sneakoscope 0.7.58 → 0.7.60

package/README.md

@@ -42,7 +42,7 @@ sks selftest --mock
 
 | Area | What it does |
 | --- | --- |
-| CLI runtime | Bare `sks` opens or reuses the default tmux Codex CLI workspace. `sks tmux open` remains the explicit form for session/workspace flags, and `sks --mad` launches a multi-pane MAD tmux cockpit with the explicit full-access high-reasoning profile. |
+| CLI runtime | Bare `sks` opens or reuses the default tmux Codex CLI workspace. `sks tmux open` remains the explicit form for session/workspace flags, and `sks --mad` launches a single-pane MAD tmux session with the explicit full-access high-reasoning profile. Split panes are reserved for active Team scout/worker lanes. |
 | Codex App commands | Installs generated skills so `$Team`, `$From-Chat-IMG`, `$DFix`, `$QA-LOOP`, `$PPT`, `$Image-UX-Review`, `$UX-Review`, `$Goal`, `$DB`, `$Wiki`, `$Help`, and related routes are visible in prompt workflows. `sks codex-app remote-control` wraps Codex CLI 0.130.0+ headless remote control without falling back to older app-server internals. |
 | OpenClaw agents | Generates an OpenClaw skill package so OpenClaw agents can attach `sneakoscope-codex`, enable the `shell` tool, and discover/use SKS commands from the target repo root. |
 | Pipeline plans | Writes `pipeline-plan.json` for stateful routes so the runtime lane, kept stages, skipped stages, verification commands, and no-unrequested-fallback invariant are visible with `sks pipeline plan`. |
@@ -80,7 +80,7 @@ The default `sks` runtime checks npm for newer `sneakoscope` and `@openai/codex`
 - Checks npm for newer `sneakoscope` and `@openai/codex` versions before launch and asks whether to update when the terminal can answer y/n.
 - Installs the latest Codex CLI with `npm i -g @openai/codex@latest` when it is missing and you approve or pass `--yes`.
 - Requires tmux 3.x or newer before opening the session.
-- Creates a named detached tmux cockpit with multiple panes and prints only the session, gate, attach, and blocker details needed to act.
+- Creates a named detached single-pane tmux session and prints only the session, gate, attach, and blocker details needed to act.
 
 ## Installation
 
@@ -211,7 +211,7 @@ sks --mad
 sks --mad --yes
 ```
 
-This syncs existing codex-lb/Codex CLI auth before launch, creates/uses the `sks-mad-high` Codex profile for a one-shot full-access, high-reasoning tmux cockpit with `sandbox_mode = "danger-full-access"` and `approval_policy = "never"`, opens an active MAD-SKS permission gate for that tmux run, then launches a tiled cockpit: Codex CLI, MAD permission gate status, and live guide panes. The cockpit recreates the named session on launch so stale single-pane sessions do not hide the split layout, then attaches in an interactive terminal. If codex-lb is configured and no explicit `--workspace`/`--session` was passed, SKS opens a fresh tmux session so the repaired key is loaded by the Codex process immediately. While the gate is active, live server work, Supabase MCP database writes, direct SQL, targeted DML, schema cleanup, Supabase MCP `apply_migration`, and required Supabase CLI migration application such as `supabase migration up` or `supabase db push` are allowed. Catastrophic database wipe/all-row/project-management safeguards remain active.
+This syncs existing codex-lb/Codex CLI auth before launch, creates/uses the `sks-mad-high` Codex profile for a one-shot full-access, high-reasoning tmux session with `sandbox_mode = "danger-full-access"` and `approval_policy = "never"`, opens an active MAD-SKS permission gate for that tmux run, then launches a single Codex CLI pane. The session recreates the named session on launch so stale split-pane MAD sessions collapse back to the single-pane default, then attaches in an interactive terminal. If codex-lb is configured and no explicit `--workspace`/`--session` was passed, SKS opens a fresh tmux session so the repaired key is loaded by the Codex process immediately. While the gate is active, live server work, Supabase MCP database writes, direct SQL, targeted DML, schema cleanup, Supabase MCP `apply_migration`, and required Supabase CLI migration application such as `supabase migration up` or `supabase db push` are allowed. Catastrophic database wipe/all-row/project-management safeguards remain active.
 
 MAD does not disable the pipeline contract: stages, executors, reviewers, and auto-review policy still must not invent unrequested fallback implementation code. If the requested path cannot be implemented, SKS should block with evidence rather than add substitute behavior.
 
@@ -283,11 +283,11 @@ SKS no longer starts from a fixed checklist such as `GOAL_PRECISE` and `ACCEPTAN
 
 The design borrows two useful ideas from external planning systems without copying their route weight: Ouroboros-style ambiguity thresholds decide whether the prompt is clear enough to proceed, while Prometheus/Hyperplan-style adversarial lenses challenge framing, remove unnecessary surface, demand evidence, test integration risk, and consider a simpler alternative before Team work starts.
 
-`sks skill-dream` keeps generated skill complexity bounded without doing a heavy evaluation on every prompt. Route use writes compact counters to `.sneakoscope/skills/dream-state.json`; after the configured count/cooldown threshold, or when you run `sks skill-dream run`, SKS scans `.agents/skills` and writes `.sneakoscope/reports/skill-dream-latest.json` with keep, merge, prune, and improvement candidates. The report is intentionally advisory: deleting or merging skills requires explicit approval.
+`sks skill-dream` keeps generated skill complexity bounded without doing a heavy evaluation on every prompt. Route use writes compact counters to `.sneakoscope/skills/dream-state.json`; after the configured 10-route-event threshold and cooldown, or when you run `sks skill-dream run`, SKS scans `.agents/skills` and writes `.sneakoscope/reports/skill-dream-latest.json` with keep, merge, prune, and improvement candidates. The report is intentionally advisory: deleting or merging skills requires explicit approval.
 
 `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.
+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. SKS does not install a generated skill named `computer-use`, because that name is reserved for the first-party Codex Computer Use plugin; use `$CU` or `$computer-use-fast` from the SKS picker for the SKS route, and use `@Computer` for the OpenAI plugin.
 
 ### Create A Presentation
 
@@ -555,6 +555,8 @@ codex mcp list
 
 Codex App workflows need the app installed. QA and UI/browser visual-evidence workflows require first-party Codex Computer Use; Browser Use may support non-UI browser context, but it is not valid UI/browser verification evidence. Generated raster assets and image-review evidence require real Codex App `$imagegen`/`gpt-image-2` output, or the route must stay blocked/unverified.
 
+SKS setup removes old SKS-generated `computer-use` skills from `.agents/skills` so they cannot shadow the first-party Computer Use plugin. If a running Codex App thread was opened before setup or upgrade, start a fresh thread and invoke `@Computer` or Browser again so the host reloads plugin tools.
+
 ### Setup is blocked by another harness
 
 ```sh

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "sneakoscope",
   "displayName": "ㅅㅋㅅ",
-  "version": "0.7.58",
+  "version": "0.7.60",
   "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/install-helpers.mjs

