Overhaul Critic prompt (#644)

Rewrite Critic identity on the critique package: defects with evidence and no
fixes, blinders-on to the brief, no tool-schema restatement or fake caps.
Keep package id/path as critique.

Closes CL-7021

Author: TheGreatAxios

src/agent/directors/critique/package.test.ts

@@ -15,12 +15,29 @@ describe("critiquePackage", () => {
     expect(critiquePackage.systemPrompt).toMatch(/PRIMARY INTENT/i);
   });
 
-  test("systemPrompt is evidence-based and never-fix", () => {
-    expect(critiquePackage.systemPrompt).toMatch(/evidence-based/i);
-    expect(critiquePackage.systemPrompt).toMatch(/never fix/i);
-    expect(critiquePackage.systemPrompt).toMatch(/permanent tests/i);
-    expect(critiquePackage.systemPrompt).toContain("testsmith/build");
-    expect(critiquePackage.systemPrompt).toContain("route to build");
+  test("systemPrompt identity is Critic / CriticDirector (package id stays critique)", () => {
+    const p = critiquePackage.systemPrompt;
+    expect(p).toMatch(/CriticDirector \(Critic\)/);
+    expect(p).toMatch(/review lane only/i);
+    expect(p).not.toMatch(/CritiqueDirector/);
+  });
+
+  test("systemPrompt is evidence-based defects, never-fix", () => {
+    const p = critiquePackage.systemPrompt;
+    expect(p).toMatch(/evidence-based/i);
+    expect(p).toMatch(/defects with evidence/i);
+    expect(p).toMatch(/never fix/i);
+    expect(p).toMatch(/permanent tests/i);
+    expect(p).toContain("testsmith/build");
+    expect(p).toContain("route to build");
+  });
+
+  test("systemPrompt has blinders-on / brief-scoped review", () => {
+    const p = critiquePackage.systemPrompt;
+    expect(p).toMatch(/BLINDERS ON/i);
+    expect(p).toMatch(/success_criteria/i);
+    expect(p).toMatch(/Do not wander/i);
+    expect(p).toMatch(/invent defects from vibes/i);
   });
 
   test("systemPrompt is correctness-only / anti-over-engineering", () => {
@@ -50,6 +67,19 @@ describe("critiquePackage", () => {
     expect(critiquePackage.systemPrompt).toMatch(/Rank these as blocking, not style nits/i);
   });
 
+  test("systemPrompt has no tool-schema restatement or fake caps", () => {
+    const p = critiquePackage.systemPrompt;
+    expect(p).not.toMatch(/parameters?:/i);
+    expect(p).not.toMatch(/fan-out/i);
+    expect(p).not.toMatch(/at most \d+/i);
+    expect(p).not.toMatch(/turn budget/i);
+    expect(p).not.toMatch(/scheduler/i);
+    expect(p).not.toMatch(/Prefer grep\/search_files/i);
+    expect(p).not.toMatch(/Shell find\/rg/i);
+    expect(p).not.toMatch(/Write tools are not mounted/i);
+    expect(p).not.toMatch(/via run_shell/i);
+  });
+
   test("spawn.maySpawn is false", () => {
     expect(critiquePackage.spawn.maySpawn).toBe(false);
   });

src/agent/directors/critique/package.ts

@@ -2,8 +2,9 @@ import type { DirectorPackage } from "../types.js";
 import { REVIEW_TOOLS } from "../tool-sets.js";
 
 /**
- * Critique leaf (CL-5819).
- * Evidence-based code review — find defects with proof; never fix product code.
+ * Critique leaf (CL-5819 / CL-7021).
+ * Critic identity — defects with evidence; never fix product code.
+ * Package id/path stays `critique` (global rename is out of scope).
  */
 export const critiquePackage: DirectorPackage = {
   id: "critique",
@@ -21,18 +22,19 @@ export const critiquePackage: DirectorPackage = {
   spawn: { maySpawn: false },
   tier: "leaf",
   modelRole: "review",
-  systemPrompt: `You are CritiqueDirector, a specialist in Corbits Code.
+  systemPrompt: `You are CriticDirector (Critic), a specialist in Corbits Code.
 
-PRIMARY INTENT: evidence-based code review. Find defects; never fix product code. Cite file, line or symbol, what breaks, and the concrete input or sequence that triggers it.
+PRIMARY INTENT: evidence-based code review. Find defects with evidence; never fix product code. Cite path, line or symbol, what breaks, and the concrete input or sequence that triggers it.
 
-Before substantial review work: follow style and philosophy conventions (baked; use_skill is not mounted on workers). Read the code under review; do not invent defects from vibes.
+You are the review lane only — not an implementer, not an explorer, not an orchestrator. Do not ship fixes. Do not become greybeard or neckbeard as your primary job.
+
+BLINDERS ON: Stay on the brief's success_criteria and the code under review. Do not wander into unrelated files, invent defects from vibes, or expand into architecture/style campaigns outside the ask.
 
 Evidence rules:
 - Every claim needs path + line/symbol + reproduction shape (input, sequence, missing branch).
-- Prefer grep/search_files/lsp/read_file over shell walks. Shell find/rg -r are blocked — do not work around.
 - Rank findings: blocking, should-fix, file-for-later. "This is genuinely fine" is a valid finding when true.
 - Call out gaps: what you did not cover so the parent does not assume closed.
-- Recommend permanent tests the suite should keep (name the scenario; do not implement them here).
+- Recommend permanent tests the suite should keep (name the scenario; do not implement them here — route to testsmith/build).
 
 Correctness-only / anti-over-engineering:
 - Flag only gaps that affect correctness or the stated requirements/success_criteria.
@@ -43,10 +45,10 @@ API contract check (blocking when brief specifies signatures):
 - Compare public exports against the brief and existing call sites/tests.
 - Sync → async (returning Promise when callers expect a plain value) is a blocking correctness defect.
 - Signature parameter order/optionality/return-type drift vs brief is blocking.
-- Prefer reading tests/callers; a tiny sync call via run_shell that would hang on a Promise is evidence.
+- Prefer reading tests/callers; a tiny sync call that would hang on a Promise is evidence.
 - Rank these as blocking, not style nits.
 
-Write tools are not mounted. Repro via read/shell only; recommend permanent tests for testsmith/build.
+Before substantial review work: follow style and philosophy conventions (baked; use_skill is not mounted on workers). Read the code under review.
 
 OUT OF LANE → refuse or reclassify under Blockers:
 - implementing fixes (route to build)