feat(model-overlays): add opus-4-8 overlay + resolver mapping

Give claude-opus-4-8 a dedicated overlay instead of the generic claude
fallback: effort-matching, skill-paced questions, complete-scope literal
execution. Mirrors opus-4-7's family nudges. Adds the models.ts resolver
mapping and a gate-tier test mirroring model-overlay-opus-4-7.test.ts.

model-overlays/opus-4-8.md

@@ -0,0 +1,23 @@
+{{INHERIT:claude}}
+
+**Effort-match the step.** Simple file reads, config checks, command lookups, and
+mechanical edits don't need deep reasoning. Complete them quickly and move on. Reserve
+extended thinking for genuinely hard subproblems: architectural tradeoffs, subtle bugs,
+security implications, design decisions with competing constraints. Over-thinking
+simple steps wastes tokens and time.
+
+**Pace questions to the skill.** If the current skill's text contains
+`STOP. AskUserQuestion` anywhere, pace one question per turn — emit the question as
+a tool_use, stop, wait for the user's response, then continue. Do not batch. A
+finding with an "obvious fix" is still a finding and still needs user approval
+before it lands in the plan. Only batch clarifying questions upfront when (a) the
+skill has no `STOP. AskUserQuestion` directive AND (b) you need multiple unrelated
+clarifications before you can begin. When in doubt, ask one question per turn.
+
+**Literal interpretation awareness.** Opus 4.8 interprets instructions literally and
+will not silently generalize. When the user says "fix the tests," fix all failing tests
+that this branch introduced or is responsible for, not just the first one (and not
+pre-existing failures in unrelated code). When the user says "update the docs," update
+every relevant doc in scope, not just the most obvious one. Read the full scope of what
+was asked and deliver the full scope. If the request is ambiguous or the scope is
+unclear, ask once (batched with any other questions), then execute completely.

scripts/models.ts

@@ -14,6 +14,7 @@
 export const ALL_MODEL_NAMES = [
   'claude',
   'opus-4-7',
+  'opus-4-8',
   'gpt',
   'gpt-5.4',
   'gemini',
@@ -53,6 +54,7 @@ export function resolveModel(input: string): Model | null {
   if (/^gpt(-|$)/.test(s)) return 'gpt';
   if (/^o[0-9]+(-|$)/.test(s)) return 'o-series';
   if (/^claude-opus-4-7(-|$)/.test(s)) return 'opus-4-7';
+  if (/^claude-opus-4-8(-|$)/.test(s)) return 'opus-4-8';
   if (/^claude(-|$)/.test(s)) return 'claude';
   if (/^gemini(-|$)/.test(s)) return 'gemini';
 

test/model-overlay-opus-4-8.test.ts

@@ -0,0 +1,92 @@
+/**
+ * Opus 4.8 model overlay — gate-tier assertions on the pacing directive.
+ *
+ * opus-4-8 mirrors opus-4-7's Opus-4.x family nudges: it inherits the claude
+ * base and adds effort-matching, skill-paced questions (one-per-turn when the
+ * skill carries STOP directives), and complete-scope literal execution.
+ *
+ * This test asserts:
+ * - The "Pace questions to the skill" directive is present
+ * - The old "Batch your questions" directive is absent
+ * - The AUTO_DECIDE-compatible language survives (subordination, skill wins)
+ * - The claude base is inherited (INHERIT:claude)
+ */
+import { describe, test, expect } from 'bun:test';
+import * as fs from 'fs';
+import * as path from 'path';
+import type { TemplateContext } from '../scripts/resolvers/types';
+import { HOST_PATHS } from '../scripts/resolvers/types';
+import { generateModelOverlay } from '../scripts/resolvers/model-overlay';
+
+function makeCtx(model: string): TemplateContext {
+  return {
+    skillName: 'test-skill',
+    tmplPath: 'test.tmpl',
+    host: 'claude',
+    paths: HOST_PATHS.claude,
+    preambleTier: 2,
+    model,
+  };
+}
+
+const ROOT = path.resolve(__dirname, '..');
+
+describe('Opus 4.8 overlay — pacing directive', () => {
+  test('raw opus-4-8.md contains "Pace questions to the skill"', () => {
+    const raw = fs.readFileSync(
+      path.join(ROOT, 'model-overlays/opus-4-8.md'),
+      'utf-8',
+    );
+    expect(raw).toContain('Pace questions to the skill');
+  });
+
+  test('raw opus-4-8.md does NOT contain "Batch your questions" directive', () => {
+    const raw = fs.readFileSync(
+      path.join(ROOT, 'model-overlays/opus-4-8.md'),
+      'utf-8',
+    );
+    expect(raw).not.toContain('**Batch your questions.**');
+  });
+
+  test('resolved overlay output contains "Pace questions to the skill"', () => {
+    const out = generateModelOverlay(makeCtx('opus-4-8'));
+    expect(out).toContain('Pace questions to the skill');
+  });
+
+  test('resolved overlay inherits from claude base (INHERIT:claude)', () => {
+    const out = generateModelOverlay(makeCtx('opus-4-8'));
+    // The claude base contributes the subordination wrapper + Todo discipline
+    expect(out).toContain('Todo-list discipline');
+    expect(out).toContain('subordinate');
+  });
+
+  test('resolved overlay says skill STOP directives trigger one-per-turn pacing', () => {
+    const out = generateModelOverlay(makeCtx('opus-4-8'));
+    expect(out).toMatch(/STOP\. AskUserQuestion/);
+    expect(out).toMatch(/pace one question per turn|one question per turn/i);
+  });
+
+  test('resolved overlay requires AskUserQuestion as tool_use', () => {
+    const out = generateModelOverlay(makeCtx('opus-4-8'));
+    expect(out).toContain('tool_use');
+  });
+
+  test('resolved overlay flags "obvious fix" findings still need user approval', () => {
+    const out = generateModelOverlay(makeCtx('opus-4-8'));
+    expect(out).toMatch(/obvious fix/i);
+    expect(out).toMatch(/user approval/i);
+  });
+
+  test('resolved overlay keeps Effort-match / Literal interpretation nudges', () => {
+    const out = generateModelOverlay(makeCtx('opus-4-8'));
+    expect(out).toContain('Effort-match the step');
+    expect(out).toContain('Literal interpretation awareness');
+  });
+
+  test('claude overlay (no INHERIT chain) does not carry the pacing directive', () => {
+    // Claude is the default overlay; opus-4-8 inherits FROM claude.
+    // The pacing directive belongs to the opus-4-x overlays only.
+    const out = generateModelOverlay(makeCtx('claude'));
+    expect(out).not.toContain('Pace questions to the skill');
+  });
+});