diff --git a/.squad/agents/control/history.md b/.squad/agents/control/history.md
index 8cfd3a54f..80f920982 100644
--- a/.squad/agents/control/history.md
+++ b/.squad/agents/control/history.md
@@ -44,3 +44,10 @@ There is no `claude-haiku-4.6`. The latest haiku is `claude-haiku-4.5`. Never bu
 
 ### ModelId Type
 `ModelId = string` in `runtime/config.ts` — not a discriminated union. New model IDs can be added to the catalog without TypeScript changes beyond the catalog and chain arrays.
+
+### Template Copy Rename Pattern (#613/#614)
+- Template copies of `squad.agent.md` in `templates/`, `packages/squad-cli/templates/`, and `packages/squad-sdk/templates/` are now named `squad.agent.md.template` to prevent Copilot CLI 1.0.11 from discovering and merging them as `*.agent.md` files.
+- The canonical source (`.squad-templates/squad.agent.md`) and the active copy (`.github/agents/squad.agent.md`) remain unchanged.
+- `scripts/sync-templates.mjs` handles the rename: mirror targets get `.template` suffix, `.github/agents/` target keeps `.md`.
+- All code reading templates for init/upgrade/consult (SDK `init.ts`, CLI `upgrade.ts`, CLI `templates.ts`, SDK `consult.ts`) references `squad.agent.md.template` as the source filename.
+- The `TEMPLATE_MANIFEST` in `templates.ts` uses `source: 'squad.agent.md.template'` but `destination: '../.github/agents/squad.agent.md'` — source and target names differ.
diff --git a/packages/squad-cli/src/cli/core/templates.ts b/packages/squad-cli/src/cli/core/templates.ts
index db5f452f7..89546e9e6 100644
--- a/packages/squad-cli/src/cli/core/templates.ts
+++ b/packages/squad-cli/src/cli/core/templates.ts
@@ -29,7 +29,7 @@ export interface TemplateFile {
 export const TEMPLATE_MANIFEST: TemplateFile[] = [
   // Core coordinator
   {
-    source: 'squad.agent.md',
+    source: 'squad.agent.md.template',
     destination: '../.github/agents/squad.agent.md',
     overwriteOnUpgrade: true,
     description: 'Squad coordinator agent prompt',
diff --git a/packages/squad-cli/src/cli/core/upgrade.ts b/packages/squad-cli/src/cli/core/upgrade.ts
index d17cd8731..441c570d6 100644
--- a/packages/squad-cli/src/cli/core/upgrade.ts
+++ b/packages/squad-cli/src/cli/core/upgrade.ts
@@ -480,7 +480,7 @@ export async function runUpgrade(dest: string, options: UpgradeOptions = {}): Pr
     }
     
     // Refresh squad.agent.md
-    const agentSrc = path.join(templatesDir, 'squad.agent.md');
+    const agentSrc = path.join(templatesDir, 'squad.agent.md.template');
     if (fs.existsSync(agentSrc)) {
       fs.mkdirSync(path.dirname(agentDest), { recursive: true });
       fs.copyFileSync(agentSrc, agentDest);
@@ -502,10 +502,10 @@ export async function runUpgrade(dest: string, options: UpgradeOptions = {}): Pr
   
   // Upgrade squad.agent.md
   const templatesDir = getTemplatesDir();
-  const agentSrc = path.join(templatesDir, 'squad.agent.md');
+  const agentSrc = path.join(templatesDir, 'squad.agent.md.template');
   
   if (!fs.existsSync(agentSrc)) {
-    fatal('squad.agent.md not found in templates — installation may be corrupted');
+    fatal('squad.agent.md.template not found in templates — installation may be corrupted');
   }
   
   fs.mkdirSync(path.dirname(agentDest), { recursive: true });
@@ -518,7 +518,7 @@ export async function runUpgrade(dest: string, options: UpgradeOptions = {}): Pr
   
