@tekyzinc/gsd-t 2.34.12 → 2.36.10

package/README.md

@@ -20,7 +20,7 @@ A methodology for reliable, parallelizable development using Claude Code with op
 npx @tekyzinc/gsd-t install
 ```
 
-This installs 44 GSD-T commands + 4 utility commands (48 total) to `~/.claude/commands/` and the global CLAUDE.md to `~/.claude/CLAUDE.md`. Works on Windows, Mac, and Linux.
+This installs 44 GSD-T commands + 5 utility commands (49 total) to `~/.claude/commands/` and the global CLAUDE.md to `~/.claude/CLAUDE.md`. Works on Windows, Mac, and Linux.
 
 ### Start Using It
 
@@ -175,6 +175,7 @@ This will replace changed command files, back up your CLAUDE.md if customized, a
 | `/user:branch` | Create and switch to a new git branch | Manual |
 | `/user:checkin` | Auto-bump version, stage, commit, and push | Manual |
 | `/user:Claude-md` | Reload CLAUDE.md directives mid-session | Manual |
+| `/global-change` | Apply file changes across all registered GSD-T projects | Manual |
 
 ---
 

package/commands/global-change.md

@@ -0,0 +1,205 @@
+# GSD-T: Global Change — Apply Changes Across All GSD-T Projects
+
+You are applying a file-level change to every GSD-T project registered in `.claude/.gsd-t-projects`. This is a **global** slash command (installed to `~/.claude/commands/`) that enables bulk updates to project configuration, CLAUDE.md files, templates, and any other files that need to stay consistent across the GSD-T ecosystem.
+
+## Syntax
+
+```
+/global-change <operation> <relative-path/filename> [arguments]
+```
+
+### Operations
+
+| Operation | Arguments | Description |
+|-----------|-----------|-------------|
+| `copy`    | `<relative-path/filename>` | Copy file from the GSD-T package directory to the same relative path in all projects |
+| `insert`  | `<relative-path/filename> <content>` | Append content to the specified file in all projects |
+| `update`  | `<relative-path/filename> <old_content> %%REPLACE_WITH%% <new_content>` | Find `old_content` in the file and replace it with `new_content` in all projects |
+| `delete`  | `<relative-path/filename>` | Delete the specified file from all projects |
+
+### Examples
+
+```
+/global-change copy .gsd-t/templates/contract.md
+
+/global-change insert .gsd-t/config.json {"newSetting": true}
+
+/global-change update CLAUDE.md
+- `model: haiku` — mechanical tasks
+- `model: sonnet` (default) — reasoning tasks
+%%REPLACE_WITH%%
+- `model: haiku` — mechanical tasks (same as now)
+- `model: sonnet` — mid-tier reasoning: routine code changes, standard refactors, test writing, straightforward synthesis
+- `model: opus` — high-stakes reasoning: architecture decisions, security analysis, complex debugging, cross-module refactors, quality judgment on critical paths
+
+/global-change delete .gsd-t/deprecated-template.md
+```
+
+## Step 1: Load the Project Registry
+
+Read `~/.claude/.gsd-t-projects`. This file contains one absolute project path per line.
+
+```
+# Example .gsd-t-projects
+C:/Users/david/MyNextListen
+C:/Users/david/TimeTracking
+C:/Users/david/tekyz-ai-copilot
+```
+
+If the file does not exist or is empty:
+- STOP. Tell the user: "No GSD-T projects registered. Register projects by adding their absolute paths (one per line) to `~/.claude/.gsd-t-projects`."
+- Do NOT proceed.
+
+Parse the file:
+- Skip blank lines
+- Skip lines starting with `#` (comments)
+- Trim whitespace from each path
+- Store as `PROJECT_PATHS[]`
+
+## Step 2: Parse Arguments
+
+Extract from $ARGUMENTS:
+1. **operation** — first word: `copy`, `insert`, `update`, or `delete`
+2. **relative-path/filename** — second token: the file path relative to each project root (e.g., `CLAUDE.md`, `.gsd-t/config.json`, `docs/architecture.md`)
+3. **Remaining arguments** depend on the operation:
+   - `copy` — no additional arguments
+   - `insert` — everything after the filename is the content to append
+   - `update` — everything after the filename is split by the `%%REPLACE_WITH%%` delimiter into **old_content** (before) and **new_content** (after)
+   - `delete` — no additional arguments
+
+### Parsing the `update` Delimiter
+
+For `update` operations, the content portion (everything after the filename) MUST contain the literal string `%%REPLACE_WITH%%` on its own line. Split on this delimiter:
+- **old_content** = trimmed text before `%%REPLACE_WITH%%` — the exact text to find in the target file
+- **new_content** = trimmed text after `%%REPLACE_WITH%%` — the replacement text
+
+If the delimiter is missing, STOP and show the user the correct syntax:
+```
+Usage: /global-change update <file> <old content> %%REPLACE_WITH%% <new content>
+```
+
+### Validation Rules
+
+- If operation is missing or not one of `copy|insert|update|delete` → STOP, show usage syntax
+- If relative-path/filename is missing → STOP, show usage syntax
+- If operation is `insert` and no content is provided → STOP, tell the user content is required
+- If operation is `update` and `%%REPLACE_WITH%%` delimiter is missing → STOP, show correct syntax
+- If operation is `update` and either old_content or new_content is empty → STOP, both sides of the delimiter are required
+- If operation is `copy` and the source file does not exist in the GSD-T package directory → STOP, tell the user the source file was not found
+
+### Determine GSD-T Package Directory
+
+The source directory for `copy` operations is the installed GSD-T package location. Resolve it by checking (in order):
+1. The directory containing this command file (walk up to the package root)
