sneakoscope 0.6.90 → 0.6.93

package/README.md

@@ -2,7 +2,7 @@
 
 ![](https://github.com/mandarange/Sneakoscope-Codex/raw/dev/docs/assets/sneakoscope-codex-logo.png)
 
-Sneakoscope Codex (`sks`, displayed as `ㅅㅋㅅ`) is a Codex CLI/App harness for repeatable agent workflows. It adds terminal commands, Codex App `$` prompt commands, warp-native CLI workspaces, Team/Goal/QA/Research routes, Context7 evidence checks, DB safety, TriWiki context tracking, Honest Mode, and release-readiness gates.
+Sneakoscope Codex (`sks`, displayed as `ㅅㅋㅅ`) is a Codex CLI/App harness for repeatable agent workflows. It adds terminal commands, Codex App `$` prompt commands, warp-native CLI workspaces, Team/QA/Research routes, a maximum-speed Computer Use lane, a fast Goal bridge for native `/goal` persistence, Context7 evidence checks, DB safety, TriWiki context tracking, Honest Mode, and release-readiness gates.
 
 ## Quick Start
 
@@ -48,7 +48,8 @@ sks selftest --mock
 | Team orchestration | Runs substantial work through ambiguity handling, scouts, TriWiki refresh, debate, runtime task graphs, worker inboxes, implementation, review, cleanup, reflection, and Honest Mode. |
 | From-Chat-IMG | Turns chat screenshots plus original attachments into source-bound work orders, then requires scoped QA evidence before completion. |
 | QA loop | Dogfoods UI/API behavior with safety gates, Codex Computer Use-only UI evidence, safe fixes, and rechecks. |
-| Goal | Bridges SKS pipeline state to Codex native persisted `/goal` create, pause, resume, and clear workflows. |
+| Computer Use fast lane | Uses `$Computer-Use` / `$CU` for UI/browser/visual work that needs maximum speed: skip Team debate and upfront TriWiki loops, use Codex Computer Use directly, then refresh/validate TriWiki and run Honest Mode at final closeout. |
+| Goal | Provides a fast SKS bridge overlay for Codex native persisted `/goal` create, pause, resume, and clear controls; implementation continues through the selected SKS execution route. |
 | TriWiki voxels | Maintains `.sneakoscope/wiki/context-pack.json` as the context SSOT with coordinate anchors, voxel metadata, `attention.use_first`, and `attention.hydrate_first`. |
 | Context7 | Requires current docs for external packages, APIs, MCPs, SDKs, and framework/runtime behavior when correctness depends on current guidance. |
 | DB safety | Treats SQL, migrations, Supabase, RLS, and destructive operations as high risk. |
@@ -201,7 +202,7 @@ Agent sessions communicate through the bounded Team transcript. Use `sks team me
 
 When the Team route reaches `session_cleanup`, SKS marks the Warp launch record complete and asks `watch --follow` / `lane --follow` panes to show a cleanup summary and stop. You can also run `sks team cleanup-warp <mission-id|latest>` manually, or `sks team cleanup-warp latest --close` to remove the generated Launch Configuration. Warp's public URI/Launch Configuration surface does not expose a live pane-close API, so the panes remain user-controlled.
 
-### QA, Goal, Research, DB, Wiki, GX
+### QA, Computer Use, Goal, Research, DB, Wiki, GX
 
 ```sh
 sks qa-loop prepare "http://localhost:3000"
@@ -222,6 +223,10 @@ sks proof-field scan --json --intent "small CLI change"
 sks code-structure scan --json
 ```
 
+`sks goal` and `$Goal` only prepare/control the native `/goal` persistence bridge. They do not replace Team, QA, DB, or other implementation routes; use the selected execution route for the actual work and verification. Context7 is only needed for Goal when external API/library documentation becomes relevant.
+
+Use `$Computer-Use` or `$CU` inside Codex App when the task specifically needs Codex Computer Use speed for UI/browser/visual work. This lane intentionally skips Team debate, QA-LOOP clarification, subagents, and upfront TriWiki refresh. It still requires Codex Computer Use as the evidence source, and it defers TriWiki refresh/validate plus Honest Mode to the final closeout.
+
 ## Codex App Usage
 
 Sneakoscope has two surfaces:
@@ -276,7 +281,8 @@ Use these inside Codex App or another agent prompt. They are prompt commands, no
 | `$Answer` | You want an answer only and no implementation should start. |
 | `$SKS` | You need setup, status, usage, or workflow help. |
 | `$QA-LOOP` | You want UI/API dogfooding, safe fixes, and rechecks. |
-| `$Goal` | You want Codex native persisted `/goal` continuation for a workflow. |
+| `$Computer-Use` / `$CU` | You want the fastest Codex Computer Use lane for UI/browser/visual inspection or small safe fixes. |
+| `$Goal` | You want a fast SKS bridge overlay for Codex native persisted `/goal` continuation. |
 | `$Research` | You need frontier-style research with hypotheses and falsification. |
 | `$AutoResearch` | You want iterative improve/test/keep-or-discard optimization. |
 | `$DB` | You need database, Supabase, migration, SQL, or MCP safety checks. |

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "sneakoscope",
   "displayName": "ㅅㅋㅅ",
-  "version": "0.6.90",
+  "version": "0.6.93",
   "description": "Sneakoscope Codex: database-safe Codex CLI/App harness with Team, Goal, AutoResearch, TriWiki, and Honest Mode.",
   "type": "module",
   "homepage": "https://github.com/mandarange/Sneakoscope-Codex#readme",

package/src/cli/main.mjs

@@ -523,7 +523,7 @@ async function updateCheck(args = []) {
   if (result.update_available) console.log('Run:     npm i -g sneakoscope');
 }
 
-const DOLLAR_DEFAULT_PIPELINE_TEXT = 'Default pipeline: questions -> $Answer, small design/content -> $DFix, code -> $Team. Use $From-Chat-IMG only for chat screenshot plus original attachments. Use $MAD-SKS only as an explicit scoped DB authorization modifier that can be combined with another $ route. No route may invent unrequested fallback implementation code.';
+const DOLLAR_DEFAULT_PIPELINE_TEXT = 'Default pipeline: questions -> $Answer, small design/content -> $DFix, Computer Use UI/browser speed work -> $Computer-Use, code -> $Team. Use $From-Chat-IMG only for chat screenshot plus original attachments. Use $MAD-SKS only as an explicit scoped DB authorization modifier that can be combined with another $ route. No route may invent unrequested fallback implementation code.';
 
