@mmerterden/multi-agent-pipeline 8.6.1 → 10.0.6

package/pipeline/skills/figma-common/performance-start/SKILL.md

@@ -1,6 +1,11 @@
-# /performance-start — Start + Auto-Launch Performance Pipeline
+---
+name: performance-start
+description: Identical to `/figma-to-swift-ui-start` for Steps 0-5. After printing the summary (Step 6), automatically invokes `/performance-swiftui <figma-url>` to begin the implementation pipeline.
+---
+
+# /performance-start  -  Start + Auto-Launch Performance Pipeline
 
-> Identical to `/figma-to-swift-ui-start` for Steps 0–5. After printing the summary (Step 6),
+> Identical to `/figma-to-swift-ui-start` for Steps 0-5. After printing the summary (Step 6),
 > automatically invokes `/performance-swiftui <figma-url>` to begin the implementation pipeline
 > without waiting for user input.
 
@@ -8,10 +13,10 @@
 
 | Parameter | Required | Default | Description |
 |-----------|----------|---------|-------------|
-| `<issue-number>` | Yes | — | GitHub issue number from uicomponents repo |
-| `jira id <KEY>` | No | — | Jira issue key (e.g., `{jira.projectKey}-129850`). If provided, updates GitHub issue body and populates Jira task. |
-| `--tour` | No | — | Tour mode: skips fetch/pull (STEP 1) and branch creation (STEP 2). Used by `/performance-tour` when producing multiple components on `iteration/develop`. |
-| `--lean` | No | — | Lean mode: forwarded to `/performance-swiftui` to skip Phase 5 (testing) and Phase 7 (wiki). Can be combined with `--tour`. |
+| `<issue-number>` | Yes |  -  | GitHub issue number from uicomponents repo |
+| `jira id <KEY>` | No |  -  | Jira issue key (e.g., `{jira.projectKey}-129850`). If provided, updates GitHub issue body and populates Jira task. |
+| `--tour` | No |  -  | Tour mode: skips fetch/pull (STEP 1) and branch creation (STEP 2). Used by `/performance-tour` when producing multiple components on `iteration/develop`. |
+| `--lean` | No |  -  | Lean mode: forwarded to `/performance-swiftui` to skip Phase 5 (testing) and Phase 7 (wiki). Can be combined with `--tour`. |
 
 ```
 /performance-start #107
@@ -28,15 +33,15 @@ When `--tour` is passed, the following steps are **SKIPPED**:
 
 | Step | Normal Mode | Tour Mode |
 |------|------------|:---------:|
-| STEP 0 — Parse Issue | ✅ | ✅ |
-| STEP 0.5 — Confirm Pipeline Mode | ✅ | **SKIP** |
-| STEP 1 — Fetch Latest | ✅ | **SKIP** |
-| STEP 2 — Create Feature Branches | ✅ | **SKIP** |
-| STEP 3 — Registry Lookup | ✅ | ✅ |
-| STEP 3.5 — Save Specs Artifact | ✅ | ✅ |
-| STEP 4 — Assign to Me | ✅ | ✅ |
-| STEP 5 — Update Issue Status | ✅ | ✅ |
-| STEP 6 — Summary + Auto-Launch | ✅ | ✅ |
+| STEP 0  -  Parse Issue | ✅ | ✅ |
+| STEP 0.5  -  Confirm Pipeline Mode | ✅ | **SKIP** |
+| STEP 1  -  Fetch Latest | ✅ | **SKIP** |
+| STEP 2  -  Create Feature Branches | ✅ | **SKIP** |
+| STEP 3  -  Registry Lookup | ✅ | ✅ |
+| STEP 3.5  -  Save Specs Artifact | ✅ | ✅ |
+| STEP 4  -  Assign to Me | ✅ | ✅ |
+| STEP 5  -  Update Issue Status | ✅ | ✅ |
+| STEP 6  -  Summary + Auto-Launch | ✅ | ✅ |
 
 **Rationale:** In tour mode, `/performance-tour` has already fetched latest and
 all submodules are on `iteration/develop`. Creating feature branches would conflict
@@ -64,24 +69,24 @@ WIKI            = ${REPO_ROOT}/{repos.wiki.path}
 
 ---
 
-## STEP 0 — Parse Issue
+## STEP 0  -  Parse Issue
 