+2. `node_modules/@tekyz/gsd-t/` relative to the global npm prefix
+3. Ask the user if neither resolves
+
+## Step 3: Dry Run — Scan All Projects First
+
+Before making any changes, scan every project to preview what will happen. For each project in `PROJECT_PATHS[]`:
+
+### For `copy`:
+- Check if the target file already exists → note "will overwrite" or "will create"
+
+### For `insert`:
+- Check if the target file exists → note "will append to existing" or "will create new file"
+
+### For `update`:
+- Read the target file
+- Search for `old_content` in the file contents
+- If found → note "match found — will replace"
+- If NOT found → note "⚠ NO MATCH — will skip" (do NOT modify files where the old content isn't found)
+- If found multiple times → note "⚠ MULTIPLE MATCHES ([count]) — will replace all occurrences"
+
+### For `delete`:
+- Check if the target file exists → note "will delete" or "will skip (not found)"
+
+### Display the dry run summary:
+
+```
+Global Change — Pre-flight Summary
+Operation:  [operation]
+Target:     [relative-path/filename]
+Projects:   [N] registered
+
+[For update — show old/new content preview]
+
+Dry run results:
+  [status] [project-name] — [description]
+  [status] [project-name] — [description]
+```
+
+**Level 3 (Full Auto)**: If ALL projects show clean matches (no warnings), auto-proceed to Step 4 without asking. If ANY project shows a warning (no match, multiple matches), pause and ask.
+
+**Level 1-2**: Always pause and ask for confirmation.
+
+## Step 4: Execute Changes
+
+For each project that passed the dry run:
+
+### `copy`
+1. Determine the target: `{PROJECT_PATH}/{relative-path/filename}`
+2. If the target directory does not exist → create it (including intermediate directories)
+3. Copy the source file to the target, overwriting if it exists
+
+### `insert`
+1. Determine the target: `{PROJECT_PATH}/{relative-path/filename}`
+2. If the target directory does not exist → create it (including intermediate directories)
+3. If the target file does not exist → create it with the provided content
+4. If the target file exists → append a newline + the provided content to the end
+
+### `update`
+1. Determine the target: `{PROJECT_PATH}/{relative-path/filename}`
+2. If the file does not exist → skip
+3. Read the file contents
+4. Search for `old_content` (exact string match, whitespace-sensitive)
+5. If NOT found → skip
+6. If found → replace ALL occurrences of `old_content` with `new_content`
+7. Write the modified contents back to the file
+
+### `delete`
+1. Determine the target: `{PROJECT_PATH}/{relative-path/filename}`
+2. If the target file does not exist → skip
+3. If the target file exists → delete it
+4. Do NOT delete the parent directory even if empty
+
+### Error Handling
+- On failure, record: `FAILED: {error message}`
+- Never abort the entire run because one project failed — continue to the next
+
+## Step 5: Report Results
+
+Display the final summary:
+
+```
+Global Change — Results
+Operation:  [operation] [relative-path/filename]
+Succeeded:  [N] / [total] projects
+Failed:     [N]
+Skipped:    [N]
+
+  [status] [project-name] — [result]
+  [status] [project-name] — [result]
+```
+
+Status icons:
+- `✓` — success
+- `⊘` — skipped (file not found, no match, etc.)
+- `✗` — failed with error
+
+If there were failures, list them with actionable error messages.
+
+## Notes
+
+- **Relative paths use forward slashes** regardless of OS
+- **No glob patterns** — operates on a single file per invocation
+- **Content for `insert`** can be provided inline or pasted in the user's message
+- **Content for `update`** uses the `%%REPLACE_WITH%%` delimiter — old_content match is exact and whitespace-sensitive
+- **Project names in logs** are derived from the last segment of the project path
+- **The `.gsd-t-projects` file** is maintained by `gsd-t init` (auto-registers) and `gsd-t update-all` (reads)
+
+$ARGUMENTS
+
+## Auto-Clear
+
+All work is committed to project files. Execute `/clear` to free the context window for the next command.

package/commands/gsd-t-feature.md

@@ -22,6 +22,14 @@ Read everything:
 
 Build a mental model of: "How does this codebase work today?"
 
+**Multi-Client Architecture Check**: Before moving to Step 2, identify whether the project has or will have multiple consumer surfaces:
+- Look for directories: `web/`, `mobile/`, `app/`, `cli/`, `client/`, `frontend/`
+- Look for split route files: `routes/web.js`, `routes/mobile.js`, `routes/api/v1/`, `routes/api/v2/`
+- Check package.json scripts for `build:web`, `build:mobile`, `start:mobile`, etc.
+- Check `.gsd-t/scan/quality.md` (if exists) for the "Consumer Surfaces Detected" table
+
+Note what you find — this informs Step 3's Multi-Consumer Check and Step 4's milestone ordering.
+
 ## Step 2: Understand the Feature
 
 From $ARGUMENTS and conversation:
@@ -102,6 +110,14 @@ Produce a combined analysis:
 - {where this feature could break existing functionality}
 - {complex integration points}
 - {performance concerns}
+
+### Multi-Consumer Check
+- Consumer surfaces that exist or will exist after this feature: {list}
+- Does this feature add a new consumer surface? {yes/no}
+- If yes: backend operations this new surface needs: {list}
+- Of those, how many are already implemented for an existing surface? {list any matches}
+- SharedCore extraction candidates (operations needed by 2+ surfaces): {list or "none found"}
+- SharedCore milestone required? {yes — if 2+ candidates found | no — if none}
 ```
 
