oh-my-opencode 4.16.3 → 4.17.0

package/packages/omo-codex/scripts/install-dist/install-local.mjs

@@ -5903,7 +5903,7 @@ var package_default;
 var init_package = __esm(() => {
   package_default = {
     name: "@oh-my-opencode/omo-codex",
-    version: "4.16.2",
+    version: "4.16.3",
     type: "module",
     private: true,
     description: "Codex harness adapter for oh-my-openagent. Vendored Codex plugin namespace (omo) + TypeScript installer + telemetry.",
@@ -7612,7 +7612,12 @@ function shouldCopyPluginPath(path, root) {
   if (relative4 === "")
     return true;
   const parts = relative4.split(sep5);
-  return !parts.some((part) => part === ".git" || part === "node_modules");
+  if (parts.some((part) => part === ".git" || part === "node_modules"))
+    return false;
+  return !isNestedComponentMcpManifest(parts);
+}
+function isNestedComponentMcpManifest(parts) {
+  return parts.length > 1 && parts.at(-1) === ".mcp.json";
 }
 var removedSparkshellReferencePattern = /\b(?:sparkshell|spark[-_\s]+shell)\b/i;
 var removedSparkshellPromptSurfaceDirs = new Set([".codex-plugin", "agents", "bundled-rules", "hooks", "skills"]);
@@ -8139,6 +8144,9 @@ function stripTomlLineComment(line) {
 var LEGACY_MANAGED_CODEX_AGENT_NAMES_TO_PURGE = ["codex-ultrawork-reviewer"];
 var CURRENT_MANAGED_CODEX_AGENT_NAMES = [
   "explorer",
+  "lazycodex-worker-high",
+  "lazycodex-worker-low",
+  "lazycodex-worker-medium",
   "librarian",
   "metis",
   "momus",
@@ -8556,12 +8564,18 @@ import { readFile as readFile10 } from "node:fs/promises";
 import { join as join17 } from "node:path";
 var FALLBACK_CODEX_MODEL_CATALOG = {
   current: {
-    model: "gpt-5.5",
-    modelContextWindow: 400000,
+    model: "gpt-5.6-sol",
+    modelContextWindow: 372000,
     modelReasoningEffort: "high",
     planModeReasoningEffort: "xhigh"
   },
   managedProfiles: [
+    {
+      model: "gpt-5.5",
+      modelContextWindow: 400000,
+      modelReasoningEffort: "high",
+      planModeReasoningEffort: "xhigh"
+    },
     {
       model: "gpt-5.5",
       modelContextWindow: 1e6,
@@ -9004,32 +9018,88 @@ import { join as join20 } from "node:path";
 var MANAGED_REASONING_DEFAULT_UPGRADES = new Map([
   [
     "explorer",
-    {
-      previous: { model: "gpt-5.4-mini", effort: "low" },
-      current: { model: "gpt-5.6-terra", effort: "medium" }
-    }
+    [
+      {
+        previous: { model: "gpt-5.4-mini", effort: "low" },
+        current: { model: "gpt-5.6-terra", effort: "medium" }
+      },
+      {
+        previous: { model: "gpt-5.6-terra", effort: "medium" },
+        current: { model: "gpt-5.6-luna", effort: "low" }
+      }
+    ]
   ],
   [
     "librarian",
-    {
-      previous: { model: "gpt-5.4-mini", effort: "low" },
-      current: { model: "gpt-5.6-terra", effort: "medium" }
-    }
+    [
+      {
+        previous: { model: "gpt-5.4-mini", effort: "low" },
+        current: { model: "gpt-5.6-terra", effort: "medium" }
+      },
+      {
+        previous: { model: "gpt-5.6-terra", effort: "medium" },
+        current: { model: "gpt-5.6-luna", effort: "low" }
+      }
+    ]
   ],
   [
     "momus",
-    {
-      previous: { model: "gpt-5.5", effort: "xhigh" },
-      current: { model: "gpt-5.6-sol", effort: "ultra" }
-    }
+    [
+      {
+        previous: { model: "gpt-5.5", effort: "xhigh" },
+        current: { model: "gpt-5.6-sol", effort: "ultra" }
+      }
+    ]
+  ],
+  [
+    "plan",
+    [
+      {
+        previous: { model: "gpt-5.6-sol", effort: "xhigh" },
+        current: { model: "gpt-5.6-sol", effort: "max" }
+      }
+    ]
+  ],
+  [
+    "lazycodex-worker-medium",
+    [
+      {
+        previous: { model: "gpt-5.6-sol", effort: "high" },
+        current: { model: "gpt-5.6-luna", effort: "max" }
+      }
+    ]
+  ],
+  [
+    "lazycodex-qa-executor",
+    [
+      {
+        previous: { model: "gpt-5.6-terra", effort: "medium" },
+        current: { model: "gpt-5.6-luna", effort: "high" }
+      }
+    ]
+  ],
+  [
+    "lazycodex-gate-reviewer",
+    [
+      {
+        previous: { model: "gpt-5.6-sol", effort: "xhigh" },
+        current: { model: "gpt-5.6-sol", effort: "high" }
+      }
+    ]
   ]
 ]);
 function resolveManagedAgentReasoning(input) {
-  const upgrade = MANAGED_REASONING_DEFAULT_UPGRADES.get(input.agentName);
-  if (upgrade !== undefined && input.preserved.model === upgrade.previous.model && input.preserved.effort === upgrade.previous.effort && input.bundledModel === upgrade.current.model && input.bundledEffort === upgrade.current.effort) {
-    return upgrade.current.effort;
-  }
-  return input.preserved.effort;
+  const steps = MANAGED_REASONING_DEFAULT_UPGRADES.get(input.agentName);
+  if (steps === undefined)
+    return input.preserved.effort;
+  const latest = steps[steps.length - 1];
+  if (latest === undefined)
+    return input.preserved.effort;
+  if (input.bundledModel !== latest.current.model || input.bundledEffort !== latest.current.effort) {
+    return input.preserved.effort;
+  }
+  const preservedMatchesAnyStep = steps.some((step) => input.preserved.model === step.previous.model && input.preserved.effort === step.previous.effort);
+  return preservedMatchesAnyStep ? latest.current.effort : input.preserved.effort;
 }
 