 function commands(args = []) {
   if (flag(args, '--json')) return console.log(JSON.stringify({ aliases: ['sks', 'sneakoscope'], dollar_commands: DOLLAR_COMMANDS, app_skill_aliases: DOLLAR_COMMAND_ALIASES, commands: COMMAND_CATALOG }, null, 2));
@@ -2249,6 +2249,31 @@ async function selftest() {
   const hookState = await readJson(stateFile(hookGoalTmp), {});
   if (hookState.phase !== 'GOAL_READY' || hookState.mode !== 'GOAL') throw new Error('selftest failed: $Goal hook did not set ready state');
   if (!(await exists(path.join(missionDir(hookGoalTmp, hookState.mission_id), GOAL_WORKFLOW_ARTIFACT)))) throw new Error('selftest failed: $Goal hook did not write goal workflow artifact');
+  const hookGoalDelegationTmp = tmpdir();
+  await initProject(hookGoalDelegationTmp, {});
+  const hookGoalDelegationPayload = JSON.stringify({ cwd: hookGoalDelegationTmp, prompt: '$Goal 설치 화면 문제 근본적으로 구현 수정해줘' });
+  const hookGoalDelegationResult = await runProcess(process.execPath, [hookBin, 'hook', 'user-prompt-submit'], { cwd: hookGoalDelegationTmp, input: hookGoalDelegationPayload, env: { SKS_DISABLE_UPDATE_CHECK: '1' }, timeoutMs: 15000, maxOutputBytes: 256 * 1024 });
+  if (hookGoalDelegationResult.code !== 0) throw new Error(`selftest failed: $Goal implementation delegation hook exited ${hookGoalDelegationResult.code}: ${hookGoalDelegationResult.stderr}`);
+  const hookGoalDelegationJson = JSON.parse(hookGoalDelegationResult.stdout);
+  const hookGoalDelegationContext = hookGoalDelegationJson.hookSpecificOutput?.additionalContext || '';
+  const hookGoalDelegationBridgeMatch = hookGoalDelegationContext.match(/Goal bridge mission: (M-[A-Za-z0-9-]+)/);
+  if (!hookGoalDelegationBridgeMatch || !hookGoalDelegationContext.includes('Delegated execution route: $Team')) throw new Error('selftest failed: $Goal implementation prompt did not prepare a bridge plus Team delegation');
+  if (!hookGoalDelegationContext.includes('MANDATORY ambiguity-removal gate activated') || !hookGoalDelegationContext.includes('Route: $Team')) throw new Error('selftest failed: $Goal implementation delegation did not prepare Team ambiguity gate');
+  const hookGoalDelegationState = await readJson(stateFile(hookGoalDelegationTmp), {});
+  if (hookGoalDelegationState.mode !== 'TEAM' || hookGoalDelegationState.phase !== 'TEAM_CLARIFICATION_AWAITING_ANSWERS' || hookGoalDelegationState.implementation_allowed !== false) throw new Error('selftest failed: $Goal implementation delegation did not leave Team gate current');
+  if (!(await exists(path.join(missionDir(hookGoalDelegationTmp, hookGoalDelegationBridgeMatch[1]), GOAL_WORKFLOW_ARTIFACT)))) throw new Error('selftest failed: $Goal implementation delegation did not write bridge workflow artifact');
+  const activeGoalMissionId = hookState.mission_id;
+  const hookGoalOverlayPayload = JSON.stringify({ cwd: hookGoalTmp, prompt: '설치 화면 문제 근본적으로 구현 수정해줘' });
+  const hookGoalOverlayResult = await runProcess(process.execPath, [hookBin, 'hook', 'user-prompt-submit'], { cwd: hookGoalTmp, input: hookGoalOverlayPayload, env: { SKS_DISABLE_UPDATE_CHECK: '1' }, timeoutMs: 15000, maxOutputBytes: 256 * 1024 });
+  if (hookGoalOverlayResult.code !== 0) throw new Error(`selftest failed: active Goal overlay hook exited ${hookGoalOverlayResult.code}: ${hookGoalOverlayResult.stderr}`);
+  const hookGoalOverlayJson = JSON.parse(hookGoalOverlayResult.stdout);
+  const hookGoalOverlayContext = hookGoalOverlayJson.hookSpecificOutput?.additionalContext || '';
+  if (!hookGoalOverlayContext.includes('MANDATORY ambiguity-removal gate activated') || !hookGoalOverlayContext.includes('Route: $Team')) throw new Error('selftest failed: active Goal hijacked a plain Korean implementation prompt instead of preparing Team');
+  if (!hookGoalOverlayContext.includes(`Active Goal overlay: existing Goal mission ${activeGoalMissionId}`) || !hookGoalOverlayContext.includes('goal-workflow.json')) throw new Error('selftest failed: active Goal overlay context was not included with the new route');
+  if (hookGoalOverlayContext.indexOf('MANDATORY ambiguity-removal gate activated') > hookGoalOverlayContext.indexOf('Active Goal overlay:')) throw new Error('selftest failed: active Goal overlay appeared before the newly prepared Team gate');
+  const hookGoalOverlayState = await readJson(stateFile(hookGoalTmp), {});
+  if (hookGoalOverlayState.mission_id === activeGoalMissionId || hookGoalOverlayState.mode !== 'TEAM' || hookGoalOverlayState.phase !== 'TEAM_CLARIFICATION_AWAITING_ANSWERS' || hookGoalOverlayState.implementation_allowed !== false) throw new Error('selftest failed: active Goal overlay did not leave a new Team ambiguity mission current');
+  if (!(await exists(path.join(missionDir(hookGoalTmp, hookGoalOverlayState.mission_id), 'required-answers.schema.json')))) throw new Error('selftest failed: active Goal overlay Team mission did not write ambiguity schema');
   const hookUpdateCurrentTmp = tmpdir();
   await initProject(hookUpdateCurrentTmp, {});
   const hookUpdateCurrentPayload = JSON.stringify({ cwd: hookUpdateCurrentTmp, prompt: '상태 확인해줘' });
@@ -2796,6 +2821,7 @@ async function selftest() {
   if (!warpTeam.launch_uri?.includes(encodeURIComponent(`sks-team-${teamId}.yaml`))) throw new Error('selftest failed: Team warp launch URI is not named for visibility');
   if (routeReasoning(routePrompt('$Research frontier idea'), '$Research frontier idea').effort !== 'xhigh') throw new Error('selftest failed: research reasoning not xhigh');
   if (routeReasoning(routePrompt('$From-Chat-IMG 채팅 이미지 작업'), '$From-Chat-IMG 채팅 이미지 작업').effort !== 'xhigh') throw new Error('selftest failed: From-Chat-IMG reasoning not xhigh');
+  if (routeReasoning(routePrompt('$Computer-Use localhost UI smoke'), '$Computer-Use localhost UI smoke').effort !== 'low') throw new Error('selftest failed: Computer Use fast lane reasoning not low');
   if (routeReasoning(routePrompt('$DB migration'), '$DB migration').effort !== 'high') throw new Error('selftest failed: logical reasoning not high');
   const lowReasoning = routeReasoning({ id: 'LowSmoke', reasoningPolicy: 'low' }, 'small metadata read');
   if (lowReasoning.effort !== 'low' || lowReasoning.profile !== 'sks-task-low') throw new Error('selftest failed: low reasoning did not route to sks-task-low');
@@ -2835,13 +2861,19 @@ async function selftest() {
   if (routePrompt('implement feature')?.id !== 'Team') throw new Error('selftest failed: implementation prompt did not default to Team');
   if (routePrompt('$SKS implement feature')?.id !== 'Team') throw new Error('selftest failed: $SKS implementation prompt did not promote to Team');
   if (routePrompt('$From-Chat-IMG 채팅 기록 이미지와 첨부 이미지로 고객사 요청 수정 작업 수행해줘')?.id !== 'Team') throw new Error('selftest failed: explicit chat capture client work did not promote to Team');
+  if (routePrompt('$Computer-Use localhost 화면 빠르게 검증해줘')?.id !== 'ComputerUse') throw new Error('selftest failed: $Computer-Use did not route to ComputerUse fast lane');
+  if (routePrompt('$CU localhost 화면 빠르게 검증해줘')?.id !== 'ComputerUse') throw new Error('selftest failed: $CU did not route to ComputerUse fast lane');
+  if (routePrompt('computer use 사용하는 파이프라인은 마지막에 triwiki honest mode만 실행되게 조정해줘')?.id !== 'ComputerUse') throw new Error('selftest failed: Computer Use pipeline request was misrouted away from fast lane');
+  if (routePrompt('triwiki나 honest mode가 마지막에만 실행되게 computer use 파이프라인 조정해줘')?.id !== 'ComputerUse') throw new Error('selftest failed: Computer Use directive was hijacked by Wiki route');
   if (routePrompt('$SKS show me available workflows')?.id !== 'SKS') throw new Error('selftest failed: $SKS workflow discovery should remain SKS');
   if (routeRequiresSubagents(routePrompt('이 파이프라인은 왜 이렇게 동작해?'), '이 파이프라인은 왜 이렇게 동작해?')) throw new Error('selftest failed: Answer route requires subagents');
   if (!routeRequiresSubagents(routePrompt('implement feature'), 'implement feature')) throw new Error('selftest failed: default Team implementation route does not require subagents');
   if (!routeRequiresSubagents(routePrompt('$Team implement feature'), '$Team implement feature')) throw new Error('selftest failed: Team route does not require subagents');
+  if (routeRequiresSubagents(routePrompt('$Computer-Use localhost UI smoke'), '$Computer-Use localhost UI smoke')) throw new Error('selftest failed: Computer Use fast lane requires subagents');
   if (!routeRequiresSubagents(routePrompt('$Goal implement feature'), '$Goal implement feature')) throw new Error('selftest failed: Goal implementation route does not require subagents');
   if (routeRequiresSubagents(routePrompt('$Help commands'), '$Help commands')) throw new Error('selftest failed: Help route incorrectly requires subagents');
   if (!reflectionRequiredForRoute(routePrompt('$Team implement feature'))) throw new Error('selftest failed: Team route does not require reflection');
+  if (reflectionRequiredForRoute(routePrompt('$Computer-Use localhost UI smoke'))) throw new Error('selftest failed: Computer Use fast lane requires full-route reflection');
   if (!reflectionRequiredForRoute(routePrompt('$DB migration'))) throw new Error('selftest failed: DB route does not require reflection');
   if (reflectionRequiredForRoute(routePrompt('$DFix button label'))) throw new Error('selftest failed: DFix route incorrectly requires reflection');
   if (reflectionRequiredForRoute(routePrompt('이 파이프라인은 왜 이렇게 동작해?'))) throw new Error('selftest failed: Answer route incorrectly requires reflection');