 ## Step 4: Decompose into Milestones
@@ -121,6 +137,7 @@ Apply these sequencing rules:
 3. **Existing contract updates early**: If existing contracts change, update and verify them before building new code against them
 4. **New functionality before integration**: Build the new thing, then wire it into existing flows
 5. **Migration/backfill as its own milestone**: If existing data needs transformation, isolate that work
+6. **SharedCore before new consumer surfaces**: If the feature adds a new consumer surface (web, mobile, CLI) AND SharedCore candidates were identified in Step 3's Multi-Consumer Check, add a SharedCore milestone BEFORE the new client's milestone. The SharedCore milestone extracts shared operations into a reusable backend domain — the new client's API calls SharedCore functions, it does not duplicate them.
 
 ### Write the Feature Roadmap
 

package/commands/gsd-t-help.md

@@ -62,6 +62,7 @@ UTILITIES                                                              Manual
   version-update      Update GSD-T package to latest version
   version-update-all  Update GSD-T package + all registered projects
   triage-and-merge    Auto-review, merge, and publish GitHub branches
+  global-change       Apply file changes across all registered GSD-T projects
 
 BACKLOG                                                                Manual
 ───────────────────────────────────────────────────────────────────────────────
@@ -347,6 +348,14 @@ Use these when user asks for help on a specific command:
 - **Use when**: Collaborators have pushed branches and you want to batch-review, merge, and publish without manual per-branch ceremony
 - **Features**: 3-tier impact scoring (auto-merge / review / skip), publish gate (auto in Level 3, prompted otherwise), conflict detection, sensitive file detection
 