 ```bash
 gh issue view <N> --repo ${GH_REPO} --json number,title,body,labels,assignees
 ```
 
 Extract from the issue body:
-- **Component Name** — from `### Component Name (PascalCase)` section
-- **Figma URL** — from `### Figma URL` section
-- **Node ID** — from `### Node ID` section
-- **Registry Name** — from `### Registry Name` section
-- **Figma Page** — from `### Figma Page` section
-- **Jira Key** — from `### Jira Issue` section (if not `_No response_`)
-- **Acceptance Criteria** — from `### Acceptance Criteria` section (if not `_No response_`)
+- **Component Name**  -  from `### Component Name (PascalCase)` section
+- **Figma URL**  -  from `### Figma URL` section
+- **Node ID**  -  from `### Node ID` section
+- **Registry Name**  -  from `### Registry Name` section
+- **Figma Page**  -  from `### Figma Page` section
+- **Jira Key**  -  from `### Jira Issue` section (if not `_No response_`)
+- **Acceptance Criteria**  -  from `### Acceptance Criteria` section (if not `_No response_`)
 
 If Jira key is `_No response_` or empty **and** user provided a `jira id` parameter:
 1. Use the user-provided key as `JIRA_ISSUE`.
-2. Update the GitHub issue body — replace `_No response_` under `### Jira Issue` with a Jira link:
+2. Update the GitHub issue body  -  replace `_No response_` under `### Jira Issue` with a Jira link:
    ```bash
    # Read current body, replace the Jira section, update via gh
    CURRENT_BODY=$(gh issue view <N> --repo ${GH_REPO} --json body --jq '.body')
@@ -114,17 +119,17 @@ Print:
 
 ---
 
-## STEP 0.5 — Confirm Pipeline Mode
+## STEP 0.5  -  Confirm Pipeline Mode
 
 > **If `--tour` is set → SKIP this step.** Tour mode delegates mode selection to `/performance-tour`.
 
-After parsing the issue, **always ask the user** to confirm which pipeline mode to use — regardless of whether `--lean` was passed as a parameter. This prevents accidental full-pipeline runs when lean was intended, or vice versa.
+After parsing the issue, **always ask the user** to confirm which pipeline mode to use  -  regardless of whether `--lean` was passed as a parameter. This prevents accidental full-pipeline runs when lean was intended, or vice versa.
 
 **Use the ask-questions tool** with these options:
 
 | Header | Question | Options |
 |--------|----------|---------|
-| Pipeline Mode | `<COMPONENT_PASCAL>` implementation — which pipeline mode? | **Lean** (skip testing & wiki — Phases 5, 7) · **Full** (all 8 phases) |
+| Pipeline Mode | `<COMPONENT_PASCAL>` implementation  -  which pipeline mode? | **Lean** (skip testing & wiki  -  Phases 5, 7) · **Full** (all 8 phases) |
 
 - If `--lean` was passed in the original command, pre-select **Lean** as the recommended option.
 - If no flag was passed, pre-select **Full** as the recommended option.
@@ -137,7 +142,7 @@ This confirmation overrides whatever was passed on the command line.
 
 ---
 
-## STEP 1 — Fetch Latest
+## STEP 1  -  Fetch Latest
 
 > **If `--tour` is set → SKIP this entire step.** Tour mode assumes
 > `/performance-tour` STEP 0e has already fetched and checked out the correct branches.
@@ -163,12 +168,12 @@ git pull origin iteration/develop
 
 ---
 
-## STEP 2 — Create Feature Branches
+## STEP 2  -  Create Feature Branches
 
 > **If `--tour` is set → SKIP this entire step.** Tour mode stays on
 > `iteration/develop` with local commits. No feature branches are created.
 
-Create feature branches on **submodules only**. Do NOT create branches on the main repo — it stays on `develop`. The main repo never receives commits from this workflow; submodule refs are updated separately.
+Create feature branches on **submodules only**. Do NOT create branches on the main repo  -  it stays on `develop`. The main repo never receives commits from this workflow; submodule refs are updated separately.
 
 ```bash
 # Common (tokens, localization, accessibility, testing identifiers)
@@ -180,11 +185,11 @@ cd ${UICOMPONENTS}
 git checkout -b ${BRANCH_NAME}
 ```
 
-Wiki submodule stays on `master` — wiki changes are committed directly.
+Wiki submodule stays on `master`  -  wiki changes are committed directly.
 
 ---
 
-## STEP 3 — Registry Lookup
+## STEP 3  -  Registry Lookup
 
 ```bash
 cd ${COMMON}
@@ -192,8 +197,8 @@ cd ${COMMON}
 ```
 
 Collect:
-- `suggestedComponentLocation` — where the Swift files will go
-- `suggestedArtifactPath` — where implementation artifacts go
+- `suggestedComponentLocation`  -  where the Swift files will go
+- `suggestedArtifactPath`  -  where implementation artifacts go
 
 Print:
 
@@ -204,7 +209,7 @@ Artifact Path:      <suggestedArtifactPath>
 
 ---
 
-## STEP 3.5 — Save Specs Artifact
+## STEP 3.5  -  Save Specs Artifact
 
 If the issue has acceptance criteria (not `_No response_`), save them as an artifact that the implementation pipeline can consume.
 
@@ -223,21 +228,21 @@ Write `${suggestedArtifactPath}/pass0/specs.md`:
 
 ## Acceptance Criteria
 
-{ACCEPTANCE_CRITERIA from issue body — verbatim}
+{ACCEPTANCE_CRITERIA from issue body  -  verbatim}
 
 ## Implementation Guidance
 
 {Convert the acceptance criteria into actionable implementation instructions for the AI agent:
 - Rephrase checkbox items as concrete requirements
 - Add technical context where the criteria imply Swift/SwiftUI patterns
-- Preserve the user's intent exactly — don't add or remove requirements}
+- Preserve the user's intent exactly  -  don't add or remove requirements}
 ```
 
 If no acceptance criteria → skip this step. No file created.
 
 ---
 
-## STEP 4 — Assign to Me
+## STEP 4  -  Assign to Me
 
 Assign the GitHub issue and linked Jira task (if any) to the current user. Same logic as `/figma-issue assign`:
 
@@ -245,7 +250,7 @@ Assign the GitHub issue and linked Jira task (if any) to the current user. Same
 gh issue edit <N> --repo ${GH_REPO} --add-assignee @me
 ```
 
-If Jira key exists (from issue body or user-provided `jira id` parameter — not `_No response_` and not `DEFAULT_JIRA`):
+If Jira key exists (from issue body or user-provided `jira id` parameter  -  not `_No response_` and not `DEFAULT_JIRA`):
 
 Use **Python urllib** for all Jira API calls (curl is blocked by terminal auto-approval policy):
 
@@ -288,7 +293,7 @@ try:
     resp2 = urllib.request.urlopen(req2, timeout=15)
     print(f"Assigned {JIRA_KEY} to {username} (HTTP {resp2.status})")
 except urllib.error.HTTPError as e:
-    print(f"Assign failed — HTTP {e.code}: {e.read().decode()[:200]}")
+    print(f"Assign failed  -  HTTP {e.code}: {e.read().decode()[:200]}")
 
 # 3. Update Jira summary, description, and labels
 description = (
@@ -328,7 +333,7 @@ try:
     resp3 = urllib.request.urlopen(req3, timeout=15)
     print(f"Updated {JIRA_KEY} content (HTTP {resp3.status})")
 except urllib.error.HTTPError as e:
-    print(f"Update failed — HTTP {e.code}: {e.read().decode()[:200]}")
+    print(f"Update failed  -  HTTP {e.code}: {e.read().decode()[:200]}")
 ```
 