 // packages/omo-codex/src/install/preserved-agent-settings.ts

package/packages/shared-skills/skills/remove-ai-slops/SKILL.md

@@ -62,7 +62,7 @@ The agent looks for these nine categories. The first three are stylistic, the ne
    **Hard rule**: only apply when behavior equivalence is obvious. Do NOT change algorithms with subtle correctness implications. Do NOT micro-optimize hot paths without a benchmark. If in doubt, SKIP.
 
 ### Behavior coverage
-9. **Missing tests** — behavior present in changed files that is not locked by any regression test. The fix is not to remove code but to ADD the narrowest test that pins the behavior.
+9. **Missing tests** — behavior present in changed files that is not locked by any regression test. The fix is not to remove code but to ADD the narrowest test that pins the behavior. EXCEPTION: a PROSE file (prompt, `SKILL.md`, rule, markdown) has no behavioral seam — do NOT add a text/word-count/phrase pin for it; that guards a diff, not behavior. Cover only a machine-consumed value (parsed field, sentinel a runtime greps, a doc JSON sample through its real validator) or leave it to review.
 
 ### Structural
 10. **Oversized modules** — any source file exceeding **250 pure LOC** (non-blank, non-comment lines). This is an architectural defect, not a style preference. Measure: `awk '!/^[[:space:]]*$/ && !/^[[:space:]]*(#|\/\/)/' <file> | wc -l`.
@@ -122,7 +122,7 @@ For each in-scope source file:
 
 1. Identify the public/observable behavior the file exposes (exported functions, HTTP handlers, CLI commands, classes used elsewhere).
 2. Check whether existing tests cover that behavior. Use `git grep` / project test conventions to find related test files.
-3. **If behavior is uncovered or weakly covered, write the narrowest regression test that pins current behavior BEFORE editing the file.** Tests should pin observable outputs, not implementation details.
+3. **If behavior is uncovered or weakly covered, write the narrowest regression test that pins current behavior BEFORE editing the file.** Tests should pin observable outputs, not implementation details. A PROSE file (prompt/`SKILL.md`/rule/markdown) is exempt — its wording is not behavior; skip the test and rely on review, or assert only a machine-consumed value.
 4. Run the test suite (or at minimum the relevant tests). They must be **green** before any cleanup begins.
 