+### global-change
+- **Summary**: Apply file changes (copy/insert/update/delete) across all registered GSD-T projects
+- **Auto-invoked**: No
+- **Files**: Reads `~/.claude/.gsd-t-projects`; modifies target file in each registered project
+- **Use when**: You need to make the same change to CLAUDE.md, contracts, templates, or config across multiple projects at once
+- **Operations**: `copy` (file from GSD-T package), `insert` (append content), `update` (find/replace with `%%REPLACE_WITH%%` delimiter), `delete` (remove file)
+- **Features**: Dry run preview, per-project match validation, parallel execution, skip-on-no-match safety
+
 ### backlog-add
 - **Summary**: Capture a new backlog item with auto-categorization
 - **Auto-invoked**: No

package/commands/gsd-t-partition.md

@@ -8,6 +8,8 @@ Read these files in order:
 1. `CLAUDE.md` — project conventions and context
 2. `.gsd-t/progress.md` — current state (if exists)
 3. `docs/` — all available documentation (requirements, architecture, schema, design)
+4. `.gsd-t/scan/quality.md` (if exists) — extract the "Consumer Surfaces Detected" and "Shared Service Candidates" tables. These pre-populate Step 1.6 with scan-discovered data and eliminate re-research.
+5. `.gsd-t/contracts/shared-services-contract.md` (if exists) — a SharedCore domain was previously identified. Its listed operations are pre-confirmed shared and carry forward automatically to Step 1.6.2.
 
 If `.gsd-t/` doesn't exist, create the full directory structure:
 ```
@@ -98,7 +100,11 @@ For each surface that will consume this system, capture:
 
 **Surface types**: `web`, `mobile`, `cli`, `external-api`, `admin`, `background-worker`, `other`
 
-If only one surface exists → mark "Single consumer — SharedCore not needed" and proceed to Step 2.
+**Existing System Check**: This milestone may be adding a NEW surface to a system that already has existing consumer surfaces. Before concluding surface enumeration, scan `.gsd-t/progress.md` completed milestones and look for directories or route files indicating prior client surfaces (`web/`, `mobile/`, `app/`, `cli/`, `client/`, `routes/web.js`, `routes/mobile.js`). Add any discovered existing surfaces to the table above.
+
+> ⚠️ **New-client signal**: If this milestone adds a consumer surface to a system that already has one or more other consumer surfaces, SharedCore evaluation is MANDATORY regardless of shared operation count.
+
+If only one surface exists and no prior surfaces were found → mark "Single consumer — SharedCore not needed" and proceed to Step 2.
 
 ---
 
@@ -123,7 +129,7 @@ Compare the "Operations Needed" column across all surfaces. Flag every operation
 
 ### 1.6.3 — Auto-Suggest SharedCore Domain
 
-**If 3 or more shared operations exist:**
+**If 2 or more shared operations exist, OR if this milestone adds a new consumer surface to a system that already has other surfaces (detected in the Existing System Check above):**
 
 > ⚠️ **SharedCore recommended** — {N} operations are needed by {M} consumer surfaces.
 > A `shared-core` domain will be added to own these functions.
@@ -134,7 +140,7 @@ Add `shared-core` to the domain list before running Step 2. The `shared-core` do
 - Consumed by: all surface-specific adapter domains
 - Contract: `shared-services-contract.md` (use the template from `templates/shared-services-contract.md`)
 
-**If fewer than 3 shared operations exist:**
+**If only 1 shared operation exists AND this is not a new-client-to-existing-system scenario:**
 
 > ℹ️ {N} shared operations found. Inline sharing is sufficient — no separate SharedCore domain needed. Document shared functions in the relevant domain's constraints.md.
 

package/commands/gsd-t-plan.md

@@ -18,6 +18,13 @@ Read ALL of these:
 
 ## Step 2: Create Task Lists Per Domain
 
+### SharedCore-First Pre-Check
+
+Before writing any domain task lists:
+1. Does `.gsd-t/contracts/shared-services-contract.md` exist?
+   - **YES**: A `shared-core` domain has been identified. Plan its tasks first. All client-surface domains that consume SharedCore operations are BLOCKED BY shared-core until its tasks complete. Use `BLOCKED BY shared-core Task {N}` in the relevant client domain task lists.
+   - **NO**: Proceed. The Cross-Domain Duplicate Operation Scan (below) will catch any shared operations missed during partition.
+
 For each domain, write `.gsd-t/domains/{domain-name}/tasks.md`:
 
 ```markdown
@@ -81,6 +88,19 @@ For each operation in each domain's task list:
 
 > ✅ No duplicate operations detected across domains.
 