@@ -36,7 +36,11 @@ export async function postinstall({ bootstrap }) {
   else if (fastModeRepair.status === 'skipped') console.log(`Codex App Fast mode: skipped (${fastModeRepair.reason}).`);
   else if (fastModeRepair.status === 'failed') console.log(`Codex App Fast mode: auto repair failed. Run \`sks setup\`. ${fastModeRepair.error || ''}`.trim());
   const globalSkills = await ensureGlobalCodexSkillsDuringInstall();
-  if (globalSkills.status === 'installed') console.log(`Codex App global $ skills: installed in ${globalSkills.root} (${globalSkills.installed_count} skills).`);
+  if (globalSkills.status === 'installed') {
+    const removed = globalSkills.removed_stale_generated_skills || [];
+    const cleanup = removed.length ? ` Removed stale generated skill shadow(s): ${removed.join(', ')}.` : '';
+    console.log(`Codex App global $ skills: installed in ${globalSkills.root} (${globalSkills.installed_count} skills).${cleanup}`);
+  }
   else if (globalSkills.status === 'partial') console.log(`Codex App global $ skills: partial in ${globalSkills.root}; missing ${globalSkills.missing_skills.join(', ')}. Run \`sks doctor --fix\`.`);
   else if (globalSkills.status === 'skipped') console.log(`Codex App global $ skills: skipped (${globalSkills.reason}).`);
   else if (globalSkills.status === 'failed') console.log(`Codex App global $ skills: auto setup failed. Run \`sks doctor --fix\`. ${globalSkills.error || ''}`.trim());
@@ -303,10 +307,10 @@ export async function ensureGlobalCodexFastModeDuringInstall(opts = {}) {
 export function normalizeCodexFastModeUiConfig(text = '') {
   let next = removeLegacyTopLevelCodexModeLocks(text);
   next = removeTomlTableKey(next, 'notice', 'fast_default_opt_out');
-  next = removeTomlTableKey(next, 'features', 'codex_hooks');
+  next = removeTomlTableKey(next, 'features', 'hooks');
   next = upsertTopLevelTomlString(next, 'model', 'gpt-5.5');
   next = upsertTopLevelTomlString(next, 'service_tier', 'fast');
-  next = upsertTomlTableKey(next, 'features', 'hooks = true');
+  next = upsertTomlTableKey(next, 'features', 'codex_hooks = true');
   next = upsertTomlTableKey(next, 'features', 'fast_mode = true');
   next = upsertTomlTableKey(next, 'features', 'fast_mode_ui = true');
   next = upsertTomlTableKey(next, 'user.fast_mode', 'visible = true');
@@ -989,7 +993,7 @@ export async function selftestCodexLb(tmp) {
   if (codexLbNotConfigured.code !== 0 || String(codexLbNotConfigured.stdout || '').includes('codex-lb auth:')) throw new Error('selftest failed: postinstall should stay quiet when codex-lb is not configured');
   const codexLbStatusText = await runProcess(process.execPath, [path.join(packageRoot(), 'bin', 'sks.mjs'), 'codex-lb', 'status'], { cwd: tmp, env: codexLbEnvForSelftest, timeoutMs: 15000, maxOutputBytes: 64 * 1024 });
   if (!String(codexLbStatusText.stdout || '').includes('Repair auth: sks codex-lb repair')) throw new Error('selftest failed: codex-lb status did not advertise repair command');
-  if (!/^model = "gpt-5\.5"/m.test(codexLbConfig) || !codexLbConfig.includes('service_tier = "fast"') || !codexLbConfig.includes('hooks = true') || codexLbConfig.includes('codex_hooks = true') || !codexLbConfig.includes('fast_mode = true') || !codexLbConfig.includes('fast_mode_ui = true') || !codexLbConfig.includes('[user.fast_mode]') || !codexLbConfig.includes('visible = true') || !codexLbConfig.includes('enabled = true') || !codexLbConfig.includes('default_profile = "sks-fast-high"') || !/\[profiles\.sks-fast-high\][\s\S]*?service_tier = "fast"/.test(codexLbConfig) || codexLbConfig.includes('fast_default_opt_out = true') || hasTopLevelCodexModeLock(codexLbConfig)) throw new Error('selftest failed: codex-lb setup did not preserve Codex App Fast mode defaults, force GPT-5.5, or migrate the hooks feature flag');
+  if (!/^model = "gpt-5\.5"/m.test(codexLbConfig) || !codexLbConfig.includes('service_tier = "fast"') || !codexLbConfig.includes('codex_hooks = true') || hasLegacyHooksFeatureFlag(codexLbConfig) || !codexLbConfig.includes('fast_mode = true') || !codexLbConfig.includes('fast_mode_ui = true') || !codexLbConfig.includes('[user.fast_mode]') || !codexLbConfig.includes('visible = true') || !codexLbConfig.includes('enabled = true') || !codexLbConfig.includes('default_profile = "sks-fast-high"') || !/\[profiles\.sks-fast-high\][\s\S]*?service_tier = "fast"/.test(codexLbConfig) || codexLbConfig.includes('fast_default_opt_out = true') || hasTopLevelCodexModeLock(codexLbConfig)) throw new Error('selftest failed: codex-lb setup did not preserve Codex App Fast mode defaults, force GPT-5.5, or migrate the hooks feature flag');
   const codexLbLaunch = codexLaunchCommand(tmp, 'codex', []);
   if (!codexLbLaunch.includes('sks-codex-lb.env')) throw new Error('selftest failed: tmux launch command does not source codex-lb env file');
   if (!codexLbLaunch.includes("'--model' 'gpt-5.5'")) throw new Error('selftest failed: tmux launch command without args did not force GPT-5.5');
@@ -1002,3 +1006,17 @@ export async function selftestCodexLb(tmp) {
 function hasTopLevelCodexModeLock(text = '') {
   return /(^|\n)\s*model\s*=\s*"codex-lb"\s*(\n|$)/.test(text) || /(^|\n)\s*model_provider\s*=\s*"openai"\s*(\n|$)/.test(text);
 }
+
+function hasLegacyHooksFeatureFlag(text = '') {
+  const lines = String(text || '').split('\n');
+  const start = lines.findIndex((line) => line.trim() === '[features]');
+  if (start === -1) return false;
+  let end = lines.length;
+  for (let i = start + 1; i < lines.length; i += 1) {
+    if (/^\s*\[.+\]\s*$/.test(lines[i])) {
+      end = i;
+      break;
+    }
+  }
+  return lines.slice(start + 1, end).some((line) => /^\s*hooks\s*=/.test(line));
+}

package/src/cli/main.mjs

@@ -283,7 +283,7 @@ async function wizard(args = []) {
         const update = await askChoice(rl, 'Update SKS before setup?', ['yes', 'no'], 'yes');
         if (update === 'yes') {
           console.log('\nRun this update command, then rerun `sks`:');
-          console.log('  npm i -g sneakoscope\n');
+          console.log('  npm i -g sneakoscope@latest\n');
           return;
         }
         console.log('Skipping update for this setup run.\n');
@@ -345,7 +345,7 @@ async function updateCheck(args = []) {
   console.log(`Latest:  ${result.latest || 'unknown'}`);
   console.log(`Update:  ${result.update_available ? 'available' : 'not needed'}`);
   if (result.error) console.log(`Error:   ${result.error}`);
-  if (result.update_available) console.log('Run:     npm i -g sneakoscope');
+  if (result.update_available) console.log('Run:     npm i -g sneakoscope@latest');
 }
 