 Run: `python3 /tmp/jira_start_<JIRA_KEY>.py`
@@ -341,7 +346,7 @@ If Jira token not found or VPN unreachable, skip with warning:
 
 ---
 
-## STEP 5 — Update Issue Status (required)
+## STEP 5  -  Update Issue Status (required)
 
 **This step is mandatory. Do not skip it and do not defer it.** The issue
 is on the board with Status=Todo after creation. Moving it to Status=In
@@ -355,7 +360,7 @@ Set the issue phase to "Implementation" and status to "In Develop" on the Projec
 # Get issue node ID
 ISSUE_NODE_ID=$(gh api graphql -f query='{ repository(owner: "{github.org}", name: "{project.slug}-components") { issue(number: <N>) { id } } }' --jq '.data.repository.issue.id')
 
-# Add to project (if not already). This mutation is idempotent — if the
+# Add to project (if not already). This mutation is idempotent  -  if the
 # item already exists it returns the existing item id.
 ITEM_ID=$(gh api graphql -f query='mutation { addProjectV2ItemById(input: { projectId: "{github.projectV2Id}", contentId: "'"$ISSUE_NODE_ID"'" }) { item { id } } }' --jq '.data.addProjectV2ItemById.item.id')
 
@@ -377,12 +382,12 @@ gh api graphql -f query='{ node(id: "'"$ITEM_ID"'") { ... on ProjectV2Item { fie
 ```
 
 Expected output: `In Develop`. If you see anything else (or empty),
-re-fetch the current option IDs and retry — do NOT proceed to implementation
+re-fetch the current option IDs and retry  -  do NOT proceed to implementation
 without the Status set correctly.
 
 ---
 
-## STEP 6 — Summary + Auto-Launch Pipeline
+## STEP 6  -  Summary + Auto-Launch Pipeline
 
 Print:
 
@@ -411,7 +416,7 @@ Ready to implement:
 
 Forward `--lean` based on the user's confirmed selection in **STEP 0.5** (not the raw command-line flag). This starts Phase 0 of the performance-optimized implementation pipeline.
 
-> If any STEP (0–5) failed or was aborted, do NOT auto-launch. Print the error and stop.
+> If any STEP (0-5) failed or was aborted, do NOT auto-launch. Print the error and stop.
 
 ---
 
@@ -420,6 +425,6 @@ Forward `--lean` based on the user's confirmed selection in **STEP 0.5** (not th
 - **Issue not found**: Print error and stop.
 - **Issue body missing required fields**: Print which fields are missing, stop.
 - **FigmaRegistryUtility not built**: Run `swift build --product FigmaRegistryUtility` in common.
-- **Branch already exists**: Print warning — checkout existing branch instead of creating.
+- **Branch already exists**: Print warning  -  checkout existing branch instead of creating.
 - **Main repo not on develop**: Fetch and checkout automatically.
 - **Submodule not on iteration/develop**: Fetch and checkout automatically.

package/pipeline/skills/figma-common/performance-swiftui/SKILL.md

@@ -8,7 +8,7 @@ status: wip-v5
 sourced-from: upstream/performance-swiftui
 ---
 
-# /performance-swiftui — Performance-Optimized Figma-to-SwiftUI Workflow
+# /performance-swiftui  -  Performance-Optimized Figma-to-SwiftUI Workflow
 
 > Based on `/figma-to-swiftui`. All phase instruction files, scripts, and reference docs
 > are shared from `.instructions/figma/figma-to-swiftui/`. Only the orchestrator routing,
@@ -31,7 +31,7 @@ sourced-from: upstream/performance-swiftui
 
 ### Lean Mode (`--lean`)
 
-When `--lean` is appended to a Figma URL, the workflow runs **Phases 0–4 + Phase 6 only**.
+When `--lean` is appended to a Figma URL, the workflow runs **Phases 0-4 + Phase 6 only**.
 Phase 5 (testing) and Phase 7 (wiki) are **skipped**.
 
 Lean mode is persisted in the `_perf_tracker.json` tracker:
@@ -62,7 +62,7 @@ Convert `-` to `:` in node-id (e.g., `9419-30700` → `9419:30700`).
 
 ### Tracker File
 
-All performance metrics are stored in `{artifactPath}/_perf_tracker.json`. This file is the **single source of truth** — never rely on in-memory variables for timing or reliability data.
+All performance metrics are stored in `{artifactPath}/_perf_tracker.json`. This file is the **single source of truth**  -  never rely on in-memory variables for timing or reliability data.
 
 **At workflow start** (Phase 0 or first resumed phase), create/update the tracker file:
 
@@ -114,7 +114,7 @@ with open(tracker_path, "w") as f:
     json.dump(tracker, f, indent=2)
 ```
 
-**CRITICAL:** The tracker file write happens IMMEDIATELY after each phase dispatch returns — before proceeding to the next phase. This is the mechanism that survives context loss.
+**CRITICAL:** The tracker file write happens IMMEDIATELY after each phase dispatch returns  -  before proceeding to the next phase. This is the mechanism that survives context loss.
 
 ---
 
@@ -141,7 +141,7 @@ These 6 rules govern orchestrator behavior. Violations have caused repeated fail
 
 In lean mode, Phase 5 (testing) and Phase 7 (wiki) are **SKIPPED**. Phase 6 runs sequentially (no parallel partner).
 
-This skill dispatches Phase 2 and Phase 5 sub-phases directly — no orchestrator subagent.
+This skill dispatches Phase 2 and Phase 5 sub-phases directly  -  no orchestrator subagent.
 