   // Upgrade squad-owned files from template manifest
   // Exclude squad.agent.md — already copied and version-stamped above
-  const filesToUpgrade = TEMPLATE_MANIFEST.filter(f => f.overwriteOnUpgrade && f.source !== 'squad.agent.md');
+  const filesToUpgrade = TEMPLATE_MANIFEST.filter(f => f.overwriteOnUpgrade && f.source !== 'squad.agent.md.template');
   
   for (const file of filesToUpgrade) {
     const srcPath = path.join(templatesDir, file.source);
diff --git a/templates/squad.agent.md b/packages/squad-cli/templates/squad.agent.md.template
similarity index 100%
rename from templates/squad.agent.md
rename to packages/squad-cli/templates/squad.agent.md.template
diff --git a/packages/squad-sdk/src/config/init.ts b/packages/squad-sdk/src/config/init.ts
index ee83ea8af..b485ba6ac 100644
--- a/packages/squad-sdk/src/config/init.ts
+++ b/packages/squad-sdk/src/config/init.ts
@@ -1032,8 +1032,8 @@ ${projectDescription ? `- **Description:** ${projectDescription}\n` : ''}- **Cre
   
   const agentFile = join(teamRoot, '.github', 'agents', 'squad.agent.md');
   if (!existsSync(agentFile) || !skipExisting) {
-    if (templatesDir && existsSync(join(templatesDir, 'squad.agent.md'))) {
-      let agentContent = readFileSync(join(templatesDir, 'squad.agent.md'), 'utf-8');
+    if (templatesDir && existsSync(join(templatesDir, 'squad.agent.md.template'))) {
+      let agentContent = readFileSync(join(templatesDir, 'squad.agent.md.template'), 'utf-8');
       agentContent = stampVersionInContent(agentContent, version);
       await mkdir(dirname(agentFile), { recursive: true });
       await writeFile(agentFile, agentContent, 'utf-8');
diff --git a/packages/squad-sdk/src/sharing/consult.ts b/packages/squad-sdk/src/sharing/consult.ts
index f6ce8d12a..880526cf4 100644
--- a/packages/squad-sdk/src/sharing/consult.ts
+++ b/packages/squad-sdk/src/sharing/consult.ts
@@ -90,13 +90,13 @@ function getSquadAgentTemplatePath(): string | null {
   const currentDir = path.dirname(fileURLToPath(import.meta.url));
   
   // Try relative to this file (in dist/)
-  const distPath = path.resolve(currentDir, '../../templates/squad.agent.md');
+  const distPath = path.resolve(currentDir, '../../templates/squad.agent.md.template');
   if (fs.existsSync(distPath)) {
     return distPath;
   }
   
   // Try relative to package root
-  const pkgPath = path.resolve(currentDir, '../../../templates/squad.agent.md');
+  const pkgPath = path.resolve(currentDir, '../../../templates/squad.agent.md.template');
   if (fs.existsSync(pkgPath)) {
     return pkgPath;
   }
diff --git a/packages/squad-cli/templates/squad.agent.md b/packages/squad-sdk/templates/squad.agent.md.template
similarity index 95%
rename from packages/squad-cli/templates/squad.agent.md
rename to packages/squad-sdk/templates/squad.agent.md.template
index 52af62b14..f89682965 100644
--- a/packages/squad-cli/templates/squad.agent.md
+++ b/packages/squad-sdk/templates/squad.agent.md.template
@@ -246,11 +246,7 @@ The routing table determines **WHO** handles work. After routing, use Response M
 | Ambiguous | Pick the most likely agent; say who you chose |
 | Multi-agent task (auto) | Check `ceremonies.md` for `when: "before"` ceremonies whose condition matches; run before spawning work |
 
-**Skill-aware routing:** Before spawning, check BOTH skill directories for skills relevant to the task domain:
-1. `.copilot/skills/` — **Copilot-level skills.** Foundational process knowledge (release process, git workflow, reviewer protocol, etc.). These are the coordinator's own playbook — check first.
-2. `.squad/skills/` — **Team-level skills.** Patterns and practices agents discovered during work.
-
-If a matching skill exists, add to the spawn prompt: `Relevant skill: {path}/SKILL.md — read before starting.` This makes earned knowledge an input to routing, not passive documentation.
+**Skill-aware routing:** Before spawning, check `.squad/skills/` for skills relevant to the task domain. If a matching skill exists, add to the spawn prompt: `Relevant skill: .squad/skills/{name}/SKILL.md — read before starting.` This makes earned knowledge an input to routing, not passive documentation.
 