 const DOLLAR_DEFAULT_PIPELINE_TEXT = 'Default pipeline: direct answers -> $Answer, tiny Direct Fix edits -> $DFix, presentation/PDF artifacts -> $PPT, image-generation UI/UX reviews -> $Image-UX-Review/$UX-Review, Computer Use UI/browser speed work -> $Computer-Use, code -> $Team. Execution routes infer their contract from prompt, TriWiki/current-code defaults, and conservative policy instead of surfacing prequestion sheets. 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.';
@@ -1720,7 +1720,11 @@ async function doctor(args) {
   console.log(`Install:   ${install.ok ? 'ok' : 'missing'} ${install.scope} (${install.command_prefix})`);
   console.log(`Conflicts: ${result.harness_conflicts.hard_block ? 'blocked' : 'ok'} ${result.harness_conflicts.conflicts.length} finding(s)`);
   if (repairApplied) console.log('Repair:    regenerated SKS managed files from the installed package template');
-  if (globalSkillsRepair) console.log(`Global $ repair: ${globalSkillsRepair.status} ${globalSkillsRepair.root || ''}`.trimEnd());
+  if (globalSkillsRepair) {
+    const removed = globalSkillsRepair.removed_stale_generated_skills || [];
+    const cleanup = removed.length ? ` removed stale generated skill shadow(s): ${removed.join(', ')}` : '';
+    console.log(`Global $ repair: ${globalSkillsRepair.status} ${globalSkillsRepair.root || ''}${cleanup}`.trimEnd());
+  }
   if (flag(args, '--fix') && result.harness_conflicts.hard_block) console.log('Repair:    skipped because another Codex harness needs human-approved removal first');
   console.log(`Rust acc.: ${rust.available ? rust.version : 'optional-missing'}`);
   console.log(`State:     ${result.sneakoscope.ok ? 'ok' : 'missing .sneakoscope'}`);
@@ -1916,6 +1920,20 @@ function hasTopLevelCodexModeLock(text = '') {
   return (Boolean(model) && model !== 'gpt-5.5') || /^model_reasoning_effort\s*=/m.test(top);
 }
 