package/src/cli/maintenance-commands.mjs

@@ -354,7 +354,7 @@ async function goalCreate(args) {
   if (!prompt) throw new Error('Missing goal task prompt.');
   const { id, dir, mission } = await createMission(root, { mode: 'goal', prompt });
   const workflow = await writeGoalWorkflow(dir, mission, { action: 'create', prompt });
-  await setCurrent(root, { mission_id: id, mode: 'GOAL', route: 'Goal', route_command: '$Goal', phase: 'GOAL_READY', questions_allowed: true, implementation_allowed: true, native_goal: workflow.native_goal, stop_gate: 'honest_mode' });
+  await setCurrent(root, { mission_id: id, mode: 'GOAL', route: 'Goal', route_command: '$Goal', phase: 'GOAL_READY', questions_allowed: true, implementation_allowed: true, native_goal: workflow.native_goal, stop_gate: 'none' });
   console.log(`Goal mission created: ${id}`);
   console.log(`Artifact: ${path.relative(root, path.join(dir, GOAL_WORKFLOW_ARTIFACT))}`);
   console.log(`Bridge: ${path.relative(root, path.join(dir, GOAL_BRIDGE_ARTIFACT))}`);
@@ -367,7 +367,7 @@ async function goalControl(action, args) {
   if (!id) throw new Error(`Usage: sks goal ${action} <mission-id|latest>`);
   const { dir } = await loadMission(root, id);
   const workflow = await updateGoalWorkflow(dir, action);
-  await setCurrent(root, { mission_id: id, mode: 'GOAL', route: 'Goal', route_command: '$Goal', phase: `GOAL_${String(action).toUpperCase()}`, native_goal: workflow.native_goal, questions_allowed: true, implementation_allowed: action !== 'pause' && action !== 'clear' });
+  await setCurrent(root, { mission_id: id, mode: 'GOAL', route: 'Goal', route_command: '$Goal', phase: `GOAL_${String(action).toUpperCase()}`, native_goal: workflow.native_goal, questions_allowed: true, implementation_allowed: action !== 'pause' && action !== 'clear', stop_gate: 'none' });
   console.log(`Goal ${action}: ${id}`);
   console.log(`Native Codex control: ${workflow.native_goal.slash_command}`);
 }

package/src/core/fsx.mjs

@@ -5,7 +5,7 @@ import os from 'node:os';
 import crypto from 'node:crypto';
 import { spawn } from 'node:child_process';
 
-export const PACKAGE_VERSION = '0.6.90';
+export const PACKAGE_VERSION = '0.6.93';
 export const DEFAULT_PROCESS_TAIL_BYTES = 256 * 1024;
 export const DEFAULT_PROCESS_TIMEOUT_MS = 30 * 60 * 1000;
 

package/src/core/goal-workflow.mjs

@@ -26,15 +26,18 @@ export async function writeGoalWorkflow(dir, mission, opts = {}) {
     prompt,
     native_goal: {
       slash_command: nativeGoalCommand(action, prompt),
-      workflow_kind: 'persisted /goal',
+      workflow_kind: 'native /goal persistence bridge',
       controls: ['create', 'pause', 'resume', 'clear'],
       runtime_continuation: true,
       app_server_api_backed: true,
       model_tools_available: true
     },
     pipeline_contract: {
+      overlay_only: true,
       ralph_removed: true,
-      ambiguity_gate: 'use normal SKS ambiguity gates when required by the selected execution route; Goal itself delegates persistence/continuation to Codex /goal',
+      ambiguity_gate: 'Goal creates/controls the native /goal persistence bridge only; use normal SKS ambiguity gates on the selected execution route when implementation is needed',
+      context7: 'optional for Goal bridge/control unless external API/library documentation is involved',
+      implementation: 'continue implementation through the selected SKS execution route; Goal is not a heavyweight independent implementation pipeline',
       evidence: ['goal-workflow.json', 'goal-bridge.md']
     },
     phase: action === 'clear' ? 'reporting' : 'intake',
@@ -44,9 +47,9 @@ export async function writeGoalWorkflow(dir, mission, opts = {}) {
       {
         timestamp: nowIso(),
         phase: 'intake',
-        summary: 'Goal workflow bridge created.',
-        completed_checkboxes: ['goal workflow artifact written'],
-        open_checkboxes: ['continue original SKS route lifecycle when implementation is needed'],
+        summary: 'Goal workflow bridge created as a native /goal persistence overlay.',
+        completed_checkboxes: ['goal bridge artifact written'],
+        open_checkboxes: ['continue the selected SKS execution route when implementation is needed'],
         blockers: [],
         evidence: [GOAL_WORKFLOW_ARTIFACT, GOAL_BRIDGE_ARTIFACT]
       }
@@ -54,7 +57,7 @@ export async function writeGoalWorkflow(dir, mission, opts = {}) {
     resume_context: {
       stable_requirements: prompt ? [prompt] : [],
       current_files: [GOAL_WORKFLOW_ARTIFACT, GOAL_BRIDGE_ARTIFACT],
-      decisions: ['Codex native /goal is the persisted continuation surface'],
+      decisions: ['Codex native /goal is the persisted continuation surface', '$Goal is a lightweight bridge overlay, not an independent implementation pipeline'],
       known_mistakes_to_avoid: ['do not clear noisy context without writing a structured handoff first'],
       active_skills: ['goal'],
       active_agents: []
@@ -79,7 +82,7 @@ export async function updateGoalWorkflow(dir, action) {
     action,
     status: action === 'clear' ? 'cleared' : action === 'pause' ? 'paused' : action === 'resume' ? 'resumed' : current.status || 'created',
     updated_at: nowIso(),
-    phase: action === 'pause' ? 'reporting' : action === 'resume' ? 'implementation' : action === 'clear' ? 'retro' : current.phase || 'intake',
+    phase: action === 'pause' ? 'reporting' : action === 'resume' ? 'continuation' : action === 'clear' ? 'retro' : current.phase || 'intake',
     native_goal: {
       ...(current.native_goal || {}),
       slash_command: nativeGoalCommand(action, current.prompt || '')
@@ -89,7 +92,7 @@ export async function updateGoalWorkflow(dir, action) {
       {
         timestamp: nowIso(),
         phase: action,
-        summary: `Goal ${action} requested through SKS bridge.`,
+        summary: `Goal ${action} requested through native /goal bridge overlay.`,
         completed_checkboxes: [`goal ${action} artifact update`],
         open_checkboxes: action === 'clear' ? ['handoff preserved before noisy context clear'] : [],
         blockers: [],
@@ -104,7 +107,7 @@ export async function updateGoalWorkflow(dir, action) {
 }
 
 function goalBridgeMarkdown(workflow) {
-  return `# SKS Goal Bridge
+  return `# SKS Goal Persistence Bridge
 