+### SharedCore Contract Compliance Check
+
+If `.gsd-t/contracts/shared-services-contract.md` exists, run a second pass:
+
+For each client-surface domain's task list, compare task operations against the SharedCore contract's "Shared Operations" table. Flag any task that implements an operation already owned by SharedCore:
+
+> ⚠️ **SharedCore contract violation** — the following tasks reimplement operations owned by SharedCore:
+> - {domain} Task {N}: implements `{operation}` — already owned by SharedCore per shared-services-contract.md
+>
+> Fix: Change these tasks to CALL the SharedCore function rather than implementing it independently.
+
+If no violations: `✅ All client domains reference SharedCore correctly.`
+
 ---
 
 ### REQ Traceability

package/docs/GSD-T-README.md

@@ -122,6 +122,7 @@ GSD-T reads all state files and tells you exactly where you left off.
 | `/user:gsd-t-version-update` | Update GSD-T to latest version | Manual |
 | `/user:gsd-t-version-update-all` | Update GSD-T + all registered projects | Manual |
 | `/user:gsd-t-triage-and-merge` | Auto-review, merge, and publish GitHub branches | Manual |
+| `/global-change` | Apply file changes (copy/insert/update/delete) across all GSD-T projects | Manual |
 
 ### Backlog Management
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tekyzinc/gsd-t",
-  "version": "2.34.12",
+  "version": "2.36.10",
   "description": "GSD-T: Contract-Driven Development for Claude Code — 48 slash commands with real-time agent dashboard, execution intelligence, backlog management, impact analysis, test sync, milestone archival, and PRD generation",
   "author": "Tekyz, Inc.",
   "license": "MIT",