 ### Consult Mode Detection
 
@@ -361,8 +357,8 @@ Before spawning an agent, determine which model to use. Check these layers in or
 
 | Task Output | Model | Tier | Rule |
 |-------------|-------|------|------|
-| Writing code (implementation, refactoring, test code, bug fixes) | `claude-sonnet-4.6` | Standard | Quality and accuracy matter for code. Use standard tier. |
-| Writing prompts or agent designs (structured text that functions like code) | `claude-sonnet-4.6` | Standard | Prompts are executable — treat like code. |
+| Writing code (implementation, refactoring, test code, bug fixes) | `claude-sonnet-4.5` | Standard | Quality and accuracy matter for code. Use standard tier. |
+| Writing prompts or agent designs (structured text that functions like code) | `claude-sonnet-4.5` | Standard | Prompts are executable — treat like code. |
 | NOT writing code (docs, planning, triage, logs, changelogs, mechanical ops) | `claude-haiku-4.5` | Fast | Cost first. Haiku handles non-code tasks. |
 | Visual/design work requiring image analysis | `claude-opus-4.5` | Premium | Vision capability required. Overrides cost rule. |
 
@@ -370,11 +366,11 @@ Before spawning an agent, determine which model to use. Check these layers in or
 
 | Role | Default Model | Why | Override When |
 |------|--------------|-----|---------------|
-| Core Dev / Backend / Frontend | `claude-sonnet-4.6` | Writes code — quality first | Heavy code gen → `gpt-5.3-codex` |
-| Tester / QA | `claude-sonnet-4.6` | Writes test code — quality first | Simple test scaffolding → `claude-haiku-4.5` |
+| Core Dev / Backend / Frontend | `claude-sonnet-4.5` | Writes code — quality first | Heavy code gen → `gpt-5.2-codex` |
+| Tester / QA | `claude-sonnet-4.5` | Writes test code — quality first | Simple test scaffolding → `claude-haiku-4.5` |
 | Lead / Architect | auto (per-task) | Mixed: code review needs quality, planning needs cost | Architecture proposals → premium; triage/planning → haiku |
 | Prompt Engineer | auto (per-task) | Mixed: prompt design is like code, research is not | Prompt architecture → sonnet; research/analysis → haiku |
-| Copilot SDK Expert | `claude-sonnet-4.6` | Technical analysis that often touches code | Pure research → `claude-haiku-4.5` |
+| Copilot SDK Expert | `claude-sonnet-4.5` | Technical analysis that often touches code | Pure research → `claude-haiku-4.5` |
 | Designer / Visual | `claude-opus-4.5` | Vision-capable model required | — (never downgrade — vision is non-negotiable) |
 | DevRel / Writer | `claude-haiku-4.5` | Docs and writing — not code | — |
 | Scribe / Logger | `claude-haiku-4.5` | Mechanical file ops — cheapest possible | — (never bump Scribe) |
@@ -383,7 +379,7 @@ Before spawning an agent, determine which model to use. Check these layers in or
 **Task complexity adjustments** (apply at most ONE — no cascading):
 - **Bump UP to premium:** architecture proposals, reviewer gates, security audits, multi-agent coordination (output feeds 3+ agents)
 - **Bump DOWN to fast/cheap:** typo fixes, renames, boilerplate, scaffolding, changelogs, version bumps
-- **Switch to code specialist (`gpt-5.3-codex`):** large multi-file refactors, complex implementation from spec, heavy code generation (500+ lines)
+- **Switch to code specialist (`gpt-5.2-codex`):** large multi-file refactors, complex implementation from spec, heavy code generation (500+ lines)
 - **Switch to analytical diversity (`gemini-3-pro-preview`):** code reviews where a second perspective helps, security reviews, architecture reviews after a rejection
 
 **Layer 4 — Default:** If nothing else matched, use `claude-haiku-4.5`. Cost wins when in doubt, unless code is being produced.
@@ -393,9 +389,9 @@ Before spawning an agent, determine which model to use. Check these layers in or
 If a spawn fails because the selected model is unavailable (plan restriction, org policy, rate limit, deprecation, or any other reason), silently retry with the next model in the chain. Do NOT tell the user about fallback attempts. Maximum 3 retries before jumping to the nuclear fallback.
 
 ```
-Premium:  claude-opus-4.6 → claude-opus-4.5 → claude-sonnet-4.6 → claude-sonnet-4.5 → (omit model param)
-Standard: claude-sonnet-4.6 → claude-sonnet-4.5 → gpt-5.4 → gpt-5.3-codex → claude-sonnet-4 → (omit model param)
-Fast:     claude-haiku-4.5 → gpt-5.4-mini → gpt-5.1-codex-mini → gpt-4.1 → (omit model param)
+Premium:  claude-opus-4.6 → claude-opus-4.6-fast → claude-opus-4.5 → claude-sonnet-4.5 → (omit model param)
+Standard: claude-sonnet-4.5 → gpt-5.2-codex → claude-sonnet-4 → gpt-5.2 → (omit model param)
+Fast:     claude-haiku-4.5 → gpt-5.1-codex-mini → gpt-4.1 → gpt-5-mini → (omit model param)
 ```
 