 When `phase-7` is invoked:
 1. Dispatch `phase-7a` (generate two wiki pages: main + iOS, plus assets into wiki submodule).
@@ -228,11 +228,11 @@ You are executing {Phase Name} of the Figma-to-SwiftUI workflow.
 - Artifact Path: {artifactPath}
 - Component Location: {componentLocation}
 - GitHub Issue: {issueNumber} (omit if not available)
-- Wiki Path: {wikiPath} (Phase 7 only — `{repos.wiki.path}`)
-- Specs: {specsPath} (if `{artifactPath}/pass0/specs.md` exists — include in Phase 3, 4 dispatch prompts as additional implementation guidance)
+- Wiki Path: {wikiPath} (Phase 7 only  -  `{repos.wiki.path}`)
+- Specs: {specsPath} (if `{artifactPath}/pass0/specs.md` exists  -  include in Phase 3, 4 dispatch prompts as additional implementation guidance)
 
 ## Tool Restrictions
-{from dispatch table — e.g., "Do NOT use the Edit tool."}
+{from dispatch table  -  e.g., "Do NOT use the Edit tool."}
 
 ## Your Instructions
 Read and STRICTLY FOLLOW your phase instructions gate-by-gate from this file:
@@ -245,18 +245,18 @@ Read the return protocol from:
 
 ## Specs (if present)
 - {artifactPath}/pass0/specs.md
-Read and incorporate specs alongside phase instructions. Both are inputs you must follow — phase instructions define methodology and coding standards, specs define acceptance criteria and design intent. Neither overrides the other.
+Read and incorporate specs alongside phase instructions. Both are inputs you must follow  -  phase instructions define methodology and coding standards, specs define acceptance criteria and design intent. Neither overrides the other.
 
 ## Reference Files (read during execution if needed)
 - .instructions/figma/figma-to-swiftui/{reference path}
 
 ## Previous Phase Artifacts (read in this order)
-{use the Read-Order Table below — list file PATHS only, do not embed content}
+{use the Read-Order Table below  -  list file PATHS only, do not embed content}
 ```
 
 ### 2. Dispatch
 
-**Phase 1 (script):** Run directly via Bash — no subagent needed:
+**Phase 1 (script):** Run directly via Bash  -  no subagent needed:
 
 ```bash
 python3 .instructions/figma/figma-to-swiftui/scripts/phase1-gather.py \
@@ -271,7 +271,7 @@ The script tries remote MCP first, falls back to local MCP automatically.
 
 **If `status` = `COMPLETE_WITH_DEFERRED`:**
 Design context was deferred (too many sublayers). All other artifacts are present.
-Do NOT ask the user — dispatch a **Phase 1 subagent** for deferred resolution:
+Do NOT ask the user  -  dispatch a **Phase 1 subagent** for deferred resolution:
 
 ```
 Agent(
@@ -301,7 +301,7 @@ Agent(
 
 ### 3. Parse the return
 
-> **All counters are persisted to `{artifactPath}/_perf_tracker.json` — NOT held in memory.**
+> **All counters are persisted to `{artifactPath}/_perf_tracker.json`  -  NOT held in memory.**
 > Read the tracker file before updating, write it back immediately after. This survives context loss.
 
 **Before dispatching each phase**, record the start time in the tracker:
@@ -319,16 +319,16 @@ with open(tracker_path, "w") as f:
 **STATUS: COMPLETE**
 → Record gates and artifacts
 → **Update tracker file on disk**: set phase `end`, `duration_seconds`, `status: "COMPLETE"`
-→ **Append phase timing to IMPLEMENTATION_HISTORY.md** (incremental write — see step 4)
+→ **Append phase timing to IMPLEMENTATION_HISTORY.md** (incremental write  -  see step 4)
 → Proceed to next phase
 
 **STATUS: HALT**
 → **Update tracker file on disk**: increment `halt_count`, append to `halt_log`
 → Show user: GATE, REASON, USER_ACTION_REQUIRED via AskUserQuestion
 → Options: "Fix and retry", "Skip this phase", "Abort workflow"
-→ Retry: update tracker — increment `retry_count`, set `resolution: "retry"`, re-dispatch same phase
-→ Skip: update tracker — set `resolution: "skipped"`, `status: "SKIPPED"`, proceed
-→ Abort: update tracker — set `resolution: "aborted"`, `status: "ABORTED"`, stop workflow
+→ Retry: update tracker  -  increment `retry_count`, set `resolution: "retry"`, re-dispatch same phase
+→ Skip: update tracker  -  set `resolution: "skipped"`, `status: "SKIPPED"`, proceed
+→ Abort: update tracker  -  set `resolution: "aborted"`, `status: "ABORTED"`, stop workflow
 
 **STATUS: NEEDS_INPUT**
 → Show user: QUESTION, OPTIONS, SUGGESTED via AskUserQuestion
@@ -339,7 +339,7 @@ with open(tracker_path, "w") as f:
     ANSWER: {user's choice}
   ```
 
-### 4. Update history (incremental — after EVERY phase)
+### 4. Update history (incremental  -  after EVERY phase)
 
 **After each phase completes, IMMEDIATELY write two things:**
 
@@ -371,15 +371,15 @@ Also update IMPLEMENTATION_HISTORY.md with the standard phase status, gates, and
 
 ---
 
-## Phase 2 Routing (inline — do NOT read phase-2-orchestrator.md)
+## Phase 2 Routing (inline  -  do NOT read phase-2-orchestrator.md)
 
 **Do NOT read `phase-2-orchestrator.md`. All routing logic is here. Subagents read their own docs.**
 
-> **UNCHANGED from original** — Phase 2 routing preserved exactly.
+> **UNCHANGED from original**  -  Phase 2 routing preserved exactly.
 