+function hasLegacyHooksFeatureFlag(text = '') {
+  const lines = String(text || '').split('\n');
+  const start = lines.findIndex((line) => line.trim() === '[features]');
+  if (start === -1) return false;
+  let end = lines.length;
+  for (let i = start + 1; i < lines.length; i += 1) {
+    if (/^\s*\[.+\]\s*$/.test(lines[i])) {
+      end = i;
+      break;
+    }
+  }
+  return lines.slice(start + 1, end).some((line) => /^\s*hooks\s*=/.test(line));
+}
+
 async function resolveMissionId(root, arg) { return (!arg || arg === 'latest') ? findLatestMission(root) : arg; }
 function readMaxCycles(args, fallback) {
   const i = args.indexOf('--max-cycles');
@@ -2024,12 +2042,14 @@ async function selftest() {
   await writeTextAtomic(path.join(repairTmp, '.agents', 'skills', 'agent-team', 'SKILL.md'), '---\nname: agent-team\ndescription: Fallback Codex App picker alias for $Team.\n---\n');
   await ensureDir(path.join(repairTmp, '.agents', 'skills', 'stale-sks-generated'));
   await writeTextAtomic(path.join(repairTmp, '.agents', 'skills', 'stale-sks-generated', 'SKILL.md'), '---\nname: stale-sks-generated\ndescription: Old SKS generated skill that should disappear on update.\n---\n');
+  await ensureDir(path.join(repairTmp, '.agents', 'skills', 'computer-use'));
+  await writeTextAtomic(path.join(repairTmp, '.agents', 'skills', 'computer-use', 'SKILL.md'), '---\nname: computer-use\ndescription: Maximum-speed $Computer-Use/$CU lane for Codex Computer Use UI/browser/visual tasks.\n---\n');
   await writeJsonAtomic(path.join(repairTmp, '.agents', 'skills', '.sks-generated.json'), {
     schema_version: 1,
     generated_by: 'sneakoscope',
     version: '0.0.1',
-    skills: ['team', 'stale-sks-generated'],
-    files: ['.agents/skills/team/SKILL.md', '.agents/skills/stale-sks-generated/SKILL.md']
+    skills: ['team', 'stale-sks-generated', 'computer-use'],
+    files: ['.agents/skills/team/SKILL.md', '.agents/skills/stale-sks-generated/SKILL.md', '.agents/skills/computer-use/SKILL.md']
   });
   const staleCodexAgentRel = '.codex/agents/stale-generated.toml';
   await writeTextAtomic(path.join(repairTmp, staleCodexAgentRel), 'name = "stale_generated"\n');
@@ -2050,6 +2070,8 @@ async function selftest() {
   await writeJsonAtomic(path.join(repairTmp, '.sneakoscope', 'policy.json'), { broken: true });
   const existingAgentsMd = await safeReadText(path.join(repairTmp, 'AGENTS.md'));
   await writeTextAtomic(path.join(repairTmp, 'AGENTS.md'), existingAgentsMd.replace(/<!-- BEGIN Sneakoscope Codex GX MANAGED BLOCK -->[\s\S]*?<!-- END Sneakoscope Codex GX MANAGED BLOCK -->\n?/, '<!-- BEGIN Sneakoscope Codex GX MANAGED BLOCK -->\ntampered managed block\n<!-- END Sneakoscope Codex GX MANAGED BLOCK -->\n'));
+  const stalePluginSkillNames = ['computer-use', 'browser-use', 'browser'];
+  const stalePluginSkillContent = (name) => `---\nname: ${name}\ndescription: Sneakoscope generated stale plugin collision for selftest.\n---\n\nCodex App pipeline activation:\n- stale selftest marker\n`;
   const doctorRepair = await runProcess(process.execPath, [path.join(packageRoot(), 'bin', 'sks.mjs'), 'doctor', '--fix', '--local-only', '--json'], {
     cwd: repairTmp,
     env: { HOME: path.join(repairTmp, 'home'), SKS_DISABLE_UPDATE_CHECK: '1' },
@@ -2065,6 +2087,7 @@ async function selftest() {
   if (!repairedTeamSkill.includes('SKS Team orchestration') || repairedTeamSkill.includes('tampered')) throw new Error('selftest failed: doctor repair did not regenerate team skill');
   if (await exists(path.join(repairTmp, '.agents', 'skills', 'agent-team', 'SKILL.md'))) throw new Error('selftest failed: doctor repair did not remove deprecated agent-team alias skill');
   if (await exists(path.join(repairTmp, '.agents', 'skills', 'stale-sks-generated', 'SKILL.md'))) throw new Error('selftest failed: doctor repair did not prune stale generated skill from previous SKS manifest');
+  if (await exists(path.join(repairTmp, '.agents', 'skills', 'computer-use', 'SKILL.md'))) throw new Error('selftest failed: doctor repair did not remove generated computer-use skill that shadows the first-party plugin');
   if (await exists(path.join(repairTmp, staleCodexAgentRel))) throw new Error('selftest failed: doctor repair did not prune stale generated agent file from previous SKS manifest');
   if (!doctorRepairJson.repair?.project?.skill_install?.removed_stale_generated_skills?.includes('.agents/skills/stale-sks-generated')) throw new Error('selftest failed: doctor repair did not report stale generated skill pruning');
   const generatedCleanupReport = doctorRepairJson.repair?.project?.generated_cleanup || {};
@@ -2079,6 +2102,29 @@ async function selftest() {
   if (repairedPolicy.broken || repairedPolicy.installation?.scope !== 'project' || !repairedPolicy.prompt_pipeline?.dollar_commands?.includes('$Team')) throw new Error('selftest failed: doctor --fix did not regenerate policy');
   const repairedAgentsMd = await safeReadText(path.join(repairTmp, 'AGENTS.md'));
   if (!repairedAgentsMd.includes('Do not create unrequested fallback implementation code') || repairedAgentsMd.includes('tampered managed block')) throw new Error('selftest failed: doctor --fix did not repair AGENTS managed block');
+  const doctorGlobalTmp = tmpdir();
+  await writeJsonAtomic(path.join(doctorGlobalTmp, 'package.json'), { name: 'doctor-global-skill-repair-smoke', version: '0.0.0' });
+  await initProject(doctorGlobalTmp, { installScope: 'global' });
+  const doctorGlobalHome = path.join(doctorGlobalTmp, 'home');
+  for (const name of stalePluginSkillNames) {
+    await ensureDir(path.join(doctorGlobalHome, '.agents', 'skills', name));
+    await writeTextAtomic(path.join(doctorGlobalHome, '.agents', 'skills', name, 'SKILL.md'), stalePluginSkillContent(name));
+  }
+  const doctorGlobalRepair = await runProcess(process.execPath, [path.join(packageRoot(), 'bin', 'sks.mjs'), 'doctor', '--fix', '--json'], {
+    cwd: doctorGlobalTmp,
+    env: { HOME: doctorGlobalHome, SKS_DISABLE_UPDATE_CHECK: '1' },
+    timeoutMs: 30000,
+    maxOutputBytes: 1024 * 1024
+  });
+  if (doctorGlobalRepair.code !== 0) throw new Error(`selftest failed: doctor --fix global skill repair exited ${doctorGlobalRepair.code}: ${doctorGlobalRepair.stderr}`);
+  const doctorGlobalRepairJson = JSON.parse(doctorGlobalRepair.stdout || '{}');
+  for (const name of stalePluginSkillNames) {
+    if (await exists(path.join(doctorGlobalHome, '.agents', 'skills', name, 'SKILL.md'))) throw new Error(`selftest failed: doctor --fix did not remove global generated ${name} plugin shadow skill`);
+  }
+  const doctorGlobalRemoved = doctorGlobalRepairJson.repair?.global_skills?.removed_stale_generated_skills || [];
+  for (const name of stalePluginSkillNames) {
+    if (!doctorGlobalRemoved.includes(`.agents/skills/${name}`)) throw new Error(`selftest failed: doctor --fix did not report global ${name} plugin shadow cleanup`);
+  }
   const conflictTmp = tmpdir();
   await ensureDir(path.join(conflictTmp, '.omx'));
   const conflictScan = await scanHarnessConflicts(conflictTmp, { home: path.join(conflictTmp, 'home') });
@@ -2092,12 +2138,18 @@ async function selftest() {
   const postinstallSetupTmp = tmpdir();
   await writeJsonAtomic(path.join(postinstallSetupTmp, 'package.json'), { name: 'postinstall-setup-smoke', version: '0.0.0' });
   await ensureDir(path.join(postinstallSetupTmp, '.git'));
+  const postinstallSetupHome = path.join(postinstallSetupTmp, 'home');
+  for (const name of stalePluginSkillNames) {