 Mission: ${workflow.mission_id}
 Status: ${workflow.status}
@@ -118,11 +121,13 @@ Run this in the Codex TUI when interactive native goal control is available:
 ${workflow.native_goal.slash_command}
 \`\`\`
 
-## SKS Pipeline Contract
+## SKS Bridge Contract
 
 - Ralph route is removed from the user-facing SKS surface.
-- This mission uses Codex native persisted \`/goal\` workflow semantics for continuation.
+- This file is a fast SKS overlay for Codex native persisted \`/goal\` workflow semantics.
+- \`$Goal\` is not a heavyweight independent implementation pipeline.
 - SKS still records route evidence in \`${GOAL_WORKFLOW_ARTIFACT}\` and this bridge file.
-- If implementation work is needed, continue through the normal SKS route gates for that work and report verification evidence honestly.
+- If implementation work is needed, continue through the selected SKS execution route gates for that work and report verification evidence honestly.
+- Context7 is optional for Goal bridge/control unless external API/library documentation becomes relevant.
 `;
 }

package/src/core/hooks-runtime.mjs

@@ -113,6 +113,7 @@ async function hookUserPrompt(root, state, payload, noQuestion) {
     const command = dollarCommand(prompt);
     const route = routePrompt(prompt);
     const bypassActiveRoute = route?.id === 'DFix' || route?.id === 'Answer';
+    const goalOverlay = activeGoalOverlayContext(state, route);
     if (route?.id === 'DFix') await recordLightRouteStop(root, route, payload, prompt);
     if (isClarificationAwaiting(state) && !looksLikeClarificationCancel(prompt)) {
       const activeContext = await activeRouteContext(root, state);
@@ -123,8 +124,9 @@ async function hookUserPrompt(root, state, payload, noQuestion) {
     const teamDigest = bypassActiveRoute ? null : await teamLiveDigest(root, state);
     const activeContext = await activeRouteContext(root, state);
     const contexts = [updateContext];
-    if (activeContext && !command && !bypassActiveRoute) contexts.push(routePipelineContext(prompt), activeContext);
+    if (activeContext && !command && !bypassActiveRoute && !goalOverlay) contexts.push(routePipelineContext(prompt), activeContext);
     else contexts.push((await prepareRoute(root, prompt, state)).additionalContext);
+    if (goalOverlay) contexts.push(goalOverlay);
     if (teamDigest?.context) contexts.push(teamDigest.context);
     const additionalContext = contexts.filter(Boolean).join('\n\n');
     return { continue: true, additionalContext, systemMessage: joinSystemMessages(visibleHookMessage('user-prompt-submit', additionalContext), teamDigest?.system) };
@@ -146,6 +148,16 @@ function looksLikeClarificationCancel(prompt = '') {
   return /^(cancel|reset|restart|new mission|새로|취소|중단|리셋|다시 시작)\b/i.test(String(prompt || '').trim());
 }
 
+function activeGoalOverlayContext(state = {}, route = null) {
+  if (state.mode !== 'GOAL' || !state.mission_id) return '';
+  if (!route || route.id === 'Goal' || route.id === 'DFix' || route.id === 'Answer') return '';
+  return [
+    `Active Goal overlay: existing Goal mission ${state.mission_id} remains available for lightweight continuation context only.`,
+    `Do not let that active Goal hijack this new ${route.command || '$SKS'} prompt. The newly prepared route mission and gate are authoritative for this turn.`,
+    `Goal artifact: .sneakoscope/missions/${state.mission_id}/goal-workflow.json. Use Codex native /goal controls only if the user explicitly returns to $Goal.`
+  ].join('\n');
+}
+
 async function hookPreTool(root, state, payload, noQuestion) {
   const harnessDecision = await checkHarnessModification(root, payload, { phase: 'pre-tool' });
   if (harnessDecision.action === 'block') {
@@ -771,6 +783,7 @@ function visibleHookMessage(name, text = '') {
     if (body.includes('SKS answer-only pipeline active')) return 'SKS: answer-only research context injected.';
     if (body.includes('SKS wiki pipeline active')) return 'SKS: wiki refresh context injected.';
     if (body.includes('$Goal route prepared')) return 'SKS: Goal workflow bridge prepared for native Codex /goal continuation.';
+    if (body.includes('Computer Use fast lane active')) return 'SKS: Computer Use fast lane injected; defer TriWiki/Honest Mode to final closeout.';
     if (body.includes('MANDATORY ambiguity-removal gate') || body.includes('VISIBLE RESPONSE CONTRACT') || body.includes('Required questions still pending')) return 'SKS: clarification questions must be shown in chat before the route can continue.';
     if (body.includes('$Team route prepared') || body.includes('Team route')) return 'SKS: Team route, live transcript, and subagent plan injected.';
     if (body.includes('$QA-LOOP route prepared') || body.includes('QA-LOOP')) return 'SKS: QA-LOOP route and safety checklist injected.';

package/src/core/init.mjs

@@ -90,7 +90,7 @@ function isSksManagedHook(hook) {
   return hook.type === 'command' && /\bhook\s+(?:user-prompt-submit|pre-tool|post-tool|permission-request|stop)\b/.test(command) && /\b(?:sks|sneakoscope|sks\.mjs)\b/.test(command);
 }
 
-const AGENTS_BLOCK = "\n# Sneakoscope Codex Managed Rules\n\nThis repository uses Sneakoscope Codex.\n\n## Core Rules\n\n- Codex native `/goal` workflows are the persisted continuation surface; Ralph is removed from the user-facing SKS surface.\n- Keep runtime state bounded: raw logs go to files, prompts get tails/summaries, and `sks gc` may prune stale artifacts.\n- Before substantive work, SKS checks npm for a newer package. If newer, ask update-now vs skip-for-this-conversation.\n- Versioning is managed by the SKS pre-commit hook; check `sks versioning status`. Bypass only with `SKS_DISABLE_VERSIONING=1`.\n- Installed harness files are immutable to LLM edits: `.codex/*`, `.agents/skills/`, `.codex/agents/`, `.sneakoscope/*policy*.json`, `AGENTS.md`, and `node_modules/sneakoscope`. The Sneakoscope engine source repo is the only automatic exception.\n- OMX/DCodex conflicts block setup/doctor. Show `sks conflicts prompt`; cleanup requires explicit human approval.\n- Do not stop at a plan when implementation was requested. Finish, verify, or report the hard blocker.\n- Do not create unrequested fallback implementation code. If the requested path is impossible, block with evidence instead of inventing substitute behavior.\n\n## Routes\n\n- General execution/code-changing prompts default to `$Team`: analysis scouts, TriWiki refresh/validate, read-only debate, consensus, concrete runtime task graph/inboxes, fresh executor team, review, integration, Honest Mode.\n- `$Goal` bridges SKS pipeline state to Codex native `/goal` create/pause/resume/clear continuation controls.\n- TriWiki recall must stay bounded. Use `sks wiki sweep` to record demote, soft-forget, archive, delete, promote-to-skill, and promote-to-rule candidates instead of injecting every old claim.\n- Team missions must keep schema-backed evidence current: `work-order-ledger.json`, `effort-decision.json`, `team-dashboard-state.json`, and route-specific visual/dogfood artifacts where applicable. Use `sks validate-artifacts latest` before claiming those artifacts pass.\n- `$DFix` is only for tiny design/content edits and bypasses the main pipeline. `$Answer`, `$Help`, and `$Wiki` stay lightweight.\n- For code work, surface route/guard/write scopes first, split independent worker scopes when available, and keep parent-owned integration and verification.\n- Design work reads `design.md`; if missing, use `design-system-builder`. Image/logo/raster assets use `imagegen`.\n- Research, AutoResearch, performance, token, accuracy, SEO/GEO, or workflow-improvement claims need experiment/eval evidence. Do not claim live model accuracy without a scored dataset.\n- Treat handwritten files above 3000 lines as split-review risks. Run `sks code-structure scan` and prefer extraction before adding substantial logic.\n\n## Evidence And Context\n\n- Context7 is required for external libraries, APIs, MCPs, package managers, SDKs, and generated docs: resolve-library-id then query-docs.\n- When tech stack, framework, package, runtime, or deployment-platform versions change, use Context7 or official vendor web docs, record current syntax/security/limit guidance as high-priority TriWiki claims, then refresh and validate before coding.\n- TriWiki is the context-tracking SSOT for long-running missions, Team handoffs, and context-pressure recovery. Read `.sneakoscope/wiki/context-pack.json` before each stage, use `attention.use_first` for compact high-trust recall, hydrate `attention.hydrate_first` from source before risky or lower-trust decisions, refresh after findings or artifact changes, and validate before handoffs/final claims.\n- Source priority: current code/tests/config, decision contract, vgraph, beta, GX render/snapshot metadata, LLM Wiki coordinate index, then model knowledge only if allowed.\n- Final response before stop: summarize what was done, what changed for the user/repo, what was verified, and what remains unverified or blocked; then run Honest Mode. Say what passed and what was not verified.\n- `$From-Chat-IMG` uses forensic visual effort, not ordinary Team effort. Completion is blocked until source inventory, visual mapping, work-order coverage, scoped dogfood/QA, and post-fix verification artifacts are present and valid.\n\n## Safety\n\n- Database access is high risk. Use read-only inspection by default; live data mutation is out of scope unless a sealed contract allows local or branch-only migration files.\n- MAD and MAD-SKS widen only explicit scoped permissions; they still do not authorize unrequested fallback implementation code.\n- Task completion requires relevant tests or justification, zero unsupported critical claims, accepted visual/wiki drift, and final evidence.\n\n## Codex App\n\nUse `.codex/SNEAKOSCOPE.md`, generated `.agents/skills`, `.codex/hooks.json`, and SKS dollar commands (`$sks`, `$team`, `$goal`, `$dfix`, `$qa-loop`, etc.) as the app control surface.\n";
+const AGENTS_BLOCK = "\n# Sneakoscope Codex Managed Rules\n\nThis repository uses Sneakoscope Codex.\n\n## Core Rules\n\n- Codex native `/goal` workflows are the persisted continuation surface; Ralph is removed from the user-facing SKS surface.\n- Keep runtime state bounded: raw logs go to files, prompts get tails/summaries, and `sks gc` may prune stale artifacts.\n- Before substantive work, SKS checks npm for a newer package. If newer, ask update-now vs skip-for-this-conversation.\n- Versioning is managed by the SKS pre-commit hook; check `sks versioning status`. Bypass only with `SKS_DISABLE_VERSIONING=1`.\n- Installed harness files are immutable to LLM edits: `.codex/*`, `.agents/skills/`, `.codex/agents/`, `.sneakoscope/*policy*.json`, `AGENTS.md`, and `node_modules/sneakoscope`. The Sneakoscope engine source repo is the only automatic exception.\n- OMX/DCodex conflicts block setup/doctor. Show `sks conflicts prompt`; cleanup requires explicit human approval.\n- Do not stop at a plan when implementation was requested. Finish, verify, or report the hard blocker.\n- Do not create unrequested fallback implementation code. If the requested path is impossible, block with evidence instead of inventing substitute behavior.\n\n## Routes\n\n- General execution/code-changing prompts default to `$Team`: analysis scouts, TriWiki refresh/validate, read-only debate, consensus, concrete runtime task graph/inboxes, fresh executor team, review, integration, Honest Mode.\n- `$Computer-Use` / `$CU` is the maximum-speed Codex Computer Use lane for UI/browser/visual tasks: skip Team debate and upfront TriWiki loops, use Codex Computer Use directly, then refresh/validate TriWiki and run Honest Mode at final closeout.\n- `$Goal` is a fast bridge/overlay for Codex native `/goal` create/pause/resume/clear persistence controls; implementation continues through the selected SKS execution route.\n- TriWiki recall must stay bounded. Use `sks wiki sweep` to record demote, soft-forget, archive, delete, promote-to-skill, and promote-to-rule candidates instead of injecting every old claim.\n- Team missions must keep schema-backed evidence current: `work-order-ledger.json`, `effort-decision.json`, `team-dashboard-state.json`, and route-specific visual/dogfood artifacts where applicable. Use `sks validate-artifacts latest` before claiming those artifacts pass.\n- `$DFix` is only for tiny design/content edits and bypasses the main pipeline. `$Answer`, `$Help`, and `$Wiki` stay lightweight.\n- For code work, surface route/guard/write scopes first, split independent worker scopes when available, and keep parent-owned integration and verification.\n- Design work reads `design.md`; if missing, use `design-system-builder`. Image/logo/raster assets use `imagegen`.\n- Research, AutoResearch, performance, token, accuracy, SEO/GEO, or workflow-improvement claims need experiment/eval evidence. Do not claim live model accuracy without a scored dataset.\n- Treat handwritten files above 3000 lines as split-review risks. Run `sks code-structure scan` and prefer extraction before adding substantial logic.\n\n## Evidence And Context\n\n- Context7 is required for external libraries, APIs, MCPs, package managers, SDKs, and generated docs: resolve-library-id then query-docs.\n- When tech stack, framework, package, runtime, or deployment-platform versions change, use Context7 or official vendor web docs, record current syntax/security/limit guidance as high-priority TriWiki claims, then refresh and validate before coding.\n- TriWiki is the context-tracking SSOT for long-running missions, Team handoffs, and context-pressure recovery. Read `.sneakoscope/wiki/context-pack.json` before each stage, use `attention.use_first` for compact high-trust recall, hydrate `attention.hydrate_first` from source before risky or lower-trust decisions, refresh after findings or artifact changes, and validate before handoffs/final claims.\n- Source priority: current code/tests/config, decision contract, vgraph, beta, GX render/snapshot metadata, LLM Wiki coordinate index, then model knowledge only if allowed.\n- Final response before stop: summarize what was done, what changed for the user/repo, what was verified, and what remains unverified or blocked; then run Honest Mode. Say what passed and what was not verified.\n- `$From-Chat-IMG` uses forensic visual effort, not ordinary Team effort. Completion is blocked until source inventory, visual mapping, work-order coverage, scoped dogfood/QA, and post-fix verification artifacts are present and valid.\n\n## Safety\n\n- Database access is high risk. Use read-only inspection by default; live data mutation is out of scope unless a sealed contract allows local or branch-only migration files.\n- MAD and MAD-SKS widen only explicit scoped permissions; they still do not authorize unrequested fallback implementation code.\n- Task completion requires relevant tests or justification, zero unsupported critical claims, accepted visual/wiki drift, and final evidence.\n\n## Codex App\n\nUse `.codex/SNEAKOSCOPE.md`, generated `.agents/skills`, `.codex/hooks.json`, and SKS dollar commands (`$sks`, `$team`, `$computer-use`, `$cu`, `$goal`, `$dfix`, `$qa-loop`, etc.) as the app control surface.\n";
 
 export async function initProject(root, opts = {}) {
   const created = [];
@@ -534,7 +534,10 @@ export async function installSkills(root) {
     'team': `---\nname: team\ndescription: SKS Team orchestration for $Team/code work; $From-Chat-IMG is the explicit chat-image alias.\n---\n\nUse for $Team/code work. Ambiguity gate first. Write team-roster.json; team-gate.json needs team_roster_confirmed=true. executor:N means N scouts, N debate voices, then fresh N executors. After consensus, compile team-graph.json, team-runtime-tasks.json, team-decomposition-report.json, and team-inbox/ so worker handoff uses concrete runtime task ids with role/path/domain/lane hints. Refresh/validate TriWiki before debate, implementation, review, and final; consume attention.use_first and hydrate attention.hydrate_first before risky decisions. Log events and use sks team message for bounded inter-agent communication in transcript/lane panes. Color-coded Warp lanes distinguish overview/scout/planning/execution/review/safety sessions. End with cleanup-warp or a cleanup event so follow panes show cleanup and stop; pass team-session-cleanup.json, then reflection and Honest Mode. Parent integrates/verifies.\n\n${chatCaptureIntakeText()}\n`,
     'from-chat-img': `---\nname: from-chat-img\ndescription: Explicit $From-Chat-IMG Team alias for chat screenshot plus attachment analysis.\n---\n\nUse only for From-Chat-IMG/$From-Chat-IMG. It enters the normal Team pipeline. Treat uploads as chat screenshot plus originals. Use Codex Computer Use visual inspection when available, list requirements first, match regions to attachments with confidence, write ${FROM_CHAT_IMG_COVERAGE_ARTIFACT}, ${FROM_CHAT_IMG_CHECKLIST_ARTIFACT}, ${FROM_CHAT_IMG_TEMP_TRIWIKI_ARTIFACT}, and ${FROM_CHAT_IMG_QA_LOOP_ARTIFACT}, then continue Team gates, review, reflection, and Honest Mode. ${CODEX_COMPUTER_USE_ONLY_POLICY} The ledger must account for every visible customer request, screenshot image region, and separate attachment; ${FROM_CHAT_IMG_CHECKLIST_ARTIFACT} must have a checked item for each request, image-region/attachment match, work item, scoped QA-LOOP, and verification step; ${FROM_CHAT_IMG_TEMP_TRIWIKI_ARTIFACT} stores temporary TriWiki-backed session context with expires_after_sessions=${FROM_CHAT_IMG_TEMP_TRIWIKI_SESSIONS}. ${FROM_CHAT_IMG_QA_LOOP_ARTIFACT} must prove QA-LOOP ran over the exact customer-request work-order range after implementation, with every work item covered, post-fix verification complete, and zero unresolved findings. team-gate.json cannot pass From-Chat-IMG completion until unresolved_items is empty, every checklist box is checked, and scoped_qa_loop_completed=true.\n`,
     'qa-loop': `---\nname: qa-loop\ndescription: $QA-LOOP dogfoods UI/API as human proxy with safety gates, Codex Computer Use-only UI evidence, safe fixes, rechecks, and a QA report.\n---\n\nUse only $QA-LOOP. Ask scope, target, mutation, login. Credentials are runtime-only; never save secrets. UI-level E2E needs Codex Computer Use evidence or must be marked unverified; Chrome MCP, Browser Use, Playwright, Selenium, Puppeteer, and other browser automation do not satisfy UI/browser verification. Deployed targets are read-only; destructive removal is forbidden. After answer/run, dogfood real flows, apply safe contract-allowed code/test/docs fixes, recheck, and do not pass qa-gate.json with unresolved findings or without post_fix_verification_complete. Finish qa-ledger, date/version report, gate, completion summary, and Honest Mode.\n`,
-    'goal': `---\nname: goal\ndescription: Dollar-command route for $Goal or $goal Codex native persisted /goal workflows.\n---\n\nUse when the user invokes $Goal/$goal or asks to persist a workflow with Codex native /goal continuation. Prepare with sks goal create or the $Goal route, then use native Codex /goal create, pause, resume, and clear controls where available. Do not recreate the old no-question loop.\n`,
+    'computer-use': `---\nname: computer-use\ndescription: Maximum-speed $Computer-Use/$CU lane for Codex Computer Use UI/browser/visual tasks.\n---\n\nUse only when the user invokes $Computer-Use/$CU or asks for a Computer Use-specific fast lane. Skip Team debate, QA-LOOP clarification, upfront TriWiki refresh, Context7, subagents, and reflection unless explicitly requested. Infer the smallest target, use Codex Computer Use directly, and never substitute Playwright, Chrome MCP, Browser Use, Selenium, Puppeteer, or other browser automation for UI/browser evidence. If Computer Use is unavailable, mark UI/browser evidence unverified and stop with the blocker. At the end only, refresh or pack TriWiki, validate it, then provide a concise completion summary plus Honest Mode.\n`,
+    'computer-use-fast': `---\nname: computer-use-fast\ndescription: Alias for the maximum-speed $Computer-Use/$CU Codex Computer Use lane.\n---\n\nUse the same rules as computer-use: skip Team debate, QA-LOOP clarification, upfront TriWiki refresh, Context7, subagents, and reflection unless explicitly requested. Use Codex Computer Use directly; never substitute Playwright, Chrome MCP, Browser Use, Selenium, Puppeteer, or other browser automation for UI/browser evidence. At the end only, refresh/pack TriWiki, validate it, then provide a concise completion summary plus Honest Mode.\n`,
+    'cu': `---\nname: cu\ndescription: Short alias for the maximum-speed $Computer-Use Codex Computer Use lane.\n---\n\nUse the same rules as computer-use. This is a speed lane for focused UI/browser/visual tasks that require Codex Computer Use evidence, with TriWiki refresh/validate and Honest Mode deferred to final closeout.\n`,
+    'goal': `---\nname: goal\ndescription: Fast $Goal/$goal bridge overlay for Codex native persisted /goal workflows.\n---\n\nUse when the user invokes $Goal/$goal or asks to persist a workflow with Codex native /goal continuation. Prepare with sks goal create or the $Goal route, write only the lightweight bridge artifacts, then use native Codex /goal create, pause, resume, and clear controls where available. Goal does not replace Team, QA, DB, or other SKS execution routes; continue implementation through the selected route and use Context7 only when external API/library docs are involved. Do not recreate the old no-question loop.\n`,
     'research': `---\nname: research\ndescription: Dollar-command route for $Research or $research frontier discovery workflows.\n---\n\nUse when the user invokes $Research/$research or asks for research, hypotheses, new mechanisms, falsification, or testable predictions. Prefer sks research prepare and sks research run. Do not use for ordinary code edits.\n`,
     'autoresearch': `---\nname: autoresearch\ndescription: Dollar-command route for $AutoResearch or $autoresearch iterative experiment loops.\n---\n\nUse for $AutoResearch, iterative improvement, SEO/GEO, ranking, workflow, benchmark, or experiments. Define program, hypothesis, experiment, metric, keep/discard, falsification, next step, and Honest Mode. Load seo-geo-optimizer for README/npm/GitHub/schema/AI-search work.\n`,
     'db': `---\nname: db\ndescription: Dollar-command route for $DB or $db database and Supabase safety checks.\n---\n\nUse when the user invokes $DB/$db or the task touches SQL, Supabase, Postgres, migrations, Prisma, Drizzle, Knex, MCP database tools, or production data. Run or follow sks db policy, sks db scan, sks db classify, and sks db check. Destructive database operations remain forbidden.\n`,
@@ -579,7 +582,7 @@ export async function installSkills(root) {
 }
 
 function enrichSkillContent(name, content) {
-  if (!['sks', 'answer', 'wiki', 'team', 'qa-loop', 'goal', 'research', 'autoresearch', 'db', 'gx', 'reflection', 'prompt-pipeline', 'pipeline-runner', 'context7-docs', 'turbo-context-pack', 'hproof-evidence-bind'].includes(name)) return content;
+  if (!['sks', 'answer', 'wiki', 'team', 'qa-loop', 'computer-use', 'computer-use-fast', 'cu', 'goal', 'research', 'autoresearch', 'db', 'gx', 'reflection', 'prompt-pipeline', 'pipeline-runner', 'context7-docs', 'turbo-context-pack', 'hproof-evidence-bind'].includes(name)) return content;
   const text = String(content || '').trimEnd();
   if (text.includes('TriWiki context-tracking SSOT')) return text;
   return `${text}
@@ -594,7 +597,9 @@ Context tracking:
 }
 
 async function writeSkillMetadata(dir, name) {
-  const effort = ['research', 'autoresearch', 'research-discovery', 'autoresearch-loop', 'from-chat-img'].includes(name)
+  const effort = ['computer-use', 'computer-use-fast', 'cu'].includes(name)
+    ? 'low'
+    : ['research', 'autoresearch', 'research-discovery', 'autoresearch-loop', 'from-chat-img'].includes(name)
     ? 'xhigh'
     : (['dfix', 'sks', 'help'].includes(name) ? 'medium' : 'high');
   await ensureDir(path.join(dir, 'agents'));

package/src/core/pipeline.mjs

@@ -36,6 +36,7 @@ export function promptPipelineContext(prompt, route = routePrompt(prompt)) {
   const fastDesign = route?.id === 'DFix';
   if (fastDesign) return dfixQuickContext(prompt, route);
   if (route?.id === 'Answer') return answerOnlyContext(prompt, route);
+  if (route?.id === 'ComputerUse') return computerUseFastContext(prompt, route);
   const lines = [
     `SKS skill-first pipeline active. Route: ${route?.command || '$SKS'} (${route?.route || 'general SKS workflow'}).`,
     reasoningInstruction(reasoning),
@@ -111,6 +112,7 @@ export async function prepareRoute(root, prompt, state = {}) {
   if (!route) return { route: null, additionalContext: promptPipelineContext(prompt, null) };
   if (route.id === 'DFix') return prepareDfixQuickRoute(route, task);
   if (route.id === 'Answer') return prepareAnswerOnlyRoute(route, task);
+  if (route.id === 'ComputerUse') return prepareComputerUseFastRoute(route, task);
   if (route.id === 'Wiki') return prepareWikiQuickRoute(route, task);
   if (route.id === 'Goal') return prepareGoal(root, route, task, routeNeedsContext7(route, prompt));
   const required = routeNeedsContext7(route, prompt);
@@ -143,6 +145,30 @@ async function prepareAnswerOnlyRoute(route, task) {
   };
 }
 
+async function prepareComputerUseFastRoute(route, task) {
+  return {
+    route,
+    additionalContext: computerUseFastContext(task, route)
+  };
+}
+
+export function computerUseFastContext(prompt, route = routePrompt(prompt)) {
+  const task = stripDollarCommand(prompt) || String(prompt || '').trim();
+  return [
+    `Computer Use fast lane active. Route: ${route?.command || '$Computer-Use'} (${route?.route || 'Computer Use fast lane'}).`,
+    'Speed contract: do not enter Team, QA-LOOP clarification, repeated upfront TriWiki refresh, Context7, subagent orchestration, debate, reflection, or broad planning unless the user explicitly requests that heavier route.',
+    `Task: ${task}`,
+    'Execution order:',
+    '1. Infer the smallest UI/browser/visual target and acceptance from the prompt and current app context.',
+    '2. Use Codex Computer Use directly for the focused screen/browser action or inspection. Do not substitute Playwright, Chrome MCP, Browser Use, Selenium, Puppeteer, or other browser automation for UI/browser evidence.',
+    '3. If Computer Use is unavailable, mark UI/browser evidence unverified and stop with the exact blocker instead of switching tools.',
+    '4. Apply only safe, directly requested fixes when the prompt asks for correction; otherwise report observed evidence only.',
+    '5. At the end only, run `sks wiki refresh` or `sks wiki pack`, then `sks wiki validate .sneakoscope/wiki/context-pack.json` when the repo/runtime is available.',
+    '6. Final response must include a short completion summary plus SKS Honest Mode: evidence used, tests/checks run, and any unverified UI/browser claims.',
+    CODEX_COMPUTER_USE_ONLY_POLICY
+  ].join('\n');
+}
+
 async function prepareWikiQuickRoute(route, task) {
   return {
     route,
@@ -187,8 +213,27 @@ export async function activeRouteContext(root, state) {
 async function prepareGoal(root, route, task, required) {
   const { id, dir, mission } = await createMission(root, { mode: 'goal', prompt: task });
   const workflow = await writeGoalWorkflow(dir, mission, { action: 'create', prompt: task });
-  await writeJsonAtomic(path.join(dir, 'route-context.json'), { route: route.id, command: route.command, mode: route.mode, task, required_skills: route.requiredSkills, context7_required: required, native_goal: workflow.native_goal, stop_gate: 'honest_mode' });
-  await setCurrent(root, routeState(id, route, 'GOAL_READY', required, { prompt: task, native_goal: workflow.native_goal, stop_gate: 'honest_mode', implementation_allowed: true, questions_allowed: true }));
+  await writeJsonAtomic(path.join(dir, 'route-context.json'), { route: route.id, command: route.command, mode: route.mode, task, required_skills: route.requiredSkills, context7_required: required, native_goal: workflow.native_goal, stop_gate: route.stopGate });
+  const executionRoute = routePrompt(task);
+  const shouldDelegateExecution = routeRequiresSubagents(route, task)
+    && executionRoute
+    && !['Answer', 'DFix', 'Goal', 'Help'].includes(executionRoute.id);
+  if (shouldDelegateExecution) {
+    await appendJsonl(path.join(dir, 'events.jsonl'), { ts: nowIso(), type: 'goal.delegated_execution_route', route: executionRoute.id, command: executionRoute.command });
+    const delegated = await prepareRoute(root, task, {});
+    return {
+      route,
+      additionalContext: [
+        `$Goal bridge prepared as a lightweight native /goal persistence overlay.
+Goal bridge mission: ${id}
+Goal artifact: .sneakoscope/missions/${id}/${GOAL_WORKFLOW_ARTIFACT}
+Native Codex control: ${workflow.native_goal.slash_command}
+Delegated execution route: ${executionRoute.command}. The delegated route mission is authoritative for implementation, verification, and final gates.`,
+        delegated.additionalContext
+      ].filter(Boolean).join('\n\n')
+    };
+  }
+  await setCurrent(root, routeState(id, route, 'GOAL_READY', required, { prompt: task, native_goal: workflow.native_goal, stop_gate: route.stopGate, implementation_allowed: true, questions_allowed: true }));
   return routeContext(route, id, task, required, `Use Codex native ${workflow.native_goal.slash_command} control for persisted continuation, then continue the relevant SKS route gates for any implementation work.`);
 }
 