 1. **PRE-CHECK**: Read `IMPLEMENTATION_HISTORY.md` (already in context). Verify `pass1/_index.md` exists.
-2. **NORMALIZE**: Check `pass1/design_context_response.json` — if `sublayers: true` and no `response` field, concatenate `responses` values into `response` field and write back.
-3. **REGISTRY_LOOKUP**: `cd {repos.common.path} && .build/debug/FigmaRegistryUtility utility-lookup --node-id '{nodeId}'` — pass result as `registryData` context to subagents.
+2. **NORMALIZE**: Check `pass1/design_context_response.json`  -  if `sublayers: true` and no `response` field, concatenate `responses` values into `response` field and write back.
+3. **REGISTRY_LOOKUP**: `cd {repos.common.path} && .build/debug/FigmaRegistryUtility utility-lookup --node-id '{nodeId}'`  -  pass result as `registryData` context to subagents.
 4. **Wave 1 (parallel)**: Dispatch 2A + 2B + 2C as subagents (each reads its own instruction doc by path).
 5. **Wave 2**: Dispatch 2D as subagent (depends on 2A output).
 6. **FINALIZE (script)**:
@@ -393,11 +393,11 @@ Also update IMPLEMENTATION_HISTORY.md with the standard phase status, gates, and
 
 ---
 
-## Phase 3 Routing (inline — do NOT read phase-3-orchestrator.md)
+## Phase 3 Routing (inline  -  do NOT read phase-3-orchestrator.md)
 
 **Do NOT read `phase-3-orchestrator.md`. Subagents read their own docs. Scripts handle deterministic phases.**
 
-> **UNCHANGED from original** — Phase 3 routing preserved exactly.
+> **UNCHANGED from original**  -  Phase 3 routing preserved exactly.
 
 1. **PRE-CHECK**: Verify `pass2/_index.md` exists.
 2. **NORMALIZE**: Same sublayer check as Phase 2 (skip if already normalized).
@@ -405,14 +405,14 @@ Also update IMPLEMENTATION_HISTORY.md with the standard phase status, gates, and
    - **Scripts**: `python3 .instructions/figma/figma-to-swiftui/scripts/phase3-scripts.py wave1 --artifact-path '{artifactPath}'` (runs 3B+3E+3F, ~5s)
    - **Subagents**: 3A (`phase-3a-location.md`, sonnet, 20 turns), 3C (`phase-3c-nested.md`, sonnet, 20 turns), 3H (`phase-3h-variant-config.md`, opus, 25 turns)
 4. **MISSING TOKEN RESOLUTION**: After Wave 1, check `pass3/02_token_mapping.md` for missing tokens (lines with "⚠️ not found"). If any exist, dispatch a subagent:
-   - **Subagent** (`general-purpose`, opus, 25 turns) — reads `reference/missing-tokens.md` for procedure, resolves each missing token by:
+   - **Subagent** (`general-purpose`, opus, 25 turns)  -  reads `reference/missing-tokens.md` for procedure, resolves each missing token by:
      - **Typography**: Adding alias entries to `typography-registry.json` (match font size + weight to existing Swift tokens)
      - **Colors**: Adding to `Shared/UIAssets/Colors/*.json` (source), running `swift package plugin --allow-writing-to-package-directory generate-ui-assets`, adding to `ui-token-index.json`
      - **Variables**: Using `FigmaRegistryUtility ui-token-lookup` / `ui-token-index` to verify
    - Pass artifact path and token mapping path as context. Subagent updates token mapping after resolution.
    - If 0 missing tokens, skip this step entirely.
 5. **Wave 2 (parallel)**: Launch simultaneously:
-   - **Subagent**: 3D (`phase-3d-patterns.md`, opus, 30 turns) — reads 3H output (`pass3/04c_variant_config_analysis.json`)
+   - **Subagent**: 3D (`phase-3d-patterns.md`, opus, 30 turns)  -  reads 3H output (`pass3/04c_variant_config_analysis.json`)
 6. **Wave 3**: `python3 .instructions/figma/figma-to-swiftui/scripts/phase3-scripts.py 3g --artifact-path '{artifactPath}'` (depends on 3D JSON output)
 7. **COLLECT**: Verify 12 artifacts exist in `pass3/` (10 original + 2 from 3H).
 8. **SPEC (script)**: `python3 .instructions/figma/figma-to-swiftui/scripts/phase3-scripts.py spec --artifact-path '{artifactPath}'`
@@ -421,24 +421,24 @@ Also update IMPLEMENTATION_HISTORY.md with the standard phase status, gates, and
 
 ---
 
-## Phase 4 Routing (inline — do NOT read phase-4-orchestrator.md)
+## Phase 4 Routing (inline  -  do NOT read phase-4-orchestrator.md)
 