package/scripts/gsd-t-dashboard.html

@@ -23,43 +23,33 @@ body{background:var(--bg);color:var(--text);font-family:var(--font);font-size:12
   font-size:10px;border:1px solid;}
 .status.live{background:var(--green-bg);border-color:var(--green);color:var(--green);}
 .status.wait{background:var(--yellow-bg);border-color:var(--yellow);color:var(--yellow);}
-.dot{width:6px;height:6px;border-radius:50%;background:currentColor;
-  animation:pdot 1.5s ease-in-out infinite;}
+.dot{width:6px;height:6px;border-radius:50%;background:currentColor;animation:pdot 1.5s ease-in-out infinite;}
 @keyframes pdot{0%,100%{opacity:1}50%{opacity:.3}}
-.hright{margin-left:auto;color:var(--muted);font-size:11px;}
-.main{display:flex;flex:1;overflow:hidden;}
-.garea{flex:1;position:relative;background:var(--bg);}
-.rfwrap{width:100%;height:100%;}
-.react-flow__background{background:var(--bg);}
-.react-flow__node{font-family:var(--font);font-size:11px;}
+.hright{margin-left:auto;color:var(--muted);font-size:11px;}.main{display:flex;flex:1;overflow:hidden;}
+.garea{flex:1;position:relative;background:var(--bg);}.rfwrap{width:100%;height:100%;}
+.react-flow__background{background:var(--bg);}.react-flow__node{font-family:var(--font);font-size:11px;}
 .agent-node{background:var(--surface);border:1px solid var(--border);border-radius:6px;
   padding:8px 12px;min-width:120px;text-align:center;}
-.agent-node.success{border-color:var(--green);background:var(--green-bg);}
-.agent-node.failure{border-color:var(--red);background:var(--red-bg);}
-.agent-node.learning,.agent-node.deferred{border-color:var(--yellow);background:var(--yellow-bg);}
-.agent-node.session{border-color:var(--blue);background:var(--blue-bg);}
-.node-id{color:var(--text);font-weight:500;overflow:hidden;text-overflow:ellipsis;white-space:nowrap;max-width:140px;}
-.node-cnt{color:var(--muted);font-size:9px;margin-top:2px;}
+.agent-node.success{border-color:var(--green);background:var(--green-bg);}.agent-node.failure{border-color:var(--red);background:var(--red-bg);}
+.agent-node.learning,.agent-node.deferred{border-color:var(--yellow);background:var(--yellow-bg);}.agent-node.session{border-color:var(--blue);background:var(--blue-bg);}
+.node-id{color:var(--text);font-weight:500;overflow:hidden;text-overflow:ellipsis;white-space:nowrap;max-width:140px;}.node-cnt{color:var(--muted);font-size:9px;margin-top:2px;}
 .sidebar{width:300px;background:var(--surface);border-left:1px solid var(--border);
   display:flex;flex-direction:column;overflow:hidden;}
 .sb-hdr{padding:10px 12px;border-bottom:1px solid var(--border);color:var(--muted);
   font-size:10px;text-transform:uppercase;letter-spacing:.8px;flex-shrink:0;}
-.feed{flex:1;overflow-y:auto;padding:8px;}
-.feed::-webkit-scrollbar{width:4px;}
-.feed::-webkit-scrollbar-thumb{background:var(--border);border-radius:2px;}
+.feed{flex:1;overflow-y:auto;padding:8px;}.feed::-webkit-scrollbar{width:4px;}.feed::-webkit-scrollbar-thumb{background:var(--border);border-radius:2px;}
 .ev{border-radius:4px;padding:6px 8px;margin-bottom:5px;border-left:3px solid var(--border);
   background:#1c2128;}
-.ev.success{border-left-color:var(--green);}
-.ev.failure{border-left-color:var(--red);}
-.ev.learning,.ev.deferred{border-left-color:var(--yellow);}
-.ev-type{font-weight:500;color:var(--text);font-size:11px;}
-.ev-cmd{color:var(--blue);font-size:10px;margin-top:1px;}
-.ev-ts{color:var(--muted);font-size:9px;margin-top:2px;}
+.ev.success{border-left-color:var(--green);}.ev.failure{border-left-color:var(--red);}.ev.learning,.ev.deferred{border-left-color:var(--yellow);}
+.ev-type{font-weight:500;color:var(--text);font-size:11px;}.ev-cmd{color:var(--blue);font-size:10px;margin-top:1px;}.ev-ts{color:var(--muted);font-size:9px;margin-top:2px;}
 .badge{display:inline-block;font-size:9px;padding:1px 5px;border-radius:3px;font-weight:bold;margin-left:4px;}
-.badge.success{background:var(--green-bg);color:var(--green);}
-.badge.failure{background:var(--red-bg);color:var(--red);}
-.badge.learning,.badge.deferred{background:var(--yellow-bg);color:var(--yellow);}
+.badge.success{background:var(--green-bg);color:var(--green);}.badge.failure{background:var(--red-bg);color:var(--red);}.badge.learning,.badge.deferred{background:var(--yellow-bg);color:var(--yellow);}
 .noevents{color:var(--muted);font-size:11px;padding:12px;text-align:center;}
+.models{padding:8px 12px;border-bottom:1px solid var(--border);flex-shrink:0;}
+.model-row{display:flex;align-items:center;gap:8px;margin-bottom:4px;font-size:11px;}
+.model-name{width:50px;color:var(--text);font-weight:500;}.model-bar-bg{flex:1;height:8px;background:var(--bg);border-radius:4px;overflow:hidden;}
+.model-bar{height:100%;border-radius:4px;transition:width .3s ease;}.model-bar.opus{background:var(--blue);}.model-bar.sonnet{background:var(--green);}.model-bar.haiku{background:var(--yellow);}
+.model-cnt{color:var(--muted);font-size:10px;min-width:20px;text-align:right;}
 </style>
 </head>
 <body>
@@ -71,6 +61,8 @@ body{background:var(--bg);color:var(--text);font-family:var(--font);font-size:12
 <div class="main">
   <div class="garea"><div id="rf-root" class="rfwrap"></div></div>
   <div class="sidebar">
+    <div class="sb-hdr">Models Invoked</div>
+    <div id="models" class="models"><div class="noevents">No model data yet</div></div>
     <div class="sb-hdr">Live Event Feed</div>
     <div id="feed" class="feed"><div class="noevents">Waiting for events...</div></div>
   </div>
@@ -109,12 +101,16 @@ function Dashboard(){
   const [edges,setEdges,onEdgesChange]=useEdgesState([]);
   const [events,setEvents]=useState([]);
   const agentMap=useRef({});
+  const modelCounts=useRef({});
 