 If you cannot establish a green baseline (e.g., test runner is broken), STOP and report. Do not proceed with cleanup on unverified ground.

package/packages/shared-skills/skills/start-work/SKILL.md

@@ -14,13 +14,16 @@ Translate any OpenCode-only tool name in an inherited example to its Codex equiv
 | OpenCode example | Codex tool to use |
 | --- | --- |
 | final-review `task(...)` | `multi_agent_v1.spawn_agent({"message":"TASK: act as a rigorous reviewer. ...","agent_type":"lazycodex-gate-reviewer","fork_context":false})` |
-| worker `task(...)` | `multi_agent_v1.spawn_agent({"message":"TASK: act as <role>. ...","fork_context":false})` |
+| worker `task(...)` | `multi_agent_v1.spawn_agent({"message":"TASK: act as <role>. ...","fork_context":false})` — for implementation workers add `agent_type: "lazycodex-worker-<low|medium|high>"` when the spawn schema exposes `agent_type` |
 | `background_output(task_id="...")` | `multi_agent_v1.wait_agent(...)` for mailbox signals |
 | `team_*(...)` | `multi_agent_v1.spawn_agent` + `multi_agent_v1.send_input` + `multi_agent_v1.wait_agent` + `multi_agent_v1.close_agent` |
 
 When translating `load_skills=[...]`, name the skills inside the spawned agent's `message`. If a code block below conflicts with this section, this section wins.
 
-Codex exposes ONE of two subagent tool surfaces per session; check your own tool list and route accordingly. If `multi_agent_v1.*` tools exist, use the table above as written. If instead a flat `spawn_agent` with a required `task_name` exists (`multi_agent_v2`), rewrite every `multi_agent_v1.*` example: `multi_agent_v1.spawn_agent({...,"fork_context":false})` becomes `spawn_agent({"task_name":"<lowercase_digits_underscores>","message":...,"agent_type":...,"fork_turns":"none"})` (`"all"` only when full parent history is truly required); `send_input` becomes `send_message`; do not call `close_agent`/`resume_agent` (finished agents end on their own; `followup_task` re-tasks one, `interrupt_agent` stops one); `wait_agent` takes only `timeout_ms` and returns on any child mailbox activity. `agent_type` works the same on both surfaces. If a code block below conflicts with this section, this section wins.
+Codex exposes ONE of two subagent tool surfaces per session; check your own tool list and route accordingly. If `multi_agent_v1.*` tools exist, use the table above as written. If instead a flat `spawn_agent` with a required `task_name` exists (`multi_agent_v2`), rewrite every `multi_agent_v1.*` example: `multi_agent_v1.spawn_agent({...,"fork_context":false})` becomes `spawn_agent({"task_name":"<lowercase_digits_underscores>","message":...,"agent_type":...,"fork_turns":"none"})` (`"all"` only when full parent history is truly required); `send_input` becomes `send_message`; do not call `close_agent`/`resume_agent` (finished agents end on their own; `followup_task` re-tasks one, `interrupt_agent` stops one); `wait_agent` takes only `timeout_ms` and returns on any child mailbox activity. On the v2 surface `agent_type` may be absent from the spawn schema — when absent, omit it and describe the role inside `message`. If a code block below conflicts with this section, this section wins.
+
+### Delegation by difficulty (Codex tier workers)
+When tier worker agents are installed (Codex), size each implementation lane by difficulty and pass the matching `agent_type` where the spawn schema exposes it: LOW (one-file fix, boilerplate, config/copy) -> `lazycodex-worker-low`; MEDIUM (standard feature, few files, known patterns) -> `lazycodex-worker-medium`; HIGH (new module, cross-module refactor, concurrency/security/migration) -> `lazycodex-worker-high`. Explorer/librarian research lanes keep their own roles. Difficulty (model power) is orthogonal to the LIGHT/HEAVY rigor tier in step 4 — judge each on its own facts. On spawn surfaces without `agent_type` (deployed v2), state the tier inside `message`.
 