+    await ensureDir(path.join(postinstallSetupHome, '.agents', 'skills', name));
+    await writeTextAtomic(path.join(postinstallSetupHome, '.agents', 'skills', name, 'SKILL.md'), stalePluginSkillContent(name));
+  }
   const postinstallSetup = await runProcess(process.execPath, [path.join(packageRoot(), 'bin', 'sks.mjs'), 'postinstall'], { cwd: postinstallSetupTmp, env: { INIT_CWD: postinstallSetupTmp, HOME: path.join(postinstallSetupTmp, 'home'), SKS_SKIP_POSTINSTALL_SHIM: '1', SKS_SKIP_POSTINSTALL_CONTEXT7: '1', SKS_SKIP_POSTINSTALL_GETDESIGN: '1', SKS_SKIP_CLI_TOOLS: '1' }, timeoutMs: 30000, maxOutputBytes: 256 * 1024 });
   if (postinstallSetup.code !== 0) throw new Error(`selftest failed: postinstall setup exited ${postinstallSetup.code}: ${postinstallSetup.stderr}`);
   if (await exists(path.join(postinstallSetupTmp, '.agents', 'skills', 'agent-team', 'SKILL.md'))) throw new Error('selftest failed: postinstall installed deprecated agent-team fallback skill');
   if (!String(postinstallSetup.stdout || '').includes('SKS bootstrap: auto-running sks setup --bootstrap --install-scope global --force') || !String(postinstallSetup.stdout || '').includes('SKS Ready')) throw new Error('selftest failed: postinstall did not auto-run global forced bootstrap');
   if (!(await exists(path.join(postinstallSetupTmp, '.codex', 'hooks.json')))) throw new Error('selftest failed: postinstall did not create project hooks during automatic bootstrap');
   if (!String(postinstallSetup.stdout || '').includes('Codex App global $ skills: installed')) throw new Error('selftest failed: postinstall did not report automatic global Codex App skills');
+  if (!String(postinstallSetup.stdout || '').includes('Removed stale generated skill shadow(s):')) throw new Error('selftest failed: postinstall did not report stale first-party plugin shadow cleanup');
   const postinstallSetupManifest = await readJson(path.join(postinstallSetupTmp, '.sneakoscope', 'manifest.json'));
   if (postinstallSetupManifest.installation?.scope !== 'global') throw new Error('selftest failed: postinstall automatic bootstrap did not use global install scope');
   if (postinstallSetupManifest.design_system_ssot?.authority_file !== DESIGN_SYSTEM_SSOT.authority_file || postinstallSetupManifest.design_system_ssot?.builder_prompt !== DESIGN_SYSTEM_SSOT.builder_prompt) throw new Error('selftest failed: postinstall manifest missing design SSOT policy');
@@ -2108,9 +2160,11 @@ async function selftest() {
   }
   const postinstallSetupGitignore = await safeReadText(path.join(postinstallSetupTmp, '.gitignore'));
   if (!postinstallSetupGitignore.includes('.sneakoscope/') || !postinstallSetupGitignore.includes('.codex/') || !postinstallSetupGitignore.includes('.agents/') || !postinstallSetupGitignore.includes('AGENTS.md')) throw new Error('selftest failed: automatic postinstall bootstrap did not ignore SKS generated files');
-  for (const { command } of DOLLAR_COMMANDS) {
-    const skillName = command.slice(1).toLowerCase();
-    if (!(await exists(path.join(postinstallSetupTmp, 'home', '.agents', 'skills', skillName, 'SKILL.md')))) throw new Error(`selftest failed: postinstall global ${command} skill not installed`);
+  for (const skillName of new Set(DOLLAR_SKILL_NAMES)) {
+    if (!(await exists(path.join(postinstallSetupTmp, 'home', '.agents', 'skills', skillName, 'SKILL.md')))) throw new Error(`selftest failed: postinstall global ${skillName} skill not installed`);
+  }
+  for (const name of stalePluginSkillNames) {
+    if (await exists(path.join(postinstallSetupHome, '.agents', 'skills', name, 'SKILL.md'))) throw new Error(`selftest failed: postinstall global skills shadow the first-party ${name} plugin`);
   }
   if (!(await exists(path.join(postinstallSetupTmp, 'home', '.agents', 'skills', 'getdesign-reference', 'SKILL.md')))) throw new Error('selftest failed: postinstall global getdesign-reference skill not installed');
   const oldNoBootstrap = process.env.SKS_POSTINSTALL_NO_BOOTSTRAP;
@@ -2375,15 +2429,16 @@ async function selftest() {
   if (globalSkillsResult.status !== 'installed') throw new Error(`selftest failed: global Codex App skills not installed: ${globalSkillsResult.status}`);
   const globalSkillStatus = await checkRequiredSkills(globalSkillsTmp, path.join(globalSkillsTmp, '.agents', 'skills'));
   if (!globalSkillStatus.ok) throw new Error(`selftest failed: global Codex App skills missing: ${globalSkillStatus.missing.join(', ')}`);
+  if (await exists(path.join(globalSkillsTmp, '.agents', 'skills', 'computer-use', 'SKILL.md'))) throw new Error('selftest failed: global generated skills shadow the first-party computer-use plugin');
   const codexSkillMirrorExists = await exists(path.join(tmp, '.codex', 'skills', 'research-discovery', 'SKILL.md'));
   if (codexSkillMirrorExists) throw new Error('selftest failed: generated .codex/skills mirror still installed');
   const codexAppSkillExists = await exists(path.join(tmp, '.agents', 'skills', 'research-discovery', 'SKILL.md'));
   if (!codexAppSkillExists) throw new Error('selftest failed: Codex App skill not installed');
-  for (const { command } of DOLLAR_COMMANDS) {
-    const skillName = command.slice(1).toLowerCase();
+  for (const skillName of new Set(DOLLAR_SKILL_NAMES)) {
     const dollarSkillExists = await exists(path.join(tmp, '.agents', 'skills', skillName, 'SKILL.md'));
-    if (!dollarSkillExists) throw new Error(`selftest failed: ${command} skill not installed`);
+    if (!dollarSkillExists) throw new Error(`selftest failed: ${skillName} skill not installed`);
   }
+  if (await exists(path.join(tmp, '.agents', 'skills', 'computer-use', 'SKILL.md'))) throw new Error('selftest failed: project generated skills shadow the first-party computer-use plugin');
   const promptPipelineSkillExists = await exists(path.join(tmp, '.agents', 'skills', 'prompt-pipeline', 'SKILL.md'));
   if (!promptPipelineSkillExists) throw new Error('selftest failed: prompt pipeline skill not installed');
   const promptPipelineText = await safeReadText(path.join(tmp, '.agents', 'skills', 'prompt-pipeline', 'SKILL.md'));
@@ -2652,6 +2707,19 @@ async function selftest() {
   if (!String(hookUpdateOldContext).includes('Update SKS now') || !String(hookUpdateOldContext).includes('Skip update for this conversation')) throw new Error('selftest failed: hook did not prompt when installed SKS is stale');
   const hookUpdateOldState = await readJson(path.join(hookUpdateOldTmp, '.sneakoscope', 'state', 'update-check.json'), {});
   if (hookUpdateOldState.pending_offer?.latest !== '9.9.9') throw new Error('selftest failed: stale installed SKS did not persist pending update offer');
+  const hookUpdateAcceptPayload = JSON.stringify({ cwd: hookUpdateOldTmp, prompt: 'Update SKS now' });
+  const hookUpdateAcceptResult = await runProcess(process.execPath, [hookBin, 'hook', 'user-prompt-submit'], {
+    cwd: hookUpdateOldTmp,
+    input: hookUpdateAcceptPayload,
+    env: { ...hookUpdateCurrentEnv, SKS_INSTALLED_SKS_VERSION: '0.0.0' },
+    timeoutMs: 15000,
+    maxOutputBytes: 256 * 1024
+  });
+  if (hookUpdateAcceptResult.code !== 0) throw new Error(`selftest failed: accepted update hook exited ${hookUpdateAcceptResult.code}: ${hookUpdateAcceptResult.stderr}`);
+  const hookUpdateAcceptJson = JSON.parse(hookUpdateAcceptResult.stdout);
+  const hookUpdateAcceptContext = hookUpdateAcceptJson.hookSpecificOutput?.additionalContext || '';