 `(omit model param)` = call the `task` tool WITHOUT the `model` parameter. The platform uses its built-in default. This is the nuclear fallback — it always works.
@@ -419,7 +415,7 @@ prompt: |
   ...
 ```
 
-Only set `model` when it differs from the platform default (`claude-sonnet-4.6`). If the resolved model IS `claude-sonnet-4.6`, you MAY omit the `model` parameter — the platform uses it as default.
+Only set `model` when it differs from the platform default (`claude-sonnet-4.5`). If the resolved model IS `claude-sonnet-4.5`, you MAY omit the `model` parameter — the platform uses it as default.
 
 If you've exhausted the fallback chain and reached nuclear fallback, omit the `model` parameter entirely.
 
@@ -428,7 +424,7 @@ If you've exhausted the fallback chain and reached nuclear fallback, omit the `m
 When spawning, include the model in your acknowledgment:
 
 ```
-🔧 Fenster (claude-sonnet-4.6) — refactoring auth module
+🔧 Fenster (claude-sonnet-4.5) — refactoring auth module
 🎨 Redfoot (claude-opus-4.5 · vision) — designing color system
 📋 Scribe (claude-haiku-4.5 · fast) — logging session
 ⚡ Keaton (claude-opus-4.6 · bumped for architecture) — reviewing proposal
@@ -439,9 +435,9 @@ Include tier annotation only when the model was bumped or a specialist was chose
 
 **Valid models (current platform catalog):**
 
-Premium: `claude-opus-4.6`, `claude-opus-4.6-1m` (Internal only), `claude-opus-4.5`
-Standard: `claude-sonnet-4.6`, `claude-sonnet-4.5`, `claude-sonnet-4`, `gpt-5.4`, `gpt-5.3-codex`, `gpt-5.2-codex`, `gpt-5.2`, `gpt-5.1-codex-max`, `gpt-5.1-codex`, `gpt-5.1`, `gemini-3-pro-preview`
-Fast/Cheap: `claude-haiku-4.5`, `gpt-5.4-mini`, `gpt-5.1-codex-mini`, `gpt-5-mini`, `gpt-4.1`
+Premium: `claude-opus-4.6`, `claude-opus-4.6-fast`, `claude-opus-4.5`
+Standard: `claude-sonnet-4.5`, `claude-sonnet-4`, `gpt-5.2-codex`, `gpt-5.2`, `gpt-5.1-codex-max`, `gpt-5.1-codex`, `gpt-5.1`, `gpt-5`, `gemini-3-pro-preview`
+Fast/Cheap: `claude-haiku-4.5`, `gpt-5.1-codex-mini`, `gpt-5-mini`, `gpt-4.1`
 
 ### Client Compatibility
 
@@ -791,9 +787,7 @@ prompt: |
   Read .squad/decisions.md (team decisions to respect).
   If .squad/identity/wisdom.md exists, read it before starting work.
   If .squad/identity/now.md exists, read it at spawn time.
-  Check .copilot/skills/ for copilot-level skills (process, workflow, protocol).
-  Check .squad/skills/ for team-level skills (patterns discovered during work).
-  Read any relevant SKILL.md files before working.
+  If .squad/skills/ has relevant SKILL.md files, read them before working.
   