 ## Codex Subagent Reliability
 

package/packages/shared-skills/skills/ulw-plan/scripts/scaffold-plan.mjs

@@ -221,7 +221,7 @@ Your next move: <fill - e.g. approve, or run a high-accuracy review>. Full execu
 ## Verification strategy
 > Zero human intervention - all verification is agent-executed.
 - Test decision: <TDD | tests-after | none> + framework
-- Evidence: .omo/evidence/task-<N>-${slug}.<ext>
+- Evidence: <attemptDir>/task-<N>-${slug}.<ext> (attemptDir = currentAttemptDir from 'omo ulw-loop status --json', .omo/evidence/ulw/<session>/<goalId>/a<attempt>; outside ulw-loop use .omo/evidence/)
 
 ## Execution strategy
 ### Parallel execution waves
@@ -239,7 +239,7 @@ Your next move: <fill - e.g. approve, or run a high-accuracy review>. Full execu
   Parallelization: Wave <N> | Blocked by: <...> | Blocks: <...>
   References (executor has NO interview context - be exhaustive): <src/path:lines>
   Acceptance criteria (agent-executable): <exact command or assertion>
-  QA scenarios (name the exact tool + invocation): happy + failure, Evidence .omo/evidence/task-1-${slug}.<ext>
+  QA scenarios (name the exact tool + invocation): happy + failure, Evidence <attemptDir>/task-1-${slug}.<ext>
   Commit: <Y/N> | <type>(<scope>): <summary>
 