package/src/core/routes.mjs

@@ -45,6 +45,8 @@ export const RECOMMENDED_SKILLS = [
   'design-system-builder',
   'design-ui-editor',
   'imagegen',
+  'computer-use',
+  'computer-use-fast',
   'db-safety-guard',
   REFLECTION_SKILL_NAME,
   'honest-mode'
@@ -215,17 +217,33 @@ export const ROUTES = [
     cliEntrypoint: 'sks qa-loop prepare|answer|run|status',
     examples: ['$QA-LOOP dogfood UI and API against local dev', '$QA-LOOP deployed smoke only']
   },
+  {
+    id: 'ComputerUse',
+    command: '$Computer-Use',
+    mode: 'COMPUTER_USE',
+    route: 'Computer Use fast lane',
+    description: 'Maximum-speed Codex Computer Use lane for UI/browser/visual tasks: skip Team debate and upfront TriWiki loops, run only focused Computer Use steps, then finish with evidence, TriWiki refresh/validate, and Honest Mode.',
+    requiredSkills: ['computer-use', 'honest-mode'],
+    dollarAliases: ['$CU'],
+    appSkillAliases: ['computer-use-fast', 'cu'],
+    lifecycle: ['fast_intake', 'focused_computer_use_steps', 'evidence_summary', 'final_triwiki_refresh_validate', 'honest_mode'],
+    context7Policy: 'optional',
+    reasoningPolicy: 'low',
+    stopGate: 'none',
+    cliEntrypoint: 'Codex App prompt route only: $Computer-Use <target/task>',
+    examples: ['$Computer-Use check the local UI as fast as possible', '$CU localhost screen smoke']
+  },
   {
     id: 'Goal',
     command: '$Goal',
     mode: 'GOAL',
-    route: 'native Codex goal workflow',
-    description: 'Bridge SKS pipeline work into Codex native persisted /goal workflows for create, pause, resume, and clear.',
-    requiredSkills: ['goal', 'pipeline-runner', 'context7-docs', REFLECTION_SKILL_NAME, 'honest-mode'],
-    lifecycle: ['goal_workflow_artifact', 'native_goal_create_or_control', 'runtime_continuation', 'post_route_reflection', 'honest_mode'],
-    context7Policy: 'required',
-    reasoningPolicy: 'high',
-    stopGate: 'honest_mode',
+    route: 'native /goal persistence bridge',
+    description: 'Fast overlay that records a bridge artifact for Codex native persisted /goal create, pause, resume, and clear controls; implementation continues through the selected SKS execution route.',
+    requiredSkills: ['goal', 'honest-mode'],
+    lifecycle: ['goal_bridge_artifact', 'native_goal_create_or_control', 'selected_sks_route_continuation', 'honest_mode'],
+    context7Policy: 'if_external_docs',
+    reasoningPolicy: 'medium',
+    stopGate: 'none',
     cliEntrypoint: 'sks goal create|pause|resume|clear|status',
     examples: ['$Goal persist this migration workflow with native /goal continuation']
   },
@@ -371,7 +389,7 @@ export const COMMAND_CATALOG = [
   { name: 'doctor', usage: 'sks doctor [--fix] [--local-only] [--json] [--install-scope global|project]', description: 'Check and repair SKS generated files, while blocking setup if another Codex harness is detected.' },
   { name: 'init', usage: 'sks init [--force] [--local-only] [--install-scope global|project]', description: 'Initialize the local SKS control surface.' },
   { name: 'selftest', usage: 'sks selftest [--mock]', description: 'Run local smoke tests without calling a model.' },
-  { name: 'goal', usage: 'sks goal create|pause|resume|clear|status ...', description: 'Prepare and control SKS bridge artifacts for Codex native persisted /goal workflows.' },
+  { name: 'goal', usage: 'sks goal create|pause|resume|clear|status ...', description: 'Prepare and control the fast SKS bridge overlay for Codex native persisted /goal workflows.' },
   { name: 'research', usage: 'sks research prepare|run|status ...', description: 'Run frontier-style research missions with novelty and falsification gates.' },
   { name: 'db', usage: 'sks db policy|scan|mcp-config|classify|check ...', description: 'Inspect and enforce database/Supabase safety policy.' },
   { name: 'eval', usage: 'sks eval run|compare|thresholds ...', description: 'Run deterministic context-quality and performance evidence checks.' },
@@ -455,6 +473,7 @@ export function routePrompt(prompt) {
     return route;
   }
   if (hasFromChatImgSignal(text)) return routeById('Team');
+  if (looksLikeComputerUseFastLane(text)) return routeById('ComputerUse');
   if (looksLikeFastDesignFix(text)) return routeById('DFix');
   if (looksLikeQuestionShapedDirective(text)) return routeById('Team');
   if (looksLikeAnswerOnlyRequest(text)) return routeById('Answer');
@@ -464,12 +483,19 @@ export function routePrompt(prompt) {
   if (/\b(qa[-\s]?loop|qaloop|e2e\s+qa|qa\s+e2e)\b/i.test(text)) return routeById('QALoop');
   if (/\b(autoresearch|experiment|benchmark|SEO|GEO|ranking|optimi[sz]e|improve metric|discoverability|visibility|github stars?|npm downloads?|검색|노출|스타|다운로드)\b/i.test(text)) return routeById('AutoResearch');
   if (/\b(research|hypothesis|falsify|novelty|frontier|조사|연구)\b/i.test(text)) return routeById('Research');
-  if (/(wiki\s+(refresh|pack|validate|prune)|triwiki\s+(refresh|pack|validate)|위키\s*(갱신|리프레시|정리|검증|패킹)|트라이위키|triwiki)/i.test(text)) return routeById('Wiki');
+  if (/(wiki\s+(refresh|pack|validate|prune)|triwiki\s+(refresh|pack|validate)|위키\s*(갱신|리프레시|정리|검증|패킹)|트라이위키|triwiki)/i.test(text) && !looksLikeDirectWorkRequest(text)) return routeById('Wiki');
   if (/\b(GX|vgraph|visual context|render cartridge|wiki coordinate|rgba|trig|llm wiki)\b/i.test(text)) return routeById('GX');
   if (looksLikeTeamDefaultWork(text)) return routeById('Team');
   return routeById('SKS');
 }
 
+export function looksLikeComputerUseFastLane(prompt = '') {
+  const text = String(prompt || '');
+  const computerUseCue = /\b(computer\s*use|codex\s+computer\s+use|computer-use)\b|컴퓨터\s*유즈|컴퓨터\s*사용|컴퓨터유즈/i.test(text);
+  if (!computerUseCue) return false;
+  return /\b(ui|browser|visual|screen|screenshot|e2e|qa|dogfood|fast|lane|pipeline|localhost|web|app|page)\b|화면|브라우저|시각|스크린|캡처|검증|빠른|고속|파이프라인|작업|속도/i.test(text);
+}
+
 export function looksLikeTeamDefaultWork(prompt = '') {
   const text = String(prompt || '').trim();
   if (!text) return false;
@@ -515,16 +541,17 @@ export function routeRequiresSubagents(route, prompt = '') {
   if (!route) return false;
   if (route.id === 'Team') return true;
   if (route.id === 'SKS') return looksLikeTeamDefaultWork(prompt);
-  if (route.id === 'Help' || route.id === 'Answer' || route.id === 'Wiki') return false;
+  if (route.id === 'Help' || route.id === 'Answer' || route.id === 'Wiki' || route.id === 'ComputerUse') return false;
   if (route.id === 'Research' || route.id === 'AutoResearch') return true;
-  if (route.id === 'Goal' || route.id === 'DB' || route.id === 'GX') return looksLikeExecutionWork(prompt);
+  if (route.id === 'Goal') return looksLikeExecutionWork(prompt) || looksLikeTeamDefaultWork(stripDollarCommand(prompt));
+  if (route.id === 'DB' || route.id === 'GX') return looksLikeExecutionWork(prompt);
   if (route.id === 'DFix') return looksLikeCodeChangingWork(prompt) && !looksLikeFastDesignFix(prompt);
   return looksLikeExecutionWork(prompt);
 }
 
 export function reflectionRequiredForRoute(route) {
   const id = String(route?.id || route?.mode || route?.route || route || '').replace(/^\$/, '');
-  return /^(team|qaloop|qa-loop|goal|research|autoresearch|db|database|madsks|mad-sks|gx)$/i.test(id);
+  return /^(team|qaloop|qa-loop|research|autoresearch|db|database|madsks|mad-sks|gx)$/i.test(id);
 }
 
 export function looksLikeCodeChangingWork(prompt = '') {
@@ -539,6 +566,14 @@ export function looksLikeExecutionWork(prompt = '') {
 
 export function subagentExecutionPolicyText(route, prompt = '') {
   const required = routeRequiresSubagents(route, prompt);
+  if (route?.id === 'Goal') {
+    if (!required) return 'Subagent policy: Goal itself is a lightweight native /goal persistence overlay; subagents are not required for bridge creation/control.';
+    return [
+      'Subagent policy: Goal itself remains a lightweight native /goal persistence overlay.',
+      'Because the prompt also asks for code-changing or execution work, continue that work through the selected SKS execution route and apply that route\'s worker/reviewer policy there.',
+      noUnrequestedFallbackCodePolicyText()
+    ].join(' ');
+  }
   if (!required) {
     return 'Subagent policy: optional for this route; use subagents only when parallel exploration materially helps.';
   }