NEEDS_FIX |
 | /generate-code          | First gen → `/review-code {UC-ID}`; re-gen → `/dev-gen-test {UC-ID}` |

package/commands/dev-gen-test.md

@@ -131,6 +131,8 @@ Read `.agent/project-context.yaml`. Extract and store:
 - `paths.specs_dir` → BDD specs root
 - `paths.prd_dir` → PRD documents root
 - `paths.refinement_dir` → findings/review output dir
+- `paths.qc_dir` → QC automation artifacts root (visible top-level, one subfolder per UC: `{qc_dir}/{UC-ID}/`)
+- `paths.qc_skills_dir` → where qc-* commands load QC skills from (default bundled `.agent/skills/qc`; override to the QC team's own repo/submodule so framework upgrade won't overwrite them)
 - `paths.product_definitions_dir` → product definitions root
 - `paths.domain_knowledge_dir` → domain knowledge root
 - `paths.business_dictionary` → path to business-dictionary.md
@@ -143,6 +145,8 @@ If `paths` section is absent, use these defaults:
 - `specs_dir` = `specs/bdd`
 - `prd_dir` = `specs/prd`
 - `refinement_dir` = `.agent/review`
+- `qc_dir` = `docs`
+- `qc_skills_dir` = `.agent/skills/qc`
 - `product_definitions_dir` = `specs/product-definition`
 - `domain_knowledge_dir` = `specs/domain-knowledge`
 - `business_dictionary` = `specs/domain-knowledge/business-dictionary.md`
@@ -187,6 +191,7 @@ If `services` section is present:
 - Override `paths.core_entities` → `{spec_source}/specs/domain-knowledge/core-entities.md`
 - Override `paths.bug_reports_dir` → `{spec_source}/feedback/bug-reports`
 - Override `paths.bdd_proposals_dir` → `{spec_source}/feedback/bdd-proposals`
+- Override `paths.prd_change_requests_dir` → `{spec_source}/feedback/prd-change-requests`
 
 > **Why under `spec_source`:** PRD, design-spec, domain knowledge, the **API contract (tech-docs)**, and tester feedback are all **cross-team artifacts** — they must live in the **shared spec repo** so every umbrella (FE/App/BE) reads the same source via `/sync`. Tech-docs specifically: BE authors the tech-design (API contract), commits + pushes it into the spec submodule (2-layer commit), and FE/App pull it on their next `/sync` to wire the real API in `/generate-code --phase=integration`. In single-service mode (no `spec_source`), these default under the repo root — still shared, same repo.
 
@@ -227,19 +232,41 @@ If the file does not exist → skip silently.
 
 ---
 
-## Step 3 — [CRITICAL] Load CLAUDE.md
+## Step 3 — [CRITICAL] Load CLAUDE.md (layered: root + service overlay)
 
 *This is the highest-priority context — it defines HOW to write code and documents for this project.*
 
-Read `CLAUDE.md`. Extract and store:
+CLAUDE.md is loaded in **two layers** so umbrella-wide rules and service-specific
+architecture/coding standards compose correctly. The agent always sits at the umbrella
+root, but the implementation code lives in a service submodule with its OWN stack,
+architecture, and conventions — so the service's CLAUDE.md must win for code generation.
+
+**Layer 1 — [BASE] Root CLAUDE.md (umbrella-wide).**
+Read `CLAUDE.md` at the repo root. Treat its contents as the **shared baseline** for the
+whole umbrella — git conventions, data-protection posture, cross-cutting rules, and (in
+single-service mode) the project's only architecture + coding standards.
+
+**Layer 2 — [OVERLAY] Service CLAUDE.md (umbrella mode only).**
+*Run only if `service_root` was set in Step 1.6 (i.e. a real service was routed to).*
+Read `{service_root}/CLAUDE.md`. This file defines the architecture + coding standards of
+the **actual stack being implemented** (e.g. `user-service` = java-spring, `web` = nextjs).
+Overlay it on top of Layer 1: **on any conflict, the service value WINS** for architecture,
+coding standards, and error handling. Layer-1 values that the service does not redefine
+(e.g. git conventions, banned patterns shared org-wide) remain in effect.
+
+From the **merged** result, extract and store:
 