 ## Final verification wave

package/dist/skills/visual-qa/scripts/skill-prompt-contract.test.ts

@@ -1,296 +0,0 @@
-import { describe, expect, test } from "bun:test"
-import { existsSync, readFileSync } from "node:fs"
-import { dirname, join } from "node:path"
-
-const repoRoot = findRepoRoot(import.meta.dir)
-const sharedSkillPath = join(repoRoot, "packages", "shared-skills", "skills", "visual-qa", "SKILL.md")
-const codexSkillPath = join(repoRoot, "packages", "omo-codex", "plugin", "skills", "visual-qa", "SKILL.md")
-const referencesPath = join(
-	repoRoot,
-	"packages",
-	"shared-skills",
-	"skills",
-	"visual-qa",
-	"references",
-	"agent-browser-setup.md",
-)
-
-type PromptFixture = {
-	readonly label: string
-	readonly text: string
-}
-
-function readPrompt(path: string): string {
-	return readFileSync(path, "utf8")
-}
-
-function findRepoRoot(start: string): string {
-	let current = start
-	while (true) {
-		if (existsSync(join(current, "package.json")) && existsSync(join(current, "packages"))) {
-			return current
-		}
-		const parent = dirname(current)
-		if (parent === current) {
-			throw new Error(`repository root not found from ${start}`)
-		}
-		current = parent
-	}
-}
-
-function fixtures(): readonly PromptFixture[] {
-	const promptFixtures: PromptFixture[] = [{ label: "shared skill", text: readPrompt(sharedSkillPath) }]
-	if (existsSync(codexSkillPath)) {
-		promptFixtures.push({ label: "codex plugin copy", text: readPrompt(codexSkillPath) })
-	}
-	return promptFixtures
-}
-
-function sectionBetween(text: string, startMarker: string, endMarker: string): string {
-	const start = text.indexOf(startMarker)
-	if (start < 0) {
-		throw new Error(`missing start marker: ${startMarker}`)
-	}
-	const end = text.indexOf(endMarker, start + startMarker.length)
-	if (end < 0) {
-		throw new Error(`missing end marker: ${endMarker}`)
-	}
-	return text.slice(start, end)
-}
-
-describe("visual-qa skill prompt contract", () => {
-	test("#given visual QA prompts #when dispatching pass B #then the oracle must directly inspect screenshots and content for CJK wrapping", () => {
-		for (const fixture of fixtures()) {
-			const passB = sectionBetween(fixture.text, "### Pass B", "## Step 4")
-			const lowerPassB = passB.toLowerCase()
-
-			expect(lowerPassB, fixture.label).toContain("directly open")
-			expect(lowerPassB, fixture.label).toContain("view_image")
-			expect(lowerPassB, fixture.label).toContain("source code")
-			expect(passB, fixture.label).toContain("[Image #1]")
-			expect(passB, fixture.label).toContain("semantic phrases")
-			expect(passB, fixture.label).toContain("놀라운 변 / 화")
-			expect(passB, fixture.label).toContain("에이전트 오케스트")
-			expect(passB, fixture.label).toContain("레이션 현황 및 미")
-			expect(passB, fixture.label).toContain("래")
-			expect(passB, fixture.label).toContain("REVISE/FAIL")
-		}
-	})
-
-	test("#given visual QA prompts #when dispatching pass A #then the oracle must reject mock-only UI instead of accepting superficial screenshots", () => {
-		for (const fixture of fixtures()) {
-			const passA = sectionBetween(fixture.text, "### Pass A", "### Pass B")
-			const checkBlock = sectionBetween(passA, "CHECK EACH:", "OUTPUT:")
-			const outputBlock = sectionBetween(passA, "OUTPUT:", '"""')
-			const lowerCheckBlock = checkBlock.toLowerCase()
-
-			expect(lowerCheckBlock, fixture.label).toContain("mock-only")
-			expect(lowerCheckBlock, fixture.label).toContain("faked-with-an-image")
-			expect(lowerCheckBlock, fixture.label).toContain("coherent design tokens")
-			expect(lowerCheckBlock, fixture.label).toContain("reused primitives")
-			expect(lowerCheckBlock, fixture.label).toContain("blocking")
-			expect(outputBlock, fixture.label).toContain("BLOCKING:")
-		}
-	})
-
-	test("#given the Web capture path #when no browser tooling is configured #then it falls back to agent-browser", () => {
-		for (const fixture of fixtures()) {
-			const web = sectionBetween(fixture.text, "### Web", "### TUI")
-
-			expect(web, fixture.label).toContain("agent-browser")
-			expect(fixture.text, fixture.label).toContain("npm install -g agent-browser")
-			expect(fixture.text, fixture.label).toContain("https://github.com/vercel-labs/agent-browser")
-			expect(fixture.text, fixture.label).toContain("references/agent-browser-setup.md")
-		}
-	})
-
-	test("#given the agent-browser fallback #when documenting setup #then a references doc lists install, link, and help", () => {
-		expect(existsSync(referencesPath)).toBe(true)
-		const doc = readFileSync(referencesPath, "utf8")
-
-		expect(doc).toContain("npm install -g agent-browser")
-		expect(doc).toContain("agent-browser install")