+  if (!String(hookUpdateAcceptContext).includes('npm i -g sneakoscope@latest')) throw new Error('selftest failed: accepted update hook did not specify the exact npm latest command');
+  if (String(hookUpdateAcceptContext).includes('sks setup') || String(hookUpdateAcceptContext).includes('sks doctor') || String(hookUpdateAcceptContext).includes('npm i -D sneakoscope')) throw new Error('selftest failed: accepted update hook still routes through setup/doctor/project update commands');
   const hookKoreanSksTmp = tmpdir();
   await initProject(hookKoreanSksTmp, {});
   const hookKoreanSksPayload = JSON.stringify({ cwd: hookKoreanSksTmp, prompt: koreanReadmeInstallPrompt });
@@ -2862,7 +2930,7 @@ async function selftest() {
   if (!wikiJson.systemMessage?.includes('wiki refresh')) throw new Error('selftest failed: Wiki route missing system message');
   const codexConfigText = await safeReadText(path.join(tmp, '.codex', 'config.toml'));
   if (!codexConfigText.includes('multi_agent = true')) throw new Error('selftest failed: multi_agent not enabled');
-  if (!codexConfigText.includes('hooks = true') || codexConfigText.includes('codex_hooks = true')) throw new Error('selftest failed: Codex hooks feature flag not migrated to hooks');
+  if (!codexConfigText.includes('codex_hooks = true') || hasLegacyHooksFeatureFlag(codexConfigText)) throw new Error('selftest failed: Codex hooks feature flag not aligned with current codex_hooks setting');
   if (!hasContext7ConfigText(codexConfigText)) throw new Error('selftest failed: Context7 MCP not configured');
   if (!codexConfigText.includes('[profiles.sks-task-low]') || !codexConfigText.includes('[profiles.sks-task-medium]') || !codexConfigText.includes('[profiles.sks-logic-high]') || !codexConfigText.includes('[profiles.sks-fast-high]') || !codexConfigText.includes('[profiles.sks-research-xhigh]') || !codexConfigText.includes('[profiles.sks-mad-high]')) throw new Error('selftest failed: GPT-5.5 reasoning profiles not configured');
   if (!/\[profiles\.sks-mad-high\][\s\S]*?approval_policy = "never"[\s\S]*?sandbox_mode = "danger-full-access"/.test(codexConfigText)) throw new Error('selftest failed: generated sks-mad-high profile is not full access');
@@ -2870,12 +2938,12 @@ async function selftest() {
   if (!codexConfigText.includes('[agents.team_consensus]')) throw new Error('selftest failed: team_consensus agent not configured');
   const preservedConfigTmp = tmpdir();
   await ensureDir(path.join(preservedConfigTmp, '.codex'));
-  await writeTextAtomic(path.join(preservedConfigTmp, '.codex', 'config.toml'), 'model = "gpt-5.5"\nmodel_reasoning_effort = "high"\nservice_tier = "fast"\n\n[notice]\nfast_default_opt_out = true\nkeep = true\n\n[features]\ncodex_hooks = true\nfast_mode_ui = true\n\n[user.fast_mode]\nvisible = true\n');
+  await writeTextAtomic(path.join(preservedConfigTmp, '.codex', 'config.toml'), 'model = "gpt-5.5"\nmodel_reasoning_effort = "high"\nservice_tier = "fast"\n\n[notice]\nfast_default_opt_out = true\nkeep = true\n\n[features]\nhooks = true\nfast_mode_ui = true\n\n[user.fast_mode]\nvisible = true\n');
   await initProject(preservedConfigTmp, {});
   const preservedConfig = await safeReadText(path.join(preservedConfigTmp, '.codex', 'config.toml'));
   if (!/^model = "gpt-5\.5"/m.test(preservedConfig) || !preservedConfig.includes('service_tier = "fast"') || !preservedConfig.includes('fast_mode = true') || !preservedConfig.includes('fast_mode_ui = true') || !preservedConfig.includes('[user.fast_mode]') || !preservedConfig.includes('visible = true') || !preservedConfig.includes('enabled = true') || !preservedConfig.includes('default_profile = "sks-fast-high"') || !/\[profiles\.sks-fast-high\][\s\S]*?service_tier = "fast"/.test(preservedConfig)) throw new Error('selftest failed: Codex config merge dropped or failed to enable Fast mode defaults and GPT-5.5');
   if (preservedConfig.includes('fast_default_opt_out = true') || !preservedConfig.includes('keep = true')) throw new Error('selftest failed: Codex config merge did not remove stale Fast opt-out notice while preserving other notice keys');
-  if (!preservedConfig.includes('hooks = true') || preservedConfig.includes('codex_hooks = true') || !preservedConfig.includes('[profiles.sks-fast-high]')) throw new Error('selftest failed: Codex config merge did not add SKS managed settings or remove the legacy hooks flag');
+  if (!preservedConfig.includes('codex_hooks = true') || hasLegacyHooksFeatureFlag(preservedConfig) || !preservedConfig.includes('[profiles.sks-fast-high]')) throw new Error('selftest failed: Codex config merge did not add current SKS hook settings or remove the legacy hooks flag');
   if (hasTopLevelCodexModeLock(preservedConfig)) throw new Error('selftest failed: Codex config merge left top-level legacy model/reasoning locks that hide Fast mode UI');
   const autoReviewHome = path.join(tmp, 'auto-review-home');
   const autoReviewEnv = { HOME: autoReviewHome };
@@ -3092,7 +3160,7 @@ async function selftest() {
   await writeJsonAtomic(path.join(teamDir, 'team-plan.json'), teamPlan);
   if (teamPlan.agent_session_count !== 5) throw new Error('selftest failed: team default sessions not 5');
   if (teamPlan.role_counts.executor !== 3 || teamPlan.role_counts.user !== 1 || teamPlan.role_counts.reviewer !== 5) throw new Error('selftest failed: team default role counts invalid');
-  if (teamPlan.codex_config_required?.features?.hooks !== true || teamPlan.codex_config_required?.features?.codex_hooks === true) throw new Error('selftest failed: team plan Codex config still uses legacy hooks feature flag');
+  if (teamPlan.codex_config_required?.features?.codex_hooks !== true || teamPlan.codex_config_required?.features?.hooks === true) throw new Error('selftest failed: team plan Codex config still uses legacy hooks feature flag');
   if (!teamPlan.review_gate?.passed || teamPlan.review_gate.required_reviewer_lanes !== 5) throw new Error('selftest failed: team review policy gate did not pass default plan');
   if (teamPlan.codex_config_required?.service_tier !== 'fast' || teamPlan.reasoning?.service_tier !== 'fast') throw new Error('selftest failed: team plan did not require Fast service tier');
   if (!teamPlan.goal_continuation?.enabled || teamPlan.goal_continuation?.mode !== 'ambient_codex_native_goal_overlay') throw new Error('selftest failed: Team plan did not include ambient Goal continuation');
@@ -3177,7 +3245,7 @@ async function selftest() {
   await writeTextAtomic(fakeTmuxLog, '');
   const madCockpit = await launchMadTmuxUi(['--workspace', 'sks-mad-selftest-ui', '--no-attach'], { root: tmp, tmux: { ok: true, bin: fakeTmuxBin, version: '3.4' }, codex: { bin: process.execPath }, app: { ok: true, guidance: [] }, missionId: 'M-MAD-SELFTEST' });
   const madTmuxLogText = await safeReadText(fakeTmuxLog);
-  if (!madCockpit.created || madCockpit.opened?.panes?.length !== 3 || !madTmuxLogText.includes('new-session') || !madTmuxLogText.includes('split-window')) throw new Error('selftest failed: MAD tmux launch did not create a multi-pane cockpit');
+  if (!madCockpit.created || madCockpit.mode !== 'mad_session' || madCockpit.opened?.panes?.length !== 1 || !madTmuxLogText.includes('new-session') || madTmuxLogText.includes('split-window')) throw new Error('selftest failed: MAD tmux launch should create one pane and leave split panes to Team lanes');
   if (previousFakeTmuxLog === undefined) delete process.env.SKS_FAKE_TMUX_LOG;
   else process.env.SKS_FAKE_TMUX_LOG = previousFakeTmuxLog;
   const codexLaunchArgs = defaultCodexLaunchArgs({ SKS_CODEX_REASONING: 'low' }).join(' ');