 - **§1 Project Overview** → project name, language, framework, build/test commands, domains
-- **§2 Architecture** → layer order (e.g., Controller → Facade → Service → Repository), architectural rules
-- **§3 Coding Standards** → naming conventions (classes, methods), response wrapper type, forbidden patterns
-- **§5 Error Handling** → exception types, HTTP status code mapping, not-found exception class name
-- **§7 Git Conventions** → branch naming pattern, commit message format
+- **§2 Architecture** → layer order (e.g., Controller → Facade → Service → Repository), architectural rules — *service overlay wins*
+- **§3 Coding Standards** → naming conventions (classes, methods), response wrapper type, forbidden patterns — *service overlay wins*
+- **§5 Error Handling** → exception types, HTTP status code mapping, not-found exception class name — *service overlay wins*
+- **§7 Git Conventions** → branch naming pattern, commit message format — *root baseline unless service redefines*
 
-If `CLAUDE.md` does not exist → note it as missing and continue with project-context.yaml data only.
+**Resolution rules:**
+- If both layers exist → merge as above; record `claude_md_source = root + {service_root}`.
+- If only the service overlay exists (no root CLAUDE.md) → use the service file alone; `claude_md_source = {service_root}`.
+- If `service_root` is set but `{service_root}/CLAUDE.md` is **missing** → fall back to root CLAUDE.md and flag ⚠️ in the Step 7 recap (the service has no architecture/coding-standards definition — code generation will use umbrella defaults, which may be the wrong stack).
+- If neither exists → note CLAUDE.md as missing and continue with project-context.yaml data only.
 
 ---
 
@@ -339,7 +366,8 @@ Output exactly this block:
 [CTX LOADED]
 Stack     : {language} / {framework} / {database}
 Platform  : {active_module} ({platform_type})
-Layers    : {layer order from CLAUDE.md §2, e.g., Controller → Facade → Service → Repository}
+Layers    : {layer order from merged CLAUDE.md §2, e.g., Controller → Facade → Service → Repository}
+CLAUDE.md : {root + {service_root} | {service_root} only | root only | ⚠️ service overlay MISSING — using root | missing}
 Ticket    : {ticket_prefix}-
 Dict      : {loaded — N canonical terms, M banned terms | missing}
 Entities  : {loaded — EntityA, EntityB, EntityC | missing}
@@ -819,7 +847,7 @@ After generating all test files, update `{paths.trace_dir}/{UC-ID}.tsv` — for
 | `dev_selftest` | `not_run` (tests now exist but have not been executed — `/dev-run-test` sets pass/fail) |
 | `last_updated` | today `YYYY-MM-DD` |
 
-Leave all other columns unchanged (including `dev_selftest_at`, which `/dev-run-test` owns).
+Leave all other columns unchanged (including `dev_selftest_at`, which `/dev-run-test` owns, and `qc_status`/`qc_run_at`, which `/qc-run-test` owns).
 
 ---
 
@@ -884,6 +912,13 @@ Suggest the logical next command based on workflow phase:
 | /generate-design-spec   | Designer review → Figma links confirmed → PO + Designer sign-off → `/generate-bdd {prd-file}` |
 | /generate-bdd           | `/review-context {feature-file}` to verify coverage |
 | /review-context (BDD)   | `/generate-tech-docs {UC-ID}` if APPROVED; regenerate if NEEDS_FIX |
+| /qc-analyze             | `/qc-plan {UC-ID}` (resolve 🔴 blocker gaps first) |
+| /qc-plan                | `/qc-design-test {UC-ID}`                     |
+| /qc-design-test         | `/qc-review {UC-ID}` (test-case review)       |
+| /qc-review (test-case)  | `/qc-run-test {UC-ID}` if APPROVED; fix TCs if NEEDS_FIX |
+| /qc-run-test            | `/qc-report {UC-ID}` then `/qc-review {UC-ID}` (script review) |
+| /qc-review (script)     | `/qc-report {UC-ID}` then create PR if APPROVED |
+| /qc-report              | `/validate-traces {UC-ID}` to refresh Living Docs (qc_status) |
 | /generate-tech-docs     | `/review-tech-docs {tech-design-file}`        |
 | /review-tech-docs       | `/generate-code {feature-file}` if APPROVED; fix doc if NEEDS_FIX |
 | /generate-code          | First gen → `/review-code {UC-ID}`; re-gen → `/dev-gen-test {UC-ID}` |

package/commands/dev-gen-test.tmpl

@@ -466,7 +466,7 @@ After generating all test files, update `{paths.trace_dir}/{UC-ID}.tsv` — for
 | `dev_selftest` | `not_run` (tests now exist but have not been executed — `/dev-run-test` sets pass/fail) |
 | `last_updated` | today `YYYY-MM-DD` |
 
-Leave all other columns unchanged (including `dev_selftest_at`, which `/dev-run-test` owns).
+Leave all other columns unchanged (including `dev_selftest_at`, which `/dev-run-test` owns, and `qc_status`/`qc_run_at`, which `/qc-run-test` owns).
 
 ---
 

package/commands/dev-run-test.md

@@ -131,6 +131,8 @@ Read `.agent/project-context.yaml`. Extract and store:
 - `paths.specs_dir` → BDD specs root
 - `paths.prd_dir` → PRD documents root
 - `paths.refinement_dir` → findings/review output dir
+- `paths.qc_dir` → QC automation artifacts root (visible top-level, one subfolder per UC: `{qc_dir}/{UC-ID}/`)
+- `paths.qc_skills_dir` → where qc-* commands load QC skills from (default bundled `.agent/skills/qc`; override to the QC team's own repo/submodule so framework upgrade won't overwrite them)
 - `paths.product_definitions_dir` → product definitions root
 - `paths.domain_knowledge_dir` → domain knowledge root
 - `paths.business_dictionary` → path to business-dictionary.md
@@ -143,6 +145,8 @@ If `paths` section is absent, use these defaults:
 - `specs_dir` = `specs/bdd`
 - `prd_dir` = `specs/prd`
 - `refinement_dir` = `.agent/review`
+- `qc_dir` = `docs`
+- `qc_skills_dir` = `.agent/skills/qc`
 - `product_definitions_dir` = `specs/product-definition`
 - `domain_knowledge_dir` = `specs/domain-knowledge`
 - `business_dictionary` = `specs/domain-knowledge/business-dictionary.md`
@@ -187,6 +191,7 @@ If `services` section is present:
 - Override `paths.core_entities` → `{spec_source}/specs/domain-knowledge/core-entities.md`
 - Override `paths.bug_reports_dir` → `{spec_source}/feedback/bug-reports`
 - Override `paths.bdd_proposals_dir` → `{spec_source}/feedback/bdd-proposals`
+- Override `paths.prd_change_requests_dir` → `{spec_source}/feedback/prd-change-requests`
 
 > **Why under `spec_source`:** PRD, design-spec, domain knowledge, the **API contract (tech-docs)**, and tester feedback are all **cross-team artifacts** — they must live in the **shared spec repo** so every umbrella (FE/App/BE) reads the same source via `/sync`. Tech-docs specifically: BE authors the tech-design (API contract), commits + pushes it into the spec submodule (2-layer commit), and FE/App pull it on their next `/sync` to wire the real API in `/generate-code --phase=integration`. In single-service mode (no `spec_source`), these default under the repo root — still shared, same repo.
 
@@ -227,19 +232,41 @@ If the file does not exist → skip silently.
 