-		expect(doc).toContain("https://github.com/vercel-labs/agent-browser")
-		expect(doc).toContain("agent-browser --help")
-	})
-
-	test("#given the visual QA evidence commands #when documented #then they use the Node bundle, not a Bun-only TypeScript launcher", () => {
-		for (const fixture of fixtures()) {
-			expect(fixture.text, fixture.label).toContain('node "$SKILL_DIR/scripts/visual-qa.mjs" image-diff')
-			expect(fixture.text, fixture.label).toContain('node "$SKILL_DIR/scripts/visual-qa.mjs" tui-check')
-			expect(fixture.text, fixture.label).not.toContain('bun "$SKILL_DIR/scripts/cli.ts"')
-		}
-	})
-
-	test("#given a concrete visual target #when in reference-fidelity mode #then dual pixel + code-fidelity verification loops until both pass", () => {
-		for (const fixture of fixtures()) {
-			const cloneMode = sectionBetween(fixture.text, "## Step 5", "## Reference evidence is not the verdict")
-			const lowerCloneMode = cloneMode.toLowerCase()
-
-			expect(lowerCloneMode, fixture.label).toContain("clone")
-			expect(lowerCloneMode, fixture.label).toContain("imagen")
-			expect(lowerCloneMode, fixture.label).toContain("stitch")
-			expect(lowerCloneMode, fixture.label).toContain("generated mockup")
-			expect(lowerCloneMode, fixture.label).toContain("overview")
-			expect(cloneMode, fixture.label).toContain("pixel-by-pixel")
-			expect(cloneMode, fixture.label).toContain("image-diff")
-			expect(cloneMode, fixture.label).toContain("lazycodex-clone-fidelity-reviewer")
-			expect(lowerCloneMode, fixture.label).toContain("extensible state variants")
-			expect(lowerCloneMode, fixture.label).toContain("retry")
-		}
-	})
-})
-
-describe("visual-qa skill exhaustive-coverage and review-gate contract", () => {
-	test("#given a multi-page surface #when capturing #then every page is enumerated and verified per page, not sampled", () => {
-		for (const fixture of fixtures()) {
-			const capture = sectionBetween(fixture.text, "## Step 2", "## Step 3")
-			const lower = capture.toLowerCase()
-
-			expect(lower, fixture.label).toContain("every page")
-			expect(lower, fixture.label).toContain("enumerate")
-			expect(lower, fixture.label).toContain("never sample")
-			expect(lower, fixture.label).toContain("per page")
-			expect(lower, fixture.label).toContain("one failing page fails")
-		}
-	})
-
-	test("#given prior QA artifacts #when verifying #then stale evidence older than the source must be regenerated", () => {
-		for (const fixture of fixtures()) {
-			const capture = sectionBetween(fixture.text, "## Step 2", "## Step 3")
-			const lower = capture.toLowerCase()
-
-			expect(lower, fixture.label).toContain("stale")
-			expect(lower, fixture.label).toContain("older than")
-			expect(lower, fixture.label).toContain("regenerate")
-		}
-	})
-
-	test("#given Step 3 dispatch #when running the review #then it is required pre-done, harness-native, and covers every enumerated page", () => {
-		for (const fixture of fixtures()) {
-			const dispatch = sectionBetween(fixture.text, "## Step 3", "### Pass A")
-			const lower = dispatch.toLowerCase()
-
-			expect(lower, fixture.label).toContain("required before")
-			expect(lower, fixture.label).toContain("do not self-review")
-			expect(dispatch, fixture.label).toContain("spawn_agent")
-			expect(dispatch, fixture.label).toContain("lazycodex-gate-reviewer")
-			expect(lower, fixture.label).toContain("every enumerated page")
-		}
-	})
-
-	test("#given the completion gate #when deciding done #then an independent reviewer must PASS on a fresh full capture, looping until clean", () => {
-		for (const fixture of fixtures()) {
-			const gate = sectionBetween(fixture.text, "## Step 4", "## Step 5")
-			const lower = gate.toLowerCase()
-
-			expect(lower, fixture.label).toContain("hard stop rule")
-			expect(lower, fixture.label).toContain("independent")
-			expect(lower, fixture.label).toContain("no blocking")
-			expect(lower, fixture.label).toContain("fresh")
-			expect(lower, fixture.label).toContain("every enumerated page")
-			expect(lower, fixture.label).toContain("loop until")
-			expect(lower, fixture.label).toContain("do not stop because the automated script")
-		}
-	})
-
-	test("#given Pass B CJK checks #when inspecting #then it flags topic, connective, and source-citation splits across every page", () => {
-		for (const fixture of fixtures()) {
-			const passB = sectionBetween(fixture.text, "### Pass B", "## Step 4")
-			const lower = passB.toLowerCase()
-
-			expect(passB, fixture.label).toContain("두 강은")
-			expect(passB, fixture.label).toContain("쓸 수")
-			expect(passB, fixture.label).toContain("Attention Is")
-			expect(lower, fixture.label).toContain("citation")