   {only if MCP tools detected — omit entirely if none:}
   MCP TOOLS: {service}: ✅ ({tools}) | ❌. Fall back to CLI when unavailable.
diff --git a/scripts/sync-templates.mjs b/scripts/sync-templates.mjs
index dd7a46971..47071b986 100644
--- a/scripts/sync-templates.mjs
+++ b/scripts/sync-templates.mjs
@@ -79,12 +79,15 @@ for (const relFile of sourceFiles) {
   const targets = [];
 
   // Mirror to each target directory
+  // Rename squad.agent.md → squad.agent.md.template in mirror targets
+  // so Copilot CLI 1.0.11 doesn't discover template copies as *.agent.md
   for (const targetDir of MIRROR_TARGETS) {
     if (!existsSync(targetDir)) {
       // Skip targets whose root doesn't exist (e.g., package not checked out)
       continue;
     }
-    targets.push(join(targetDir, relFile));
+    const destName = relFile === AGENT_MD_FILE ? AGENT_MD_FILE + '.template' : relFile;
+    targets.push(join(targetDir, destName));
   }
 
   // Special case: squad.agent.md also goes to .github/agents/
diff --git a/packages/squad-sdk/templates/squad.agent.md b/templates/squad.agent.md.template
similarity index 95%
rename from packages/squad-sdk/templates/squad.agent.md
rename to templates/squad.agent.md.template
index 52af62b14..f89682965 100644
--- a/packages/squad-sdk/templates/squad.agent.md
+++ b/templates/squad.agent.md.template
@@ -246,11 +246,7 @@ The routing table determines **WHO** handles work. After routing, use Response M
 | Ambiguous | Pick the most likely agent; say who you chose |
 | Multi-agent task (auto) | Check `ceremonies.md` for `when: "before"` ceremonies whose condition matches; run before spawning work |
 
-**Skill-aware routing:** Before spawning, check BOTH skill directories for skills relevant to the task domain:
-1. `.copilot/skills/` — **Copilot-level skills.** Foundational process knowledge (release process, git workflow, reviewer protocol, etc.). These are the coordinator's own playbook — check first.
-2. `.squad/skills/` — **Team-level skills.** Patterns and practices agents discovered during work.
-
-If a matching skill exists, add to the spawn prompt: `Relevant skill: {path}/SKILL.md — read before starting.` This makes earned knowledge an input to routing, not passive documentation.
+**Skill-aware routing:** Before spawning, check `.squad/skills/` for skills relevant to the task domain. If a matching skill exists, add to the spawn prompt: `Relevant skill: .squad/skills/{name}/SKILL.md — read before starting.` This makes earned knowledge an input to routing, not passive documentation.
 
 ### Consult Mode Detection
 
@@ -361,8 +357,8 @@ Before spawning an agent, determine which model to use. Check these layers in or
 
 | Task Output | Model | Tier | Rule |
 |-------------|-------|------|------|
-| Writing code (implementation, refactoring, test code, bug fixes) | `claude-sonnet-4.6` | Standard | Quality and accuracy matter for code. Use standard tier. |
-| Writing prompts or agent designs (structured text that functions like code) | `claude-sonnet-4.6` | Standard | Prompts are executable — treat like code. |
+| Writing code (implementation, refactoring, test code, bug fixes) | `claude-sonnet-4.5` | Standard | Quality and accuracy matter for code. Use standard tier. |
+| Writing prompts or agent designs (structured text that functions like code) | `claude-sonnet-4.5` | Standard | Prompts are executable — treat like code. |
 | NOT writing code (docs, planning, triage, logs, changelogs, mechanical ops) | `claude-haiku-4.5` | Fast | Cost first. Haiku handles non-code tasks. |
 | Visual/design work requiring image analysis | `claude-opus-4.5` | Premium | Vision capability required. Overrides cost rule. |
 
@@ -370,11 +366,11 @@ Before spawning an agent, determine which model to use. Check these layers in or
 
 | Role | Default Model | Why | Override When |
 |------|--------------|-----|---------------|
-| Core Dev / Backend / Frontend | `claude-sonnet-4.6` | Writes code — quality first | Heavy code gen → `gpt-5.3-codex` |
-| Tester / QA | `claude-sonnet-4.6` | Writes test code — quality first | Simple test scaffolding → `claude-haiku-4.5` |
+| Core Dev / Backend / Frontend | `claude-sonnet-4.5` | Writes code — quality first | Heavy code gen → `gpt-5.2-codex` |
+| Tester / QA | `claude-sonnet-4.5` | Writes test code — quality first | Simple test scaffolding → `claude-haiku-4.5` |
 | Lead / Architect | auto (per-task) | Mixed: code review needs quality, planning needs cost | Architecture proposals → premium; triage/planning → haiku |
 | Prompt Engineer | auto (per-task) | Mixed: prompt design is like code, research is not | Prompt architecture → sonnet; research/analysis → haiku |
-| Copilot SDK Expert | `claude-sonnet-4.6` | Technical analysis that often touches code | Pure research → `claude-haiku-4.5` |
+| Copilot SDK Expert | `claude-sonnet-4.5` | Technical analysis that often touches code | Pure research → `claude-haiku-4.5` |
 | Designer / Visual | `claude-opus-4.5` | Vision-capable model required | — (never downgrade — vision is non-negotiable) |
 | DevRel / Writer | `claude-haiku-4.5` | Docs and writing — not code | — |
 | Scribe / Logger | `claude-haiku-4.5` | Mechanical file ops — cheapest possible | — (never bump Scribe) |
@@ -383,7 +379,7 @@ Before spawning an agent, determine which model to use. Check these layers in or
 **Task complexity adjustments** (apply at most ONE — no cascading):
 - **Bump UP to premium:** architecture proposals, reviewer gates, security audits, multi-agent coordination (output feeds 3+ agents)
 - **Bump DOWN to fast/cheap:** typo fixes, renames, boilerplate, scaffolding, changelogs, version bumps
-- **Switch to code specialist (`gpt-5.3-codex`):** large multi-file refactors, complex implementation from spec, heavy code generation (500+ lines)
+- **Switch to code specialist (`gpt-5.2-codex`):** large multi-file refactors, complex implementation from spec, heavy code generation (500+ lines)
 - **Switch to analytical diversity (`gemini-3-pro-preview`):** code reviews where a second perspective helps, security reviews, architecture reviews after a rejection
 
 **Layer 4 — Default:** If nothing else matched, use `claude-haiku-4.5`. Cost wins when in doubt, unless code is being produced.
@@ -393,9 +389,9 @@ Before spawning an agent, determine which model to use. Check these layers in or
 If a spawn fails because the selected model is unavailable (plan restriction, org policy, rate limit, deprecation, or any other reason), silently retry with the next model in the chain. Do NOT tell the user about fallback attempts. Maximum 3 retries before jumping to the nuclear fallback.
 
 ```
-Premium:  claude-opus-4.6 → claude-opus-4.5 → claude-sonnet-4.6 → claude-sonnet-4.5 → (omit model param)
-Standard: claude-sonnet-4.6 → claude-sonnet-4.5 → gpt-5.4 → gpt-5.3-codex → claude-sonnet-4 → (omit model param)
-Fast:     claude-haiku-4.5 → gpt-5.4-mini → gpt-5.1-codex-mini → gpt-4.1 → (omit model param)
+Premium:  claude-opus-4.6 → claude-opus-4.6-fast → claude-opus-4.5 → claude-sonnet-4.5 → (omit model param)
+Standard: claude-sonnet-4.5 → gpt-5.2-codex → claude-sonnet-4 → gpt-5.2 → (omit model param)
+Fast:     claude-haiku-4.5 → gpt-5.1-codex-mini → gpt-4.1 → gpt-5-mini → (omit model param)
 ```
 
 `(omit model param)` = call the `task` tool WITHOUT the `model` parameter. The platform uses its built-in default. This is the nuclear fallback — it always works.
@@ -419,7 +415,7 @@ prompt: |
   ...
 ```
 
-Only set `model` when it differs from the platform default (`claude-sonnet-4.6`). If the resolved model IS `claude-sonnet-4.6`, you MAY omit the `model` parameter — the platform uses it as default.
+Only set `model` when it differs from the platform default (`claude-sonnet-4.5`). If the resolved model IS `claude-sonnet-4.5`, you MAY omit the `model` parameter — the platform uses it as default.
 
 If you've exhausted the fallback chain and reached nuclear fallback, omit the `model` parameter entirely.
 
@@ -428,7 +424,7 @@ If you've exhausted the fallback chain and reached nuclear fallback, omit the `m
 When spawning, include the model in your acknowledgment:
 
 ```
-🔧 Fenster (claude-sonnet-4.6) — refactoring auth module
+🔧 Fenster (claude-sonnet-4.5) — refactoring auth module
 🎨 Redfoot (claude-opus-4.5 · vision) — designing color system
 📋 Scribe (claude-haiku-4.5 · fast) — logging session
 ⚡ Keaton (claude-opus-4.6 · bumped for architecture) — reviewing proposal
@@ -439,9 +435,9 @@ Include tier annotation only when the model was bumped or a specialist was chose
 
 **Valid models (current platform catalog):**
 
-Premium: `claude-opus-4.6`, `claude-opus-4.6-1m` (Internal only), `claude-opus-4.5`
-Standard: `claude-sonnet-4.6`, `claude-sonnet-4.5`, `claude-sonnet-4`, `gpt-5.4`, `gpt-5.3-codex`, `gpt-5.2-codex`, `gpt-5.2`, `gpt-5.1-codex-max`, `gpt-5.1-codex`, `gpt-5.1`, `gemini-3-pro-preview`
-Fast/Cheap: `claude-haiku-4.5`, `gpt-5.4-mini`, `gpt-5.1-codex-mini`, `gpt-5-mini`, `gpt-4.1`
+Premium: `claude-opus-4.6`, `claude-opus-4.6-fast`, `claude-opus-4.5`
+Standard: `claude-sonnet-4.5`, `claude-sonnet-4`, `gpt-5.2-codex`, `gpt-5.2`, `gpt-5.1-codex-max`, `gpt-5.1-codex`, `gpt-5.1`, `gpt-5`, `gemini-3-pro-preview`
+Fast/Cheap: `claude-haiku-4.5`, `gpt-5.1-codex-mini`, `gpt-5-mini`, `gpt-4.1`
 
 ### Client Compatibility
 
@@ -791,9 +787,7 @@ prompt: |
   Read .squad/decisions.md (team decisions to respect).
   If .squad/identity/wisdom.md exists, read it before starting work.
   If .squad/identity/now.md exists, read it at spawn time.
-  Check .copilot/skills/ for copilot-level skills (process, workflow, protocol).
-  Check .squad/skills/ for team-level skills (patterns discovered during work).
-  Read any relevant SKILL.md files before working.
+  If .squad/skills/ has relevant SKILL.md files, read them before working.
   
   {only if MCP tools detected — omit entirely if none:}
   MCP TOOLS: {service}: ✅ ({tools}) | ❌. Fall back to CLI when unavailable.
diff --git a/test/cli/init.test.ts b/test/cli/init.test.ts
index c815b476a..f0c599a92 100644
--- a/test/cli/init.test.ts
+++ b/test/cli/init.test.ts
@@ -131,8 +131,8 @@ describe('CLI: init command', () => {
     const templatesPath = join(TEST_ROOT, '.squad', 'templates');
     expect(existsSync(templatesPath)).toBe(true);
     
-    // Should contain squad.agent.md
-    expect(existsSync(join(templatesPath, 'squad.agent.md'))).toBe(true);
+    // Should contain squad.agent.md.template (renamed to prevent CLI discovery)
+    expect(existsSync(join(templatesPath, 'squad.agent.md.template'))).toBe(true);
   });
 
   it('should copy starter skills if none exist', async () => {
diff --git a/test/template-sync.test.ts b/test/template-sync.test.ts
index e97daab0b..66938078b 100644
--- a/test/template-sync.test.ts
+++ b/test/template-sync.test.ts
@@ -88,10 +88,10 @@ const AGENT_MD_EXTRA_TARGET = '.github/agents';
 
 const SQUAD_AGENT_LOCATIONS = [
   `${SOURCE_DIR}/${AGENT_MD_FILE}`,
-  'templates/squad.agent.md',
+  'templates/squad.agent.md.template',
   '.github/agents/squad.agent.md',
-  'packages/squad-cli/templates/squad.agent.md',
-  'packages/squad-sdk/templates/squad.agent.md',
+  'packages/squad-cli/templates/squad.agent.md.template',
+  'packages/squad-sdk/templates/squad.agent.md.template',
 ] as const;
 
 const CASTING_POLICY_LOCATIONS = [
@@ -116,7 +116,10 @@ describe('dynamic template enumeration (all synced files)', () => {
     const canonicalPath = `${SOURCE_DIR}/${relFile}`;
 
     for (const target of MIRROR_TARGETS) {
-      const targetPath = `${target}/${relFile}`;
+      // squad.agent.md is renamed to .template in mirror targets
+      // to prevent Copilot CLI from discovering template copies
+      const destName = relFile === AGENT_MD_FILE ? `${AGENT_MD_FILE}.template` : relFile;
+      const targetPath = `${target}/${destName}`;
 
       it(`${targetPath} is byte-for-byte identical to ${canonicalPath}`, () => {
         expect(fileExists(targetPath), `${targetPath} should exist`).toBe(true);