package/src/cli/maintenance-commands.mjs

@@ -1778,7 +1778,7 @@ export function buildTeamPlan(id, prompt, opts = {}) {
     reasoning: teamReasoningPolicy(prompt, roster),
     codex_config_required: {
       service_tier: 'fast',
-      features: { multi_agent: true, hooks: true },
+      features: { multi_agent: true, codex_hooks: true },
       agents: { max_threads: 6, max_depth: 1 },
       custom_agents_dir: '.codex/agents'
     },

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 = '0.7.58';
+export const PACKAGE_VERSION = '0.7.60';
 export const DEFAULT_PROCESS_TAIL_BYTES = 256 * 1024;
 export const DEFAULT_PROCESS_TIMEOUT_MS = 30 * 60 * 1000;
 

package/src/core/hooks-runtime.mjs

@@ -533,7 +533,7 @@ async function updateCheckContext(root, payload, prompt) {
       pending_offer: null,
       accepted: { conversation_id: conv, latest: pending.latest, accepted_at: nowIso() }
     });
-    return `SKS update check: user accepted update to ${pending.latest}. Before doing other work, run the appropriate update command, then rerun sks setup and sks doctor --fix. Global install: npm i -g sneakoscope. Project install: npm i -D sneakoscope && npx sks setup --install-scope project.`;
+    return `SKS update check: user accepted update to ${pending.latest}. Before doing other work, run exactly this command and nothing else: npm i -g sneakoscope@latest. Do not start a pipeline route, run setup, or run doctor for this accepted update command.`;
   }
   if (updateState.skipped?.conversation_id === conv && updateState.skipped?.latest) {
     return `SKS update check: update ${updateState.skipped.latest} was skipped for this conversation only. Do not ask again in this conversation; check again next conversation.`;
@@ -562,7 +562,7 @@ async function updateCheckContext(root, payload, prompt) {
     pending_offer: { conversation_id: conv, latest: check.latest, offered_at: nowIso() },
     skipped: updateState.skipped?.conversation_id === conv ? null : updateState.skipped || null
   });
-  return `SKS update check: installed ${current}, latest ${check.latest}. Before any other work, ask the user to choose: "Update SKS now" or "Skip update for this conversation". If they choose update, run npm i -g sneakoscope for global installs, or npm i -D sneakoscope && npx sks setup --install-scope project for project installs, then run sks setup and sks doctor --fix. If they skip, do not ask again in this conversation, but check again next conversation.`;
+  return `SKS update check: installed ${current}, latest ${check.latest}. Before any other work, ask the user to choose: "Update SKS now" or "Skip update for this conversation". If they choose update, run exactly this command and nothing else: npm i -g sneakoscope@latest. Do not start a pipeline route, run setup, or run doctor for this accepted update command. If they skip, do not ask again in this conversation, but check again next conversation.`;
 }
 
 async function checkLatestVersion() {

package/src/core/init.mjs

@@ -7,7 +7,7 @@ import { isHarnessSourceProject, writeHarnessGuardPolicy } from './harness-guard
 import { repairSksGeneratedArtifacts } from './harness-conflicts.mjs';
 import { installVersionGitHook } from './version-manager.mjs';
 import { MIN_TEAM_REVIEWER_LANES, MIN_TEAM_REVIEW_POLICY_TEXT } from './team-review-policy.mjs';
-import { AWESOME_DESIGN_MD_REFERENCE, CODEX_APP_IMAGE_GENERATION_DOC_URL, CODEX_COMPUTER_USE_ONLY_POLICY, CODEX_IMAGEGEN_REQUIRED_POLICY, DESIGN_SYSTEM_SSOT, DOLLAR_COMMANDS, DOLLAR_COMMAND_ALIASES, DOLLAR_SKILL_NAMES, FROM_CHAT_IMG_CHECKLIST_ARTIFACT, FROM_CHAT_IMG_COVERAGE_ARTIFACT, FROM_CHAT_IMG_QA_LOOP_ARTIFACT, FROM_CHAT_IMG_TEMP_TRIWIKI_ARTIFACT, FROM_CHAT_IMG_TEMP_TRIWIKI_SESSIONS, GETDESIGN_REFERENCE, PPT_CONDITIONAL_SKILL_ALLOWLIST, PPT_PIPELINE_MCP_ALLOWLIST, PPT_PIPELINE_SKILL_ALLOWLIST, RECOMMENDED_DESIGN_REFERENCES, RECOMMENDED_MCP_SERVERS, RECOMMENDED_SKILLS, chatCaptureIntakeText, context7ConfigToml, getdesignReferencePolicyText, imageUxReviewPipelinePolicyText, outcomeRubricPolicyText, pptPipelineAllowlistPolicyText, speedLanePolicyText, stackCurrentDocsPolicyText, triwikiContextTracking, triwikiContextTrackingText, triwikiStagePolicyText } from './routes.mjs';
+import { AWESOME_DESIGN_MD_REFERENCE, CODEX_APP_IMAGE_GENERATION_DOC_URL, CODEX_COMPUTER_USE_ONLY_POLICY, CODEX_IMAGEGEN_REQUIRED_POLICY, DESIGN_SYSTEM_SSOT, DOLLAR_COMMANDS, DOLLAR_COMMAND_ALIASES, DOLLAR_SKILL_NAMES, FROM_CHAT_IMG_CHECKLIST_ARTIFACT, FROM_CHAT_IMG_COVERAGE_ARTIFACT, FROM_CHAT_IMG_QA_LOOP_ARTIFACT, FROM_CHAT_IMG_TEMP_TRIWIKI_ARTIFACT, FROM_CHAT_IMG_TEMP_TRIWIKI_SESSIONS, GETDESIGN_REFERENCE, PPT_CONDITIONAL_SKILL_ALLOWLIST, PPT_PIPELINE_MCP_ALLOWLIST, PPT_PIPELINE_SKILL_ALLOWLIST, RECOMMENDED_DESIGN_REFERENCES, RECOMMENDED_MCP_SERVERS, RECOMMENDED_SKILLS, RESERVED_CODEX_PLUGIN_SKILL_NAMES, chatCaptureIntakeText, context7ConfigToml, getdesignReferencePolicyText, imageUxReviewPipelinePolicyText, outcomeRubricPolicyText, pptPipelineAllowlistPolicyText, speedLanePolicyText, stackCurrentDocsPolicyText, triwikiContextTracking, triwikiContextTrackingText, triwikiStagePolicyText } from './routes.mjs';
 import { SKILL_DREAM_POLICY, skillDreamPolicyText } from './skill-forge.mjs';
 