-			expect(lower, fixture.label).toContain("every page")
-			expect(lower, fixture.label).toContain("regardless of similarityscore")
-		}
-	})
-
-	test("#given a generated reference packet #when reviewing #then Pass A and B require extensible design-system code and pixel-level reference matching", () => {
-		for (const fixture of fixtures()) {
-			const passA = sectionBetween(fixture.text, "### Pass A", "### Pass B")
-			const passB = sectionBetween(fixture.text, "### Pass B", "## Step 4")
-			const lowerPassA = passA.toLowerCase()
-			const lowerPassB = passB.toLowerCase()
-
-			expect(passA, fixture.label).toContain("REFERENCE PACKET:")
-			expect(passB, fixture.label).toContain("REFERENCE PACKET:")
-			expect(lowerPassA, fixture.label).toContain("reusable tokens/primitives")
-			expect(lowerPassA, fixture.label).toContain("extend to new pages")
-			expect(lowerPassA, fixture.label).toContain("missing overview content")
-			expect(lowerPassB, fixture.label).toContain("pixel-perfectly")
-			expect(lowerPassB, fixture.label).toContain("actual against reference")
-			expect(lowerPassB, fixture.label).toContain("overview text is part of the target")
-		}
-	})
-
-	test("#given reference packet evidence #when prompting reviewers #then sensitive content is redacted and annotations stay untrusted data", () => {
-		for (const fixture of fixtures()) {
-			const capture = sectionBetween(fixture.text, "## Step 2", "## Step 3")
-			const passA = sectionBetween(fixture.text, "### Pass A", "### Pass B")
-			const passB = sectionBetween(fixture.text, "### Pass B", "## Step 4")
-			const combined = `${capture}\n${passA}\n${passB}`.toLowerCase()
-
-			expect(combined, fixture.label).toContain("redact or omit secrets")
-			expect(combined, fixture.label).toContain("credentials")
-			expect(combined, fixture.label).toContain("tokens")
-			expect(combined, fixture.label).toContain("auth headers")
-			expect(combined, fixture.label).toContain("customer data")
-			expect(combined, fixture.label).toContain("private messages")
-			expect(combined, fixture.label).toContain("internal urls")
-			expect(combined, fixture.label).toContain("other sensitive content")
-			expect(combined, fixture.label).toContain("overview text")
-			expect(combined, fixture.label).toContain("annotations")
-			expect(combined, fixture.label).toContain("untrusted data")
-			expect(combined, fixture.label).toContain("captured ui copy")
-			expect(combined, fixture.label).toContain("comments")
-			expect(combined, fixture.label).toContain("filenames")
-			expect(combined, fixture.label).toContain("not reviewer instructions")
-			expect(combined, fixture.label).toContain("never as instructions")
-		}
-	})
-})
-
-describe("visual-qa motion capture and slop-animation contract", () => {
-	test("#given an animated or interactive surface #when capturing #then rest, mid-transition and settled frames are driven and captured", () => {
-		for (const fixture of fixtures()) {
-			const motion = sectionBetween(fixture.text, "### Motion and interaction capture", "## Step 3")
-			const lower = motion.toLowerCase()
-
-			expect(lower, fixture.label).toContain("rest")
-			expect(lower, fixture.label).toContain("mid-transition")
-			expect(lower, fixture.label).toContain("settled")
-			expect(lower, fixture.label).toContain("hover")
-			expect(lower, fixture.label).toContain("focus")
-			expect(lower, fixture.label).toContain("click")
-			expect(lower, fixture.label).toContain("scroll-triggered")
-			expect(lower, fixture.label).toContain("load animation")
-		}
-	})
-
-	test("#given animation-induced pixel diff #when judging fidelity #then it is never an excuse to dismiss a defect", () => {
-		for (const fixture of fixtures()) {
-			const motion = sectionBetween(fixture.text, "### Motion and interaction capture", "## Step 3")
-			const lower = motion.toLowerCase()
-
-			expect(lower, fixture.label).toContain("never a valid excuse")
-			expect(lower, fixture.label).toContain("settled state to settled state")
-			expect(lower, fixture.label).toContain("reference's own motion")
-		}
-	})
-
-	test("#given meaningless motion #when reviewing #then Pass A flags slop animation, especially hover-without-action", () => {
-		for (const fixture of fixtures()) {
-			const passA = sectionBetween(fixture.text, "### Pass A", "### Pass B")
-			const checkBlock = sectionBetween(passA, "CHECK EACH:", "OUTPUT:")
-			const lower = checkBlock.toLowerCase()
-
-			expect(lower, fixture.label).toContain("slop animation")
-			expect(lower, fixture.label).toContain("non-interactive")
-			expect(lower, fixture.label).toContain("no state change")
-			expect(lower, fixture.label).toContain("hover-without-action")
-		}
-	})
-})