 ---
 
-## Step 3 — [CRITICAL] Load CLAUDE.md
+## Step 3 — [CRITICAL] Load CLAUDE.md (layered: root + service overlay)
 
 *This is the highest-priority context — it defines HOW to write code and documents for this project.*
 
-Read `CLAUDE.md`. Extract and store:
+CLAUDE.md is loaded in **two layers** so umbrella-wide rules and service-specific
+architecture/coding standards compose correctly. The agent always sits at the umbrella
+root, but the implementation code lives in a service submodule with its OWN stack,
+architecture, and conventions — so the service's CLAUDE.md must win for code generation.
+
+**Layer 1 — [BASE] Root CLAUDE.md (umbrella-wide).**
+Read `CLAUDE.md` at the repo root. Treat its contents as the **shared baseline** for the
+whole umbrella — git conventions, data-protection posture, cross-cutting rules, and (in
+single-service mode) the project's only architecture + coding standards.
+
+**Layer 2 — [OVERLAY] Service CLAUDE.md (umbrella mode only).**
+*Run only if `service_root` was set in Step 1.6 (i.e. a real service was routed to).*
+Read `{service_root}/CLAUDE.md`. This file defines the architecture + coding standards of
+the **actual stack being implemented** (e.g. `user-service` = java-spring, `web` = nextjs).
+Overlay it on top of Layer 1: **on any conflict, the service value WINS** for architecture,
+coding standards, and error handling. Layer-1 values that the service does not redefine
+(e.g. git conventions, banned patterns shared org-wide) remain in effect.
+
+From the **merged** result, extract and store:
 
 - **§1 Project Overview** → project name, language, framework, build/test commands, domains
-- **§2 Architecture** → layer order (e.g., Controller → Facade → Service → Repository), architectural rules
-- **§3 Coding Standards** → naming conventions (classes, methods), response wrapper type, forbidden patterns
-- **§5 Error Handling** → exception types, HTTP status code mapping, not-found exception class name
-- **§7 Git Conventions** → branch naming pattern, commit message format
+- **§2 Architecture** → layer order (e.g., Controller → Facade → Service → Repository), architectural rules — *service overlay wins*
+- **§3 Coding Standards** → naming conventions (classes, methods), response wrapper type, forbidden patterns — *service overlay wins*
+- **§5 Error Handling** → exception types, HTTP status code mapping, not-found exception class name — *service overlay wins*
+- **§7 Git Conventions** → branch naming pattern, commit message format — *root baseline unless service redefines*
 
-If `CLAUDE.md` does not exist → note it as missing and continue with project-context.yaml data only.
+**Resolution rules:**
+- If both layers exist → merge as above; record `claude_md_source = root + {service_root}`.
+- If only the service overlay exists (no root CLAUDE.md) → use the service file alone; `claude_md_source = {service_root}`.
+- If `service_root` is set but `{service_root}/CLAUDE.md` is **missing** → fall back to root CLAUDE.md and flag ⚠️ in the Step 7 recap (the service has no architecture/coding-standards definition — code generation will use umbrella defaults, which may be the wrong stack).
+- If neither exists → note CLAUDE.md as missing and continue with project-context.yaml data only.
 
 ---
 
@@ -339,7 +366,8 @@ Output exactly this block:
 [CTX LOADED]
 Stack     : {language} / {framework} / {database}
 Platform  : {active_module} ({platform_type})
-Layers    : {layer order from CLAUDE.md §2, e.g., Controller → Facade → Service → Repository}
+Layers    : {layer order from merged CLAUDE.md §2, e.g., Controller → Facade → Service → Repository}
+CLAUDE.md : {root + {service_root} | {service_root} only | root only | ⚠️ service overlay MISSING — using root | missing}
 Ticket    : {ticket_prefix}-
 Dict      : {loaded — N canonical terms, M banned terms | missing}
 Entities  : {loaded — EntityA, EntityB, EntityC | missing}
@@ -543,8 +571,11 @@ test's `@trace.verifies={UC-ID}-SC{N}` tag):
 | `dev_selftest` | `pass` if all tests for this SC passed · `fail` if any failed · `not_run` if its tests were skipped/absent |
 | `dev_selftest_at` | today `YYYY-MM-DD` |
 
-Leave all other columns unchanged. `dev_selftest`/`dev_selftest_at` are orthogonal to `status`
-(OK/GAP/DRIFT/UNTRACKED): `status` tracks *coverage*, `dev_selftest` tracks the latest *run result*.
+Leave all other columns unchanged — in particular **never** touch `qc_status`/`qc_run_at`
+(the official QC automation result, owned by `/qc-run-test`). `dev_selftest` (dev smoke)
+and `qc_status` (official QC) are separate
+signals. `dev_selftest`/`dev_selftest_at` are also orthogonal to `status`
+(OK/GAP/DRIFT/UNTRACKED): `status` tracks *coverage*, `dev_selftest` tracks the dev's latest *run result*.
 
 ## Refresh Panel Mirror
 # Refresh Living Docs panel mirror *(local, umbrella mode)*
@@ -605,6 +636,13 @@ Suggest the logical next command based on workflow phase:
 | /generate-design-spec   | Designer review → Figma links confirmed → PO + Designer sign-off → `/generate-bdd {prd-file}` |
 | /generate-bdd           | `/review-context {feature-file}` to verify coverage |
 | /review-context (BDD)   | `/generate-tech-docs {UC-ID}` if APPROVED; regenerate if NEEDS_FIX |
+| /qc-analyze             | `/qc-plan {UC-ID}` (resolve 🔴 blocker gaps first) |
+| /qc-plan                | `/qc-design-test {UC-ID}`                     |
+| /qc-design-test         | `/qc-review {UC-ID}` (test-case review)       |
+| /qc-review (test-case)  | `/qc-run-test {UC-ID}` if APPROVED; fix TCs if NEEDS_FIX |
+| /qc-run-test            | `/qc-report {UC-ID}` then `/qc-review {UC-ID}` (script review) |
+| /qc-review (script)     | `/qc-report {UC-ID}` then create PR if APPROVED |
+| /qc-report              | `/validate-traces {UC-ID}` to refresh Living Docs (qc_status) |
 | /generate-tech-docs     | `/review-tech-docs {tech-design-file}`        |
 | /review-tech-docs       | `/generate-code {feature-file}` if APPROVED; fix doc if NEEDS_FIX |
 | /generate-code          | First gen → `/review-code {UC-ID}`; re-gen → `/dev-gen-test {UC-ID}` |

package/commands/dev-run-test.tmpl

@@ -190,8 +190,11 @@ test's `@trace.verifies={UC-ID}-SC{N}` tag):
 | `dev_selftest` | `pass` if all tests for this SC passed · `fail` if any failed · `not_run` if its tests were skipped/absent |
 | `dev_selftest_at` | today `YYYY-MM-DD` |
 
-Leave all other columns unchanged. `dev_selftest`/`dev_selftest_at` are orthogonal to `status`
-(OK/GAP/DRIFT/UNTRACKED): `status` tracks *coverage*, `dev_selftest` tracks the latest *run result*.
+Leave all other columns unchanged — in particular **never** touch `qc_status`/`qc_run_at`
+(the official QC automation result, owned by `/qc-run-test`). `dev_selftest` (dev smoke)
+and `qc_status` (official QC) are separate
+signals. `dev_selftest`/`dev_selftest_at` are also orthogonal to `status`
+(OK/GAP/DRIFT/UNTRACKED): `status` tracks *coverage*, `dev_selftest` tracks the dev's latest *run result*.
 
 ## Refresh Panel Mirror
 {{include:steps/trace-mirror.md}}

package/commands/dev-smoke-test.md

@@ -127,6 +127,8 @@ Read `.agent/project-context.yaml`. Extract and store:
 - `paths.specs_dir` → BDD specs root
 - `paths.prd_dir` → PRD documents root
 - `paths.refinement_dir` → findings/review output dir
+- `paths.qc_dir` → QC automation artifacts root (visible top-level, one subfolder per UC: `{qc_dir}/{UC-ID}/`)
+- `paths.qc_skills_dir` → where qc-* commands load QC skills from (default bundled `.agent/skills/qc`; override to the QC team's own repo/submodule so framework upgrade won't overwrite them)
 - `paths.product_definitions_dir` → product definitions root
 - `paths.domain_knowledge_dir` → domain knowledge root
 - `paths.business_dictionary` → path to business-dictionary.md
@@ -139,6 +141,8 @@ If `paths` section is absent, use these defaults:
 - `specs_dir` = `specs/bdd`
 - `prd_dir` = `specs/prd`
 - `refinement_dir` = `.agent/review`
+- `qc_dir` = `docs`
+- `qc_skills_dir` = `.agent/skills/qc`
 - `product_definitions_dir` = `specs/product-definition`
 - `domain_knowledge_dir` = `specs/domain-knowledge`
 - `business_dictionary` = `specs/domain-knowledge/business-dictionary.md`
@@ -183,6 +187,7 @@ If `services` section is present:
 - Override `paths.core_entities` → `{spec_source}/specs/domain-knowledge/core-entities.md`
 - Override `paths.bug_reports_dir` → `{spec_source}/feedback/bug-reports`
 - Override `paths.bdd_proposals_dir` → `{spec_source}/feedback/bdd-proposals`
+- Override `paths.prd_change_requests_dir` → `{spec_source}/feedback/prd-change-requests`
 
 > **Why under `spec_source`:** PRD, design-spec, domain knowledge, the **API contract (tech-docs)**, and tester feedback are all **cross-team artifacts** — they must live in the **shared spec repo** so every umbrella (FE/App/BE) reads the same source via `/sync`. Tech-docs specifically: BE authors the tech-design (API contract), commits + pushes it into the spec submodule (2-layer commit), and FE/App pull it on their next `/sync` to wire the real API in `/generate-code --phase=integration`. In single-service mode (no `spec_source`), these default under the repo root — still shared, same repo.
 
@@ -223,19 +228,41 @@ If the file does not exist → skip silently.
 
 ---
 
-## Step 3 — [CRITICAL] Load CLAUDE.md
+## Step 3 — [CRITICAL] Load CLAUDE.md (layered: root + service overlay)
 
 *This is the highest-priority context — it defines HOW to write code and documents for this project.*
 
-Read `CLAUDE.md`. Extract and store:
+CLAUDE.md is loaded in **two layers** so umbrella-wide rules and service-specific
+architecture/coding standards compose correctly. The agent always sits at the umbrella
+root, but the implementation code lives in a service submodule with its OWN stack,
+architecture, and conventions — so the service's CLAUDE.md must win for code generation.
+
+**Layer 1 — [BASE] Root CLAUDE.md (umbrella-wide).**
+Read `CLAUDE.md` at the repo root. Treat its contents as the **shared baseline** for the
+whole umbrella — git conventions, data-protection posture, cross-cutting rules, and (in
+single-service mode) the project's only architecture + coding standards.
+
+**Layer 2 — [OVERLAY] Service CLAUDE.md (umbrella mode only).**
+*Run only if `service_root` was set in Step 1.6 (i.e. a real service was routed to).*
+Read `{service_root}/CLAUDE.md`. This file defines the architecture + coding standards of
+the **actual stack being implemented** (e.g. `user-service` = java-spring, `web` = nextjs).
+Overlay it on top of Layer 1: **on any conflict, the service value WINS** for architecture,
+coding standards, and error handling. Layer-1 values that the service does not redefine
+(e.g. git conventions, banned patterns shared org-wide) remain in effect.
+
+From the **merged** result, extract and store:
 
 - **§1 Project Overview** → project name, language, framework, build/test commands, domains
-- **§2 Architecture** → layer order (e.g., Controller → Facade → Service → Repository), architectural rules
-- **§3 Coding Standards** → naming conventions (classes, methods), response wrapper type, forbidden patterns
-- **§5 Error Handling** → exception types, HTTP status code mapping, not-found exception class name
-- **§7 Git Conventions** → branch naming pattern, commit message format
+- **§2 Architecture** → layer order (e.g., Controller → Facade → Service → Repository), architectural rules — *service overlay wins*
+- **§3 Coding Standards** → naming conventions (classes, methods), response wrapper type, forbidden patterns — *service overlay wins*
+- **§5 Error Handling** → exception types, HTTP status code mapping, not-found exception class name — *service overlay wins*
+- **§7 Git Conventions** → branch naming pattern, commit message format — *root baseline unless service redefines*
 
-If `CLAUDE.md` does not exist → note it as missing and continue with project-context.yaml data only.
+**Resolution rules:**
+- If both layers exist → merge as above; record `claude_md_source = root + {service_root}`.
+- If only the service overlay exists (no root CLAUDE.md) → use the service file alone; `claude_md_source = {service_root}`.
+- If `service_root` is set but `{service_root}/CLAUDE.md` is **missing** → fall back to root CLAUDE.md and flag ⚠️ in the Step 7 recap (the service has no architecture/coding-standards definition — code generation will use umbrella defaults, which may be the wrong stack).
+- If neither exists → note CLAUDE.md as missing and continue with project-context.yaml data only.
 
 ---
 
@@ -335,7 +362,8 @@ Output exactly this block:
 [CTX LOADED]
 Stack     : {language} / {framework} / {database}
 Platform  : {active_module} ({platform_type})
-Layers    : {layer order from CLAUDE.md §2, e.g., Controller → Facade → Service → Repository}
+Layers    : {layer order from merged CLAUDE.md §2, e.g., Controller → Facade → Service → Repository}
+CLAUDE.md : {root + {service_root} | {service_root} only | root only | ⚠️ service overlay MISSING — using root | missing}
 Ticket    : {ticket_prefix}-
 Dict      : {loaded — N canonical terms, M banned terms | missing}
 Entities  : {loaded — EntityA, EntityB, EntityC | missing}
@@ -590,6 +618,13 @@ Suggest the logical next command based on workflow phase:
 | /generate-design-spec   | Designer review → Figma links confirmed → PO + Designer sign-off → `/generate-bdd {prd-file}` |
 | /generate-bdd           | `/review-context {feature-file}` to verify coverage |
 | /review-context (BDD)   | `/generate-tech-docs {UC-ID}` if APPROVED; regenerate if NEEDS_FIX |
+| /qc-analyze             | `/qc-plan {UC-ID}` (resolve 🔴 blocker gaps first) |
+| /qc-plan                | `/qc-design-test {UC-ID}`                     |
+| /qc-design-test         | `/qc-review {UC-ID}` (test-case review)       |
+| /qc-review (test-case)  | `/qc-run-test {UC-ID}` if APPROVED; fix TCs if NEEDS_FIX |
+| /qc-run-test            | `/qc-report {UC-ID}` then `/qc-review {UC-ID}` (script review) |
+| /qc-review (script)     | `/qc-report {UC-ID}` then create PR if APPROVED |
+| /qc-report              | `/validate-traces {UC-ID}` to refresh Living Docs (qc_status) |
 | /generate-tech-docs     | `/review-tech-docs {tech-design-file}`        |
 | /review-tech-docs       | `/generate-code {feature-file}` if APPROVED; fix doc if NEEDS_FIX |
 | /generate-code          | First gen → `/review-code {UC-ID}`; re-gen → `/dev-gen-test {UC-ID}` |