 **Do NOT read `phase-4-orchestrator.md`. Subagents read their own docs. Orchestrator stays lean.**
 
 1. **PRE-CHECK**: Verify `pass3/_index.md` exists.
-2. **LOAD_SPEC**: Read `pass3/07_implementation_spec.md` and `pass3/05_complexity.md` — extract `componentLocation`, `complexity` (SIMPLE/COMPLEX).
+2. **LOAD_SPEC**: Read `pass3/07_implementation_spec.md` and `pass3/05_complexity.md`  -  extract `componentLocation`, `complexity` (SIMPLE/COMPLEX).
 3. **PREPARE_DIRECTORY**: `mkdir -p {componentLocation}`. Get `gitUser` via `git config user.name`. Get `date` in DD.MM.YYYY format.
 4. **Wave 1 (parallel)**: Dispatch subagents:
-   - **4A** (`phase-4a-configuration.md`, opus, 30 turns) — **COMPLEX only** (skip if SIMPLE). Writes `{ComponentName}Configuration.swift`.
-   - **4B** (`phase-4b-view.md`, opus, 40 turns) — **ALWAYS**. Writes `{ComponentName}.swift`.
-   - **4C** (`phase-4c-documentation.md`, sonnet, 20 turns) — **ALWAYS**. Writes `FIGMA.md`.
-   - Pass to each: componentName, componentLocation, artifactPath, nodeId, fileKey, complexity, gitUser, date, issueNumber (from IMPLEMENTATION_HISTORY.md `GitHub Issue` field — extract the number after `#`).
+   - **4A** (`phase-4a-configuration.md`, opus, 30 turns)  -  **COMPLEX only** (skip if SIMPLE). Writes `{ComponentName}Configuration.swift`.
+   - **4B** (`phase-4b-view.md`, opus, 40 turns)  -  **ALWAYS**. Writes `{ComponentName}.swift`.
+   - **4C** (`phase-4c-documentation.md`, sonnet, 20 turns)  -  **ALWAYS**. Writes `FIGMA.md`.
+   - Pass to each: componentName, componentLocation, artifactPath, nodeId, fileKey, complexity, gitUser, date, issueNumber (from IMPLEMENTATION_HISTORY.md `GitHub Issue` field  -  extract the number after `#`).
 5. **Wave 2 (parallel)**: Dispatch subagents that depend on 4A+4B:
-   - **4D** (`phase-4d-preview.md`, sonnet, 20 turns) — appends Preview to `{ComponentName}.swift`.
-   - **4E** (`phase-4e-modifiers.md`, sonnet, 20 turns) — **COMPLEX only** (skip if SIMPLE). Writes `{ComponentName}+Modifiers.swift`.
+   - **4D** (`phase-4d-preview.md`, sonnet, 20 turns)  -  appends Preview to `{ComponentName}.swift`.
+   - **4E** (`phase-4e-modifiers.md`, sonnet, 20 turns)  -  **COMPLEX only** (skip if SIMPLE). Writes `{ComponentName}+Modifiers.swift`.
 6. **COLLECT**: Verify `{ComponentName}.swift`, `{ComponentName}Configuration.swift` (if COMPLEX), `{ComponentName}+Modifiers.swift` (if COMPLEX), `FIGMA.md` exist.
-7. **VALIDATE**: `bash .instructions/figma/figma-to-swiftui/scripts/validate-phase4.sh "{componentLocation}" "{ComponentName}" "{artifactPath}/pass3/00_property_coverage.json"` — fix violations if any.
-8. **BUILD**: `xcodebuild build -project "$(git rev-parse --show-toplevel)/{build.xcodeproj}" -scheme {build.scheme} -destination 'generic/platform=iOS' CODE_SIGNING_ALLOWED=NO -quiet` — fix compilation errors if any.
+7. **VALIDATE**: `bash .instructions/figma/figma-to-swiftui/scripts/validate-phase4.sh "{componentLocation}" "{ComponentName}" "{artifactPath}/pass3/00_property_coverage.json"`  -  fix violations if any.
+8. **BUILD**: `xcodebuild build -project "$(git rev-parse --show-toplevel)/{build.xcodeproj}" -scheme {build.scheme} -destination 'generic/platform=iOS' CODE_SIGNING_ALLOWED=NO -quiet`  -  fix compilation errors if any.
 9. **REGISTRY FINALIZE**: After build passes, mark `status.ios.implemented` green in the component registry with a content-hashed version bump:
    ```bash
    python3 .instructions/figma/figma-to-swiftui/scripts/phase4-finalize.py \
@@ -447,32 +447,32 @@ Also update IMPLEMENTATION_HISTORY.md with the standard phase status, gates, and
        --source-file "{componentLocation}/{ComponentName}.swift" \
        --platform ios
    ```
-   Parse stdout JSON. On success (`"status": "ok"`), the registry entry now has `implemented.value: true`, `implemented.version: 1` (or bumped), and a content hash. On failure, log the error but do NOT halt — the finalize can be re-run manually or via `/figma-iteration-commit`.
+   Parse stdout JSON. On success (`"status": "ok"`), the registry entry now has `implemented.value: true`, `implemented.version: 1` (or bumped), and a content hash. On failure, log the error but do NOT halt  -  the finalize can be re-run manually or via `/figma-iteration-commit`.
 10. **UPDATE HISTORY**: Append Phase 4 summary.
 
 ---
 
-## Phase 5 Routing (inline — do NOT read phase-5-orchestrator.md)
+## Phase 5 Routing (inline  -  do NOT read phase-5-orchestrator.md)
 
 > **LEAN MODE: If `lean_mode` is `true` in `_perf_tracker.json`, SKIP this entire section.**
-> Record Phase 5 as `"status": "SKIPPED"` in the tracker and append `| Phase 5 (Testing) | — | ⏭️ lean | ... |` to IMPLEMENTATION_HISTORY.md.
+> Record Phase 5 as `"status": "SKIPPED"` in the tracker and append `| Phase 5 (Testing) |  -  | ⏭️ lean | ... |` to IMPLEMENTATION_HISTORY.md.
 > Proceed directly to Phase 6 (sequentially, not parallel with Phase 7).
 
 **Do NOT read `phase-5-orchestrator.md`. Subagents read their own docs.**
 
-> **PERF CHANGE: Combined test execution** — runs ViewInspector + Snapshot tests in a single xcodebuild invocation instead of two separate build+test cycles.
-> **PERF CHANGE: Simulator pre-warm** — boots simulator in background during test file generation to eliminate cold-start latency.
+> **PERF CHANGE: Combined test execution**  -  runs ViewInspector + Snapshot tests in a single xcodebuild invocation instead of two separate build+test cycles.
+> **PERF CHANGE: Simulator pre-warm**  -  boots simulator in background during test file generation to eliminate cold-start latency.
 