package/packages/omo-codex/plugin/components/ulw-loop/test/skill-contract.test.ts

@@ -1,70 +0,0 @@
-import { readFile } from "node:fs/promises";
-
-import { describe, expect, it } from "vitest";
-
-const SKILL_URL = new URL("../skills/ulw-loop/SKILL.md", import.meta.url);
-const FULL_WORKFLOW_URL = new URL("../skills/ulw-loop/references/full-workflow.md", import.meta.url);
-
-function wordCount(text: string): number {
-	return text.split(/\s+/).filter(Boolean).length;
-}
-
-describe("ulw-loop skill contract", () => {
-	it("#given full workflow #when tier triage is inspected #then criteria scale by LIGHT/HEAVY with upgrade-only ratchet", async () => {
-		// given
-		const workflow = await readFile(FULL_WORKFLOW_URL, "utf8");
-
-		// then
-		expect(workflow).toMatch(/[Tt]ier triage/);
-		expect(workflow).toMatch(/LIGHT/);
-		expect(workflow).toMatch(/HEAVY/);
-		expect(workflow).toMatch(/1-2 successCriteria/);
-		expect(workflow).toMatch(/3\+ criteria|3\+ successCriteria/);
-		expect(workflow).toMatch(/When unsure[^.]{0,30}HEAVY/);
-		expect(workflow).toMatch(/never downgrade/i);
-	});
-
-	it("#given full workflow #when evidence rules are inspected #then tautological tests are rejected and the light quality gate is named", async () => {
-		// given
-		const workflow = await readFile(FULL_WORKFLOW_URL, "utf8");
-
-		// then
-		expect(workflow).toMatch(/mirrors its implementation/);
-		expect(workflow).toMatch(/none-applicable/);
-	});
-
-	it("#given full workflow #when optimization work is planned #then speed and behavior evidence are required per attempt", async () => {
-		// given
-		const workflow = await readFile(FULL_WORKFLOW_URL, "utf8");
-
-		// then
-		expect(workflow).toMatch(/(?:optimization|performance) work[^.]+baseline speed[^.]+before/i);
-		expect(workflow).toMatch(/baseline speed[^.]+behavior[^.]+regression/i);
-		expect(workflow).toMatch(
-			/(?:each|every) (?:try|attempt)[^.]+speed[^.]+(?:behavior|regression)[^.]+(?:keep|revert|iterate)/i,
-		);
-	});
-
-	it("#given full workflow #when checkpoint guidance is inspected #then non-final and final criteria gates differ", async () => {
-		// given
-		const workflow = await readFile(FULL_WORKFLOW_URL, "utf8");
-
-		// then
-		expect(workflow).toMatch(/non-final aggregate goal[^.]+essential[^.]+pass/i);
-		expect(workflow).toMatch(/non-essential criteria may remain pending/i);
-		expect(workflow).toMatch(/final aggregate goal[^.]+every criterion across the whole plan/i);
-		expect(workflow).toMatch(/final aggregate completion requires all criteria across the whole plan/i);
-		expect(workflow).toMatch(/5 cycles on one goal without required criteria passing/i);
-	});
-
-	it("#given full workflow #when echo discipline is inspected #then the ultraqa class list is enumerated once and budgets hold", async () => {
-		// given
-		const workflow = await readFile(FULL_WORKFLOW_URL, "utf8");
-		const skill = await readFile(SKILL_URL, "utf8");
-
-		// then
-		expect(workflow.match(/malformed input, prompt injection/g)?.length ?? 0).toBe(1);
-		expect(wordCount(workflow)).toBeLessThanOrEqual(3697);
-		expect(wordCount(skill)).toBeLessThanOrEqual(625);
-	});
-});