   const processEvent=useCallback((ev)=>{
     setEvents(prev=>{
       const next=[ev,...prev];
       return next.length>MAX_EVENTS?next.slice(0,MAX_EVENTS):next;
     });
+    const m=ev.model||(ev.event_type==='session_start'&&ev.reasoning?ev.reasoning.match(/opus|sonnet|haiku/i):null);
+    const mName=m?(typeof m==='string'?m:m[0]).toLowerCase():null;
+    if(mName){modelCounts.current[mName]=(modelCounts.current[mName]||0)+1;}
     if(!ev.agent_id)return;
     const id=ev.agent_id;
     const prev=agentMap.current[id]||{count:0,outcome:null,parent:null,nodeType:null,firstTs:null};
@@ -167,14 +163,18 @@ function Dashboard(){
 
   useEffect(()=>{
     document.getElementById('ev-count').textContent=`${events.length} event${events.length!==1?'s':''}`;
+    const mp=document.getElementById('models'),mc=modelCounts.current,mEntries=Object.entries(mc).sort((a,b)=>b[1]-a[1]);
+    if(mEntries.length){const maxC=Math.max(...mEntries.map(e=>e[1]));
+      mp.innerHTML=mEntries.map(([n,c])=>`<div class="model-row"><span class="model-name">${n}</span><div class="model-bar-bg"><div class="model-bar ${n}" style="width:${Math.round((c/maxC)*100)}%"></div></div><span class="model-cnt">${c}</span></div>`).join('');}
     const feed=document.getElementById('feed');
     if(!events.length){feed.innerHTML='<div class="noevents">Waiting for events...</div>';return;}
     feed.innerHTML=events.slice(0,50).map(ev=>{
       const oc=outcomeClass(ev.outcome);
       const ts=ev.ts?new Date(ev.ts).toLocaleTimeString():'';
       const cmd=ev.command||ev.phase||'';
+      const evModel=ev.model||null;
       return`<div class="ev${oc?' '+oc:''}">
-        <div class="ev-type">${ev.event_type||'event'}${oc?`<span class="badge ${oc}">${ev.outcome}</span>`:''}</div>
+        <div class="ev-type">${ev.event_type||'event'}${evModel?` <span style="color:var(--muted);font-size:9px">[${evModel}]</span>`:''}${oc?`<span class="badge ${oc}">${ev.outcome}</span>`:''}</div>
         ${cmd?`<div class="ev-cmd">${cmd}</div>`:''}
         ${ev.reasoning?`<div class="ev-ts" style="color:var(--muted)">${ev.reasoning.slice(0,60)}</div>`:''}
         <div class="ev-ts">${ts}</div>

package/scripts/gsd-t-event-writer.js

@@ -78,6 +78,7 @@ function buildEvent(args) {
     trace_id: nullify(args["trace-id"]),
     reasoning: nullify(args["reasoning"]),
     outcome: nullify(args["outcome"]),
+    model: nullify(args["model"]),
   };
 }
 

package/templates/CLAUDE-global.md

@@ -76,6 +76,7 @@ PROJECT or FEATURE or SCAN
 | `/user:branch` | Create and switch to a new git branch |
 | `/user:checkin` | Auto-bump version, stage, commit, and push |
 | `/user:Claude-md` | Reload and apply CLAUDE.md directives |
+| `/global-change` | Apply file changes across all registered GSD-T projects |
 
 
 # Living Documents
@@ -252,6 +253,13 @@ Report: pass/fail counts and any coverage gaps."
 
 **QA failure blocks phase completion.** Lead cannot proceed until QA reports PASS or user explicitly overrides.
 
+## Model Display (MANDATORY)
+
+**Before every subagent spawn, display the model being used to the user:**
+`⚙ [{model}] {command} → {brief description}` (e.g., `⚙ [sonnet] gsd-t-execute → domain: auth-service`, `⚙ [haiku] gsd-t-execute → QA validation`)
+
+This gives the user real-time visibility into which model is handling each operation.
+
 ## API Documentation Guard (Swagger/OpenAPI)
 
 **Every API endpoint MUST be documented in a Swagger/OpenAPI spec. No exceptions.**