 1. **PRE-CHECK**: Verify Phase 4 complete (component Swift file exists at `{componentLocation}`).
 2. **SIMULATOR PRE-WARM** (parallel with Wave 1): Boot the simulator in the background before test files are written:
    ```bash
    xcrun simctl boot "iPhone 17 Pro" 2>/dev/null &
    ```
-   This runs asynchronously — no need to wait. By the time test execution starts (step 4b), the simulator is ready.
+   This runs asynchronously  -  no need to wait. By the time test execution starts (step 4b), the simulator is ready.
 3. **Wave 1 (parallel)**: Dispatch subagents:
-   - **5A** (`phase-5a-viewinspector.md`, sonnet, 40 turns) — ViewInspector structure + accessibility tests.
-   - **5B** (`phase-5b-snapshot.md`, sonnet, 40 turns) — Snapshot tests for all Figma variants.
-4. **Wave 2 (conditional)**: **5C** (`phase-5c-unit.md`, sonnet, 30 turns) — Unit tests. Only if component has ViewModel/model logic. N/A for pure View + Configuration.
+   - **5A** (`phase-5a-viewinspector.md`, sonnet, 40 turns)  -  ViewInspector structure + accessibility tests.
+   - **5B** (`phase-5b-snapshot.md`, sonnet, 40 turns)  -  Snapshot tests for all Figma variants.
+4. **Wave 2 (conditional)**: **5C** (`phase-5c-unit.md`, sonnet, 30 turns)  -  Unit tests. Only if component has ViewModel/model logic. N/A for pure View + Configuration.
 5. **TEST EXECUTION (combined)**: Run all tests via a SINGLE xcodebuild invocation:
    a. **Switch to local common dependency**: In `{repos.components.path}/Package.swift`, comment out the `.package(url: "...{project.slug}-common...", ...)` line and add `.package(path: "../{project.slug}-common"),` below it. This is needed because the SPM package resolves dependencies from remote git, but Phase 2 adds identifiers/keys to the local editable copy.
    b. **Run ALL tests in a single invocation**:
@@ -499,10 +499,10 @@ Also update IMPLEMENTATION_HISTORY.md with the standard phase status, gates, and
 
 > **LEAN MODE:** If `lean_mode` is `true` in `_perf_tracker.json`:
 > - Run **Phase 6 only** (sequentially, after Phase 4).
-> - **SKIP Phase 7 entirely.** Record as `"status": "SKIPPED"` in the tracker and append `| Phase 7 (Wiki) | — | ⏭️ lean | ... |` to IMPLEMENTATION_HISTORY.md.
+> - **SKIP Phase 7 entirely.** Record as `"status": "SKIPPED"` in the tracker and append `| Phase 7 (Wiki) |  -  | ⏭️ lean | ... |` to IMPLEMENTATION_HISTORY.md.
 > - Do NOT touch the wiki submodule.
 
-> **PERF CHANGE:** Phase 6 (Code Connect) and Phase 7 (Wiki Markdown generation) have NO dependency on each other. Phase 7 reads component Swift files + FIGMA.md + pass3 artifacts — all completed in Phase 4. Phase 6 publishes to Figma. Running them in parallel saves ~5-10 minutes.
+> **PERF CHANGE:** Phase 6 (Code Connect) and Phase 7 (Wiki Markdown generation) have NO dependency on each other. Phase 7 reads component Swift files + FIGMA.md + pass3 artifacts  -  all completed in Phase 4. Phase 6 publishes to Figma. Running them in parallel saves ~5-10 minutes.
 
 After Phase 5 completes (or Phase 4 in lean mode):
 
@@ -524,7 +524,7 @@ After Phase 5 completes (or Phase 4 in lean mode):
      subagent_type: "general-purpose",
      model: sonnet,
      max_turns: 30,
-     prompt: {standard Phase 7 dispatch prompt — include wikiPath in context}
+     prompt: {standard Phase 7 dispatch prompt  -  include wikiPath in context}
    )
    ```
 
@@ -549,24 +549,24 @@ After Phase 5 completes (or Phase 4 in lean mode):
 
 When building the `Previous Phase Artifacts` section of the dispatch prompt, list artifacts in this order. Compact artifacts go FIRST so the subagent establishes context before large files consume the context window.
 
-Every phase must be independently operable from a clean session — all artifacts remain accessible on disk. This table is a **read-ordering preference**, not a prohibition.
+Every phase must be independently operable from a clean session  -  all artifacts remain accessible on disk. This table is a **read-ordering preference**, not a prohibition.
 
 | Phase | Read FIRST (compact) | Read SECOND (if detail needed) |
 |-------|---------------------|-------------------------------|
 | 2A-2D | `pass1/component_summary.json` | `pass1/design_context_response.json`, `pass1/component_properties.json` |
-| 3A | `pass1/component_summary.json`, `IMPLEMENTATION_HISTORY.md` | — |
+| 3A | `pass1/component_summary.json`, `IMPLEMENTATION_HISTORY.md` |  -  |
 | 3B | `pass1/component_summary.json`, `pass1/variable_defs_response.json` | `pass1/design_context_response.json` (for binding context) |
-| 3C | `pass1/component_summary.json`, `pass1/code_connect_map_response.json` | — |
+| 3C | `pass1/component_summary.json`, `pass1/code_connect_map_response.json` |  -  |
 | 3D | `pass1/component_summary.json`, `pass1/component_properties.json` | `pass1/design_context_response.json`, `pass1/metadata_response.xml` |
-| 3E | `pass1/component_summary.json`, `pass1/design_context_assets.txt` | — |
+| 3E | `pass1/component_summary.json`, `pass1/design_context_assets.txt` |  -  |
 | 3F | `pass1/component_summary.json`, `pass2/utility_*.md` | `pass1/design_context_response.json` |
-| 3G | `pass1/component_summary.json`, `pass3/04b_component_architecture.md` | — |
+| 3G | `pass1/component_summary.json`, `pass3/04b_component_architecture.md` |  -  |
 | 4A | `pass3/04b_component_architecture.md`, `pass3/05_complexity.md`, `pass3/00_property_coverage.json` | `pass1/component_summary.json` |
 | 4B | `pass1/component_summary.json`, `pass3/00_property_coverage.json`, `pass3/07_implementation_spec.md`, `pass3/02_token_mapping.md`, `pass3/04b_component_architecture.md`, `pass3/04_patterns.md`, `pass3/03_nested_components.md`, `pass3/08_utility_integration.md`, `pass1/screenshot.png` | `pass1/design_context_response.json` (for complex layout detail) |
 | 4C | `pass3/07_implementation_spec.md`, `pass3/04b_component_architecture.md`, `pass3/00_property_coverage.json` | `pass1/component_summary.json` |
 | 4D | `{componentLocation}/{ComponentName}.swift`, `{componentLocation}/{ComponentName}Configuration.swift` (if exists) | `pass3/04_patterns.md` |
-| 4E | `{componentLocation}/{ComponentName}Configuration.swift`, `{componentLocation}/{ComponentName}.swift` | — |
-| 6 | `pass1/component_properties.json`, `{sourceLocation}/FIGMA.md`, `{sourceLocation}/{componentName}.swift` | — |
+| 4E | `{componentLocation}/{ComponentName}Configuration.swift`, `{componentLocation}/{ComponentName}.swift` |  -  |
+| 6 | `pass1/component_properties.json`, `{sourceLocation}/FIGMA.md`, `{sourceLocation}/{componentName}.swift` |  -  |
 