 const REFLECTION_MEMORY_PATH = '.sneakoscope/memory/q2_facts/post-route-reflection.md';
@@ -94,7 +94,7 @@ 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 `$Team`: analysis scouts, TriWiki refresh/validate, read-only debate, consensus, concrete runtime task graph/inboxes, fresh executor team, minimum five-lane Team review, integration, Honest Mode.\n- `$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. Team completion requires at least five independent reviewer/QA validation lanes before integration or final, even when a prompt requests fewer reviewers. Use `sks validate-artifacts latest` before claiming those artifacts pass.\n- `$DFix` is Direct Fix: only tiny copy/config/docs/labels/spacing/translation/simple mechanical edits, bypassing the main pipeline, Team, TriWiki/TriFix/reflection recording, and persistent route state; it still uses a one-line DFix-specific Honest check before final. Broad implementation stays on `$Team`, while UI design specifics follow the relevant design/UI route rules. `$PPT` is the restrained, information-first HTML/PDF presentation route and must seal delivery context, audience profile, STP, decision context, and 3+ pain-point/solution/aha mappings before design/render work. It must avoid over-designed visuals, carry detail through hierarchy, spacing, alignment, thin rules, source clarity, and subtle accents, preserve editable source HTML under `source-html/`, record `ppt-parallel-report.json`, and clean PPT-only temporary build files before completion. `$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` as the only design decision SSOT. If missing, create it through `design-system-builder` from `docs/Design-Sys-Prompt.md`; getdesign.md, getdesign-reference, and curated DESIGN.md examples from https://github.com/VoltAgent/awesome-design-md are source inputs to fuse into that SSOT or route-local style tokens, not parallel design authorities. Image/logo/raster assets use `imagegen`, which must prefer official Codex App built-in image generation via `$imagegen` / `gpt-image-2` before API generation and must not be replaced by placeholder SVG/HTML/CSS, prose-only reviews, or fabricated files when generated raster evidence is required.\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- Skill dreaming stays lightweight: route use records JSON counters in `.sneakoscope/skills/dream-state.json`, and full skill inventory/recommendation runs only after the configured count/cooldown threshold. Reports are recommendation-only; deleting or merging skills needs explicit user approval.\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`, `$ppt`, `$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 `$Team`: analysis scouts, TriWiki refresh/validate, read-only debate, consensus, concrete runtime task graph/inboxes, fresh executor team, minimum five-lane Team review, integration, Honest Mode.\n- `$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. Team completion requires at least five independent reviewer/QA validation lanes before integration or final, even when a prompt requests fewer reviewers. Use `sks validate-artifacts latest` before claiming those artifacts pass.\n- `$DFix` is Direct Fix: only tiny copy/config/docs/labels/spacing/translation/simple mechanical edits, bypassing the main pipeline, Team, TriWiki/TriFix/reflection recording, and persistent route state; it still uses a one-line DFix-specific Honest check before final. Broad implementation stays on `$Team`, while UI design specifics follow the relevant design/UI route rules. `$PPT` is the restrained, information-first HTML/PDF presentation route and must seal delivery context, audience profile, STP, decision context, and 3+ pain-point/solution/aha mappings before design/render work. It must avoid over-designed visuals, carry detail through hierarchy, spacing, alignment, thin rules, source clarity, and subtle accents, preserve editable source HTML under `source-html/`, record `ppt-parallel-report.json`, and clean PPT-only temporary build files before completion. `$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` as the only design decision SSOT. If missing, create it through `design-system-builder` from `docs/Design-Sys-Prompt.md`; getdesign.md, getdesign-reference, and curated DESIGN.md examples from https://github.com/VoltAgent/awesome-design-md are source inputs to fuse into that SSOT or route-local style tokens, not parallel design authorities. Image/logo/raster assets use `imagegen`, which must prefer official Codex App built-in image generation via `$imagegen` / `gpt-image-2` before API generation and must not be replaced by placeholder SVG/HTML/CSS, prose-only reviews, or fabricated files when generated raster evidence is required.\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- Skill dreaming stays lightweight: route use records JSON counters in `.sneakoscope/skills/dream-state.json`, and full skill inventory/recommendation runs only after the configured 10-route-event threshold and cooldown. Reports are recommendation-only; deleting or merging skills needs explicit user approval.\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`, `$ppt`, `$goal`, `$dfix`, `$qa-loop`, etc.) as the app control surface.\n";
 
 function agentsBlockText() {
   return AGENTS_BLOCK
@@ -440,10 +440,10 @@ function installPolicy(scope, commandPrefix) {
 function mergeManagedCodexConfigToml(existingContent = '') {
   let next = removeLegacyTopLevelCodexModeLocks(String(existingContent || '').trimEnd());
   next = removeTomlTableKey(next, 'notice', 'fast_default_opt_out');
-  next = removeTomlTableKey(next, 'features', 'codex_hooks');
+  next = removeTomlTableKey(next, 'features', 'hooks');
   next = upsertTopLevelTomlString(next, 'model', 'gpt-5.5');
   next = upsertTopLevelTomlString(next, 'service_tier', 'fast');
-  next = upsertTomlTableKey(next, 'features', 'hooks = true');
+  next = upsertTomlTableKey(next, 'features', 'codex_hooks = true');
   next = upsertTomlTableKey(next, 'features', 'multi_agent = true');
   next = upsertTomlTableKey(next, 'features', 'fast_mode = true');
   next = upsertTomlTableKey(next, 'features', 'fast_mode_ui = true');
@@ -750,7 +750,6 @@ export async function installSkills(root) {
     '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. Infer scope, target, mutation policy, and login boundary from the prompt plus TriWiki/current-code defaults; do not surface a prequestion sheet. Credentials are runtime-only; never save secrets. UI-level E2E needs official 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`,
     'ppt': `---\nname: ppt\ndescription: $PPT information-first HTML/PDF presentation pipeline with inferred STP, audience, pain-point, format, research, design-system, and verification contract.\n---\n\nUse only when the user invokes $PPT or asks to create a presentation, deck, slides, pitch deck, proposal deck, HTML presentation, or PDF presentation artifact. Before artifact work, auto-seal presentation-specific answers from prompt, TriWiki/current-code defaults, and conservative policy: delivery context, target audience profile including role/average age/job/industry/topic familiarity/decision power, STP strategy, decision context and objections, and 3+ pain-point to solution mappings with expected aha moments. Do not surface a prequestion sheet. Presentation design must be simple, restrained, and information-first: avoid over-designed decoration, ornamental gradients, nested cards, and effects that compete with the message. Design detail should be embedded through typography hierarchy, spacing, alignment, thin rules, source clarity, and subtle accents. ${pptPipelineAllowlistPolicyText()} Use design.md as the only design decision SSOT. If design.md is missing, use docs/Design-Sys-Prompt.md plus getdesign-reference and curated DESIGN.md examples from ${AWESOME_DESIGN_MD_REFERENCE.url} only as source inputs, then fuse them into route-local PPT style tokens with a recorded design_ssot instead of treating references as parallel authorities. If generated image assets or slide visual critique are needed, use Codex App $imagegen/gpt-image-2 only when that asset/review need is explicitly sealed in the $PPT contract; direct API fallback, placeholder files, and prose-only substitutes do not satisfy the route gate. ${CODEX_IMAGEGEN_REQUIRED_POLICY} Use web or Context7 evidence only when external facts/libraries/current docs are required by the PPT contract, record verified claims in ppt-fact-ledger.json, record generated image asset plans/results/blockers in ppt-image-asset-ledger.json, then create the PDF plus editable source HTML under source-html/, keep independent strategy/render/file-write phases parallel where inputs allow, record ppt-parallel-report.json, run the bounded ppt-review-policy/ppt-review-ledger/ppt-iteration-report loop, and verify readability, overlap, format fit, source coverage, export state, unsupported-claim status, image-asset completion, review-loop termination, and temporary build files cleanup. Finish with reflection and Honest Mode.\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`,
@@ -796,11 +795,12 @@ export async function installSkills(root) {
   }
   const skillNames = Object.keys(skills);
   const removedStaleGeneratedSkills = await removeStaleGeneratedSkillsFromManifest(root, skillNames);
+  const removedPluginSkillCollisions = await removeGeneratedPluginSkillCollisions(root);
   await writeGeneratedSkillManifest(root, skillNames);
   return {
     installed_skills: skillNames,
     generated_files: generatedSkillFiles(skillNames),
-    removed_stale_generated_skills: removedStaleGeneratedSkills,
+    removed_stale_generated_skills: [...removedStaleGeneratedSkills, ...removedPluginSkillCollisions].sort(),
     removed_agent_skill_aliases: await removeGeneratedAgentSkