@torus-engineering/tas-kit 1.13.0 → 2.1.0

package/.tas/commands/tas-apitest.md

@@ -1,143 +1,147 @@
-# /tas-apitest $ARGUMENTS
-
-Role: SE - Software Engineer
-Generate .NET xUnit automation test project for REST API from API Test Spec file (Markdown).
-
-## Always / Ask / Never
-
-| | Action |
-|---|---|
-| **Always** | Read entire API Test Spec file before generating any test |
-| **Always** | Organize tests by API version — each version separate folder |
-| **Always** | Append-only: don't modify files in existing old version folder |
-| **Always** | URL and credentials in `appsettings.json` — not hardcoded in code |
-| **Always** | XML doc comment on each test method |
-| **Ask** | When test spec unclear about expected response schema |
-| **Never** | Modify or delete old version test files |
-| **Never** | Hardcode base URL, API key, credentials in test code |
-| **Never** | Skip error path — each endpoint needs ≥1 happy path + ≥1 error path |
-
-## Actions
-
-### Step 1 — Locate Input
-
-`$ARGUMENTS` is path to API Test Spec file: `docs/tests/API-Test-Spec-{slug}.md`.
-
-If not provided → ask user:
-```
-Enter path to API Test Spec file (e.g., docs/tests/API-Test-Spec-users.md)
-```
-
-### Step 2 — Parse API Test Spec
-
-Read `.tas/rules/csharp/api-testing.md` for conventions before generating.
-
-From API Test Spec file, collect:
-- API version
-- Endpoints with method, path, params
-- Test cases per endpoint (TC-XXX)
-- Request/response schemas
-- Auth requirements
-- Test data requirements
-- Setup/teardown notes
-
-### Step 3 — Detect Existing Test Project
-
-Glob find `**/ApiTests/*.csproj`, `**/Api.Tests/*.csproj`, `**/IntegrationTests/*.csproj`.
-
-- **Found**: Read current framework (xUnit/NUnit/MSTest), glob `v*/` folders to know existing versions.
-- **Not found**: Create new at `tests/ApiTests/` with xUnit + FluentAssertions (per `csharp/testing.md`).
-
-### Step 4 — Get API Version from Spec
-
-Read version from API Test Spec file (find frontmatter `api_version` or section headers `## v{N}`).
-
-Version folder: lowercase, no dot — `v1`, `v2` (not `v1.0`).
-
-### Step 5 — Generate Infrastructure (only when creating new project)
-
-Read `.tas/rules/csharp/api-testing.md` section **Project Structure** and **Config Pattern** to generate:
-- `ApiTests.csproj` with standard packages
-- `appsettings.json` (base) + `appsettings.Test.json` + `appsettings.Staging.json` with values from spec
-- `Shared/TestBase.cs` — load config, HttpClient, helper methods
-- `Shared/ApiTestSettings.cs` — strongly typed settings
-- `.gitignore` for `appsettings.*.local.json`
-
-### Step 6 — Generate Test Classes from Spec
-
-Group endpoints by resource. Each group → `tests/ApiTests/{version}/{Resource}ApiTests.cs`.
-
-For each test case (TC-XXX) in spec:
-1. Read test case details
-2. Map to test method with naming: `{HttpMethod}_{Resource}_Returns{Status}_When{Condition}`
-3. Generate XML doc from test case title
-4. Generate assertions from expected response
-5. Add AC reference comment if any
-
-Test class header comment:
-```csharp
-// ============================================================
-// {Resource} API Tests — v{N}
-// Spec: docs/tests/API-Test-Spec-{slug}.md
-// Generated: {YYYY-MM-DD}
-// Story: {ID} (if applicable)
-// APPEND-ONLY: don't modify existing methods.
-// ============================================================
-```
-
-### Step 7 — Append-Only Guard
-
-Before writing file: check if file already exists.
-- **File doesn't exist** → create normally.
-- **File exists** in version folder → check each test method:
-  - Method exists (same name) → **SKIP**, don't overwrite
-  - Method doesn't exist → append to end of class
-
-### Step 8 — Generate Test Data Files (if spec requires)
-
-If spec has `test-data.{env}.json` references:
-- Create `tests/ApiTests/data/test-data.Test.json` with sample data from spec
-- Guide user to create `test-data.Staging.json` and `test-data.local.json`
-
-### Step 9 — Post-Generate Review
-
-Launch `csharp-reviewer` agent:
-> Review `tests/ApiTests/{version}/`. Read `.tas/rules/csharp/testing.md` + `.tas/rules/csharp/api-testing.md`.
-> Focus: async/await, HttpClient disposal, assertion completeness, XML doc coverage.
-> Format: Critical / High / Medium / Low with file:line.
-
-Gate: Critical/High → fix immediately. Medium/Low → list suggestions.
-
-### Step 10 — Summary
-
-Display:
-1. Test project path
-2. Number of test classes generated
-3. Number of test methods generated
-4. Coverage matrix (vs spec)
-5. Next steps to run tests
-
-```
-## API Tests Generated
-
-**Project**: `tests/ApiTests/`
-**Version**: v{N}
-**Test Classes**: {N}
-**Test Methods**: {N}
-
-### Generated Files
-- tests/ApiTests/{version}/{Resource}ApiTests.cs
-- tests/ApiTests/Shared/TestBase.cs (if new project)
-
-### Coverage (vs Spec)
-[Print coverage table: spec test cases vs generated methods]
-
-### Next Steps
-1. Configure test environment: edit tests/ApiTests/appsettings.Test.json
-2. Add test data: tests/ApiTests/data/test-data.Test.json
-3. Run tests: `dotnet test tests/ApiTests/`
-```
-
-## Final Step — Token Log
-
-Follow `.tas/rules/common/token-logging.md`: write AI Usage Log to API Test Spec file.
+---
+model: sonnet
+---
+
+# /tas-apitest $ARGUMENTS
+
+Role: SE - Software Engineer
+Generate .NET xUnit automation test project for REST API from API Test Spec file (Markdown).
+
+## Always / Ask / Never
+
+| | Action |
+|---|---|
+| **Always** | Read entire API Test Spec file before generating any test |
+| **Always** | Organize tests by API version — each version separate folder |
+| **Always** | Append-only: don't modify files in existing old version folder |
+| **Always** | URL and credentials in `appsettings.json` — not hardcoded in code |
+| **Always** | XML doc comment on each test method |
+| **Ask** | When test spec unclear about expected response schema |
+| **Never** | Modify or delete old version test files |
+| **Never** | Hardcode base URL, API key, credentials in test code |
+| **Never** | Skip error path — each endpoint needs ≥1 happy path + ≥1 error path |
+
+## Actions
+
+### Step 1 — Locate Input
+
+`$ARGUMENTS` is path to API Test Spec file: `docs/tests/API-Test-Spec-{slug}.md`.
+
+If not provided → ask user:
+```
+Enter path to API Test Spec file (e.g., docs/tests/API-Test-Spec-users.md)
+```
+
+### Step 2 — Parse API Test Spec
+
+Read `.tas/rules/csharp/api-testing.md` for conventions before generating.
+
+From API Test Spec file, collect:
+- API version
+- Endpoints with method, path, params
+- Test cases per endpoint (TC-XXX)
+- Request/response schemas
+- Auth requirements
+- Test data requirements
+- Setup/teardown notes
+
+### Step 3 — Detect Existing Test Project
+
+Glob find `**/ApiTests/*.csproj`, `**/Api.Tests/*.csproj`, `**/IntegrationTests/*.csproj`.
+
+- **Found**: Read current framework (xUnit/NUnit/MSTest), glob `v*/` folders to know existing versions.
+- **Not found**: Create new at `tests/ApiTests/` with xUnit + FluentAssertions (per `csharp/testing.md`).
+
+### Step 4 — Get API Version from Spec
+
+Read version from API Test Spec file (find frontmatter `api_version` or section headers `## v{N}`).
+
+Version folder: lowercase, no dot — `v1`, `v2` (not `v1.0`).
+
+### Step 5 — Generate Infrastructure (only when creating new project)
+
+Read `.tas/rules/csharp/api-testing.md` section **Project Structure** and **Config Pattern** to generate:
+- `ApiTests.csproj` with standard packages
+- `appsettings.json` (base) + `appsettings.Test.json` + `appsettings.Staging.json` with values from spec
+- `Shared/TestBase.cs` — load config, HttpClient, helper methods
+- `Shared/ApiTestSettings.cs` — strongly typed settings
+- `.gitignore` for `appsettings.*.local.json`
+
+### Step 6 — Generate Test Classes from Spec
+
+Group endpoints by resource. Each group → `tests/ApiTests/{version}/{Resource}ApiTests.cs`.
+
+For each test case (TC-XXX) in spec:
+1. Read test case details
+2. Map to test method with naming: `{HttpMethod}_{Resource}_Returns{Status}_When{Condition}`
+3. Generate XML doc from test case title
+4. Generate assertions from expected response
+5. Add AC reference comment if any
+
+Test class header comment:
+```csharp
+// ============================================================
+// {Resource} API Tests — v{N}
+// Spec: docs/tests/API-Test-Spec-{slug}.md
+// Generated: {YYYY-MM-DD}
+// Feature: {ID} (if applicable)
+// APPEND-ONLY: don't modify existing methods.
+// ============================================================
+```
+
+### Step 7 — Append-Only Guard
+
+Before writing file: check if file already exists.
+- **File doesn't exist** → create normally.
+- **File exists** in version folder → check each test method:
+  - Method exists (same name) → **SKIP**, don't overwrite
+  - Method doesn't exist → append to end of class
+
+### Step 8 — Generate Test Data Files (if spec requires)
+
+If spec has `test-data.{env}.json` references:
+- Create `tests/ApiTests/data/test-data.Test.json` with sample data from spec
+- Guide user to create `test-data.Staging.json` and `test-data.local.json`
+
+### Step 9 — Post-Generate Review
+
+Launch `csharp-reviewer` agent:
+> Review `tests/ApiTests/{version}/`. Read `.tas/rules/csharp/testing.md` + `.tas/rules/csharp/api-testing.md`.
+> Focus: async/await, HttpClient disposal, assertion completeness, XML doc coverage.
+> Format: Critical / High / Medium / Low with file:line.
+
+Gate: Critical/High → fix immediately. Medium/Low → list suggestions.
+
+### Step 10 — Summary
+
+Display:
+1. Test project path
+2. Number of test classes generated
+3. Number of test methods generated
+4. Coverage matrix (vs spec)
+5. Next steps to run tests
+
+```
+## API Tests Generated
+
+**Project**: `tests/ApiTests/`
+**Version**: v{N}
+**Test Classes**: {N}
+**Test Methods**: {N}
+
+### Generated Files
+- tests/ApiTests/{version}/{Resource}ApiTests.cs
+- tests/ApiTests/Shared/TestBase.cs (if new project)
+
+### Coverage (vs Spec)
+[Print coverage table: spec test cases vs generated methods]
+
+### Next Steps
+1. Configure test environment: edit tests/ApiTests/appsettings.Test.json
+2. Add test data: tests/ApiTests/data/test-data.Test.json
+3. Run tests: `dotnet test tests/ApiTests/`
+```
+
+## Final Step — Token Log
+
+Follow `.tas/rules/common/token-logging.md`: write AI Usage Log to API Test Spec file.

package/.tas/commands/tas-brainstorm.md

@@ -1,19 +1,23 @@
-# /tas-brainstorm $ARGUMENTS
-
-Role: Any
-Structured brainstorming before coding or designing.
-
-## Actions
-1. $ARGUMENTS is the brainstorming topic
-2. Guide through 4 steps:
-   a. **Clarify**: Ask 3-5 questions to clarify the problem
-   b. **Explore**: Propose 3+ solution directions, each with pros/cons
-   c. **Evaluate**: Compare directions by criteria: complexity, maintainability, cost, time
-   d. **Decide**: Recommend best direction and reasoning
-
-3. If brainstorming result leads to architecture decision, suggest user run /tas-adr
-
-## Principles
-- DO NOT jump straight to solution
-- Ask first, suggest later
-- Always consider at least 2 alternatives
+---
+model: opus
+---
+
+# /tas-brainstorm $ARGUMENTS
+
+Role: Any
+Structured brainstorming before coding or designing.
+
+## Actions
+1. $ARGUMENTS is the brainstorming topic
+2. Guide through 4 steps:
+   a. **Clarify**: Ask 3-5 questions to clarify the problem
+   b. **Explore**: Propose 3+ solution directions, each with pros/cons
+   c. **Evaluate**: Compare directions by criteria: complexity, maintainability, cost, time
+   d. **Decide**: Recommend best direction and reasoning
+
+3. If brainstorming result leads to architecture decision, suggest user run /tas-adr
+
+## Principles
+- DO NOT jump straight to solution
+- Ask first, suggest later
+- Always consider at least 2 alternatives

package/.tas/commands/tas-brd.md

@@ -0,0 +1,50 @@
+---
+model: opus
+---
+
+# /tas-brd $ARGUMENTS
+
+Role: PE - Product Engineer
+Create or update Business Requirements Document.
+
+## Actions
+1. Read root/tas.yaml for project context
+2. Check if docs/brd.md already exists:
+
+### CREATE mode (file doesn't exist):
+3. Read .tas/templates/BRD.md
+4. If $ARGUMENTS has content, use as initiative/problem description input
+5. If no $ARGUMENTS, ask user:
+   - What business problem or opportunity does this initiative address?
+   - What are the primary business objectives and KPIs?
+   - Who are the key stakeholders?
+   - What is in scope vs out of scope?
+   - Are there budget, timeline, or regulatory constraints?
+6. Create file docs/brd.md per template — fill all 9 sections
+7. Update `project-status.yaml` per `.tas/rules/common/project-status.md` — add `artifacts.brd`
+
+### UPDATE mode (file exists):
+3. Read current docs/brd.md
+4. $ARGUMENTS is change description. If not provided, ask user which section to update.
+5. Update file, keep unchanged sections as-is
+6. Add line to Changelog section at end: date, change description
+7. Update `project-status.yaml` per `.tas/rules/common/project-status.md` — update `artifacts.brd`
+
+## Principles
+- **BRD is business-level only** — no technical implementation detail, no architecture decisions
+- Business Requirements (BR-xxx) describe WHAT the business needs, not HOW to build it
+- Stakeholder table must include decision makers, contributors, and informed parties
+- Constraints section must include budget, timeline, legal/regulatory, and technical limits
+- Always include Out of Scope items — explicit exclusions prevent scope creep
+- KPIs must be measurable with targets (e.g. "reduce by 30%" not "improve")
+- Mermaid diagrams must use :::mermaid wrapper, NO () characters
+
+## Relationship to PRD
+- BRD answers: **Why?** (business need, goals, constraints)
+- PRD answers: **What?** (product behavior, features, acceptance criteria)
+- 1 BRD → 1 PRD in this kit (Option A cardinality)
+- PRD command (`/tas-prd`) reads BRD for context and generates summary link-back
+
+## Final Step — Token Log
+
+Apply `.tas/rules/common/token-logging.md` to `docs/brd.md` NOW (do not defer, do not leave placeholder text). Estimate input/output tokens from this session per the rule, then fill the `## AI Usage Log` table row and Total. The BRD template already includes the skeleton — replace `~{N}k` with actual estimates.

package/.tas/commands/tas-bug.md

@@ -1,113 +1,127 @@
-# /tas-bug $ARGUMENTS
-
-Manage entire bug lifecycle: create, analyze, fix, verify.
-Bug status determines next step — no role declaration needed.
-
-## Always / Ask / Never
-
-| | Action |
-|---|---|
-| **Always** | Display current status and next action before doing anything |
-| **Always** | Write regression test BEFORE fixing |
-| **Always** | Launch independent review agent after fix — no review in same session |
-| **Ask** | When needing to read files outside Bug file (Status = Committed) |
-| **Never** | Patch symptom — must fix root cause |
-| **Never** | Skip review step after fix |
-| **Never** | Auto-commit or push — wait for user manual testing first |
-
-## Stack Detection
-Read `.tas/rules/common/stack-detection.md`.
-
-## Actions
-
-### Step 1 — Determine mode
-
-`$ARGUMENTS` is new bug description → **CREATE mode**
-`$ARGUMENTS` is Bug ID (e.g., `Bug-001`) → **UPDATE mode**
-
----
-
-### CREATE mode
-
-Role: PE or SE (whoever discovered the bug)
-
-1. Read `project.code` from root/`tas.yaml`
-2. Ask user:
-   - Which Feature does this bug belong to?
-   - Severity: `Critical` | `High` | `Medium` | `Low`
-   - Steps to reproduce
-   - Expected vs Actual behavior
-   - Environment where discovered: Test | Staging | Production
-3. Create `docs/bugs/{code}-Bug-{NNN}-{slug}.md` from template `.tas/templates/Bug.md`
-4. Initial bug status: `New`
-
----
-
-### UPDATE mode
-
-Find Bug file via glob `docs/bugs/*-Bug-{ID}-*.md`, read current status.
-
-**Display before acting:**
-> "Bug-{NNN} is currently at status: **{status}** — next step is {action}. Continue?"
-
----
-
-#### Status = `New` — Analyze (SE)
-
-1. Read error logs/stack trace from Bug file
-2. Trace code flow, identify file and line causing error
-3. Write Root Cause Analysis into Bug file
-4. Write Regression Test Cases (test that reproduces bug)
-5. Update status: `New` → `Committed`
-
----
-
-#### Status = `Committed` — Fix (SE)
-
-**File reading rule:** ONLY read Bug file. DO NOT read PRD, SAD, ADR, Design-Spec, DO NOT scan directories.
-If additional files needed → ask user confirmation first.
-
-Before fixing, read:
-- `.tas/rules/common/security.md` — fix must not create new security risks
-- `.tas/rules/common/testing.md` — regression test writing patterns
-- `.tas/rules/[lang_agent stack]/coding-style.md` — follow conventions
-
-**Fix workflow:**
-a. Run regression test case → confirm **FAIL** (reproduces bug)
-b. Fix code at root cause
-c. Run regression test → confirm **PASS**
-d. Run full test suite → no new regressions
-→ If build fails or test compile errors: launch `build-resolver` agent with error output before continuing.
-
-**After fix — Post-Fix Review (Isolated Agent):**
-
-Follow `.tas/rules/common/post-implementation-review.md`.
-Pass in: Bug file path, changed files list, stack (from CLAUDE.md), lang_agent.
-
-After review passes:
-- Update status: `Committed` → `Deploy Test`
-- Output suggested commit message: `fix: {short description} - resolves Bug-{NNN}`
-- Ask: "Have you tested manually? Want to commit and deploy to Test?"
-
----
-
-#### Status = `Verify Test` / `Verify Stag` — Verify (PE)
-
-1. PE verifies on corresponding environment:
-   - Run Steps to Reproduce again → confirm bug no longer exists
-   - Check regression test case has passed
-2. **Pass** → update to next status (`Deploy Stag` or `Done`)
-3. **Fail** → document reason, update status back to `Committed`, SE fixes again
-
----
-
-## Principles
-- DO NOT patch symptom — must fix root cause
-- MUST have regression test case BEFORE fixing
-- Review must run through independent Agent — not inline in current session
-- `Critical`/`High` bugs must be fixed before Feature is Verified
-- Flow: `New` → `Committed` → `Deploy Test` → `Verify Test` → `Deploy Stag` → `Verify Stag` → `Deploy Prod` → `Verify Prod` → `Done`
-
-## Final Step — Token Log
-
-Follow `.tas/rules/common/token-logging.md`: write AI Usage Log to working Bug file.
+---
+model: sonnet
+---
+
+# /tas-bug $ARGUMENTS
+
+Manage entire bug lifecycle: create, analyze, fix, verify.
+Bug status determines next step — no role declaration needed.
+
+## Always / Ask / Never
+
+| | Action |
+|---|---|
+| **Always** | Display current status and next action before doing anything |
+| **Always** | Write regression test BEFORE fixing |
+| **Always** | Launch independent review agent after fix — no review in same session |
+| **Ask** | When needing to read files outside Bug file (Status = Committed) |
+| **Never** | Patch symptom — must fix root cause |
+| **Never** | Skip review step after fix |
+| **Never** | Auto-commit or push — wait for user manual testing first |
+
+## Stack Detection
+Read `.tas/rules/common/stack-detection.md`.
+
+## Actions
+
+### Step 1 — Determine mode
+
+`$ARGUMENTS` is new bug description → **CREATE mode**
+`$ARGUMENTS` is Bug ID (e.g., `Bug-001`) → **UPDATE mode**
+
+---
+
+### CREATE mode
+
+Role: PE or SE (whoever discovered the bug)
+
+1. Read `project.code` from root/`tas.yaml`
+2. Ask user:
+   - Which Feature does this bug belong to?
+   - Severity: `Critical` | `High` | `Medium` | `Low`
+   - Steps to reproduce
+   - Expected vs Actual behavior
+   - Environment where discovered: Test | Staging | Production
+3. Create `docs/bugs/{code}-Bug-{NNN}-{slug}.md` from template `.tas/templates/Bug.md`
+4. Initial bug status: `New`
+
+---
+
+### UPDATE mode
+
+Find Bug file via glob `docs/bugs/*-Bug-{ID}-*.md`, read current status.
+
+**Display before acting:**
+> "Bug-{NNN} is currently at status: **{status}** — next step is {action}. Continue?"
+
+---
+
+#### Status = `New` — Analyze (SE)
+
+1. Read error logs/stack trace from Bug file
+2. Trace code flow, identify file and line causing error
+3. Write Root Cause Analysis into Bug file
+4. Write Regression Test Cases (test that reproduces bug)
+5. **Fill SAD Impact Matrix** — read `.tas/rules/common/sad-impact.md`. Anticipate fix scope (will it add lib / cache / queue / column / ENV / port / auth change / etc.). Mark `Detected: Yes` rows + SAD section + summary. If any Yes → set frontmatter `sad_impact: true`. Reading `docs/sad.md` allowed in this step (limited to sections referenced by matrix).
+6. Update status: `New` → `Committed`
+
+---
+
+#### Status = `Committed` — Fix (SE)
+
+**File reading rule:** ONLY read Bug file. DO NOT read PRD, ADR, Design-Spec, DO NOT scan directories.
+SAD read **allowed** if Bug frontmatter `sad_impact: true` (limited to sections in matrix).
+If other files needed → ask user confirmation first.
+
+Before fixing, read:
+- `.tas/rules/common/security.md` — fix must not create new security risks
+- `.tas/rules/common/testing.md` — regression test writing patterns
+- `.tas/rules/[lang_agent stack]/coding-style.md` — follow conventions
+
+**Fix workflow:**
+a. Run regression test case → confirm **FAIL** (reproduces bug)
+b. Fix code at root cause
+c. Run regression test → confirm **PASS**
+d. Run full test suite → no new regressions
+→ If build fails or test compile errors: launch `build-resolver` agent with error output before continuing.
+
+**After fix — Post-Fix Review (Isolated Agent):**
+
+Follow `.tas/rules/common/post-implementation-review.md`.
+Pass in: Bug file path, changed files list, stack (from CLAUDE.md), lang_agent.
+
+After review passes:
+
+**SAD update (if flagged):** If Bug frontmatter `sad_impact: true`:
+- Re-evaluate matrix vs actual fix (fix scope may have shifted from analyze-time estimate). Update matrix Yes/No if changed.
+- If still any Yes → auto-invoke `/tas-sad "Bug-{NNN}: {one-line summary from matrix Yes rows}"` inline. Verify `docs/sad.md` Changelog contains `Bug-{NNN}` ref before status transition.
+- If matrix is now all No → set frontmatter `sad_impact: false`, skip invoke.
+
+**Status transition:**
+- Update status: `Committed` → `Deploy Test`
+- Output suggested commit message: `fix: {short description} - resolves Bug-{NNN}`
+- Ask: "Have you tested manually? Want to commit and deploy to Test?"
+
+---
+
+#### Status = `Verify Test` / `Verify Stag` — Verify (PE)
+
+1. PE verifies on corresponding environment:
+   - Run Steps to Reproduce again → confirm bug no longer exists
+   - Check regression test case has passed
+2. **Pass** → update to next status (`Deploy Stag` or `Done`)
+   - **SAD Done Gate** (when transitioning to `Done`): if Bug frontmatter `sad_impact: true` → grep `docs/sad.md` Changelog for `Bug-{NNN}` ref. No match → BLOCK `Done`, surface: "SAD impact flagged but `docs/sad.md` Changelog missing Bug-{NNN} ref. Re-run `/tas-sad` before closing."
+3. **Fail** → document reason, update status back to `Committed`, SE fixes again
+
+---
+
+## Principles
+- DO NOT patch symptom — must fix root cause
+- MUST have regression test case BEFORE fixing
+- Review must run through independent Agent — not inline in current session
+- `Critical`/`High` bugs must be fixed before Feature is Verified
+- Flow: `New` → `Committed` → `Deploy Test` → `Verify Test` → `Deploy Stag` → `Verify Stag` → `Deploy Prod` → `Verify Prod` → `Done`
+
+## Final Step — Token Log
+
+Follow `.tas/rules/common/token-logging.md`: write AI Usage Log to working Bug file.