 ---
 
@@ -591,7 +591,7 @@ When `$ARGUMENTS` is `status`:
 2. For each found IMPLEMENTATION_HISTORY.md, look for a sibling `_perf_tracker.json` in the same directory.
 3. If `_perf_tracker.json` exists:
    a. Read it and display the full timing/reliability summary (same format as Final Summary).
-   b. If IMPLEMENTATION_HISTORY.md is missing the `## Workflow Summary` section but the tracker shows all phases completed, **generate and append the summary now** — this recovers from context loss.
+   b. If IMPLEMENTATION_HISTORY.md is missing the `## Workflow Summary` section but the tracker shows all phases completed, **generate and append the summary now**  -  this recovers from context loss.
 4. If `_perf_tracker.json` does not exist, fall back to displaying: component name, current phase, last gate, last updated (from IMPLEMENTATION_HISTORY.md only).
 
 ---
@@ -618,8 +618,8 @@ Derive confluencePath from artifactPath: replace `Figma/Components` with `Conflu
 
 When the last phase completes (or workflow is aborted/skipped):
 
-1. **Read `{artifactPath}/_perf_tracker.json`** — this is the single source of truth for all timing and reliability data.
-2. **Read IMPLEMENTATION_HISTORY.md** `## Phase Timings` table — as a cross-check.
+1. **Read `{artifactPath}/_perf_tracker.json`**  -  this is the single source of truth for all timing and reliability data.
+2. **Read IMPLEMENTATION_HISTORY.md** `## Phase Timings` table  -  as a cross-check.
 3. **Compute totals** from the tracker file (not from memory).
 4. **Output the summary** to the user AND **append it to IMPLEMENTATION_HISTORY.md**.
 
@@ -633,9 +633,9 @@ When the last phase completes (or workflow is aborted/skipped):
 ## Workflow Summary
 
 - Component: {componentName}
-- Lean Mode: {yes/no — from tracker `lean_mode` field}
-- Phases Executed: {list of completed phases — from tracker}
-- Phases Skipped: {list, if any — from tracker. In lean mode: Phase 5, Phase 7}
+- Lean Mode: {yes/no  -  from tracker `lean_mode` field}
+- Phases Executed: {list of completed phases  -  from tracker}
+- Phases Skipped: {list, if any  -  from tracker. In lean mode: Phase 5, Phase 7}
 - Total Elapsed Time: {HH:MM:SS} (from tracker workflow_start to last phase end)
 - Artifacts: {artifactPath}
 - Component Location: {componentLocation}
@@ -655,12 +655,12 @@ When the last phase completes (or workflow is aborted/skipped):
 
 ### Reliability
 - First-pass success: {phases_without_halt}/{total_phases} phases ({percentage}%)
-- HALTs: {halt_count from tracker} — {halt_log entries}
+- HALTs: {halt_count from tracker}  -  {halt_log entries}
 - Retries: {retry_count from tracker}
 
 ### Bottlenecks
-⚠️ Phase {N} took {actual} (expected ~{expected}) — {reason if known from halt_log, else "investigate"}
-{If no bottlenecks: "None — all phases within expected duration."}
+⚠️ Phase {N} took {actual} (expected ~{expected})  -  {reason if known from halt_log, else "investigate"}
+{If no bottlenecks: "None  -  all phases within expected duration."}
 ```
 
 **Expected Phase Durations** (used for bottleneck detection):
@@ -700,7 +700,7 @@ The `status` command reads `_perf_tracker.json`, computes the summary, and appen
 | **Combined test execution** | Single `xcodebuild test` with multiple `--only-testing:` instead of 2 separate build+test cycles |
 | **Simulator pre-warm** | Boots iOS Simulator in background during test file generation, eliminating cold-start latency |
 | **Phase 6 ∥ 7 parallelism** | Code Connect publish + Wiki Markdown generation run simultaneously |
-| **Phase 4 registry finalize** | Calls `phase4-finalize.py` after BUILD to mark `implemented: true` — was missing in original routing, caused gray implementation flags on issue board |
-| **Disk-persisted tracking** | All timing, HALT, and retry data written to `_perf_tracker.json` after every phase — survives context loss |
-| **Incremental history writes** | Phase timing rows appended to IMPLEMENTATION_HISTORY.md after each phase — no data lost if conversation cuts |
-| **Bottleneck detection** | Flags phases exceeding 2× expected duration — reconstructable from `_perf_tracker.json` at any time |
+| **Phase 4 registry finalize** | Calls `phase4-finalize.py` after BUILD to mark `implemented: true`  -  was missing in original routing, caused gray implementation flags on issue board |
+| **Disk-persisted tracking** | All timing, HALT, and retry data written to `_perf_tracker.json` after every phase  -  survives context loss |
+| **Incremental history writes** | Phase timing rows appended to IMPLEMENTATION_HISTORY.md after each phase  -  no data lost if conversation cuts |
+| **Bottleneck detection** | Flags phases exceeding 2× expected duration  -  reconstructable from `_perf_tracker.json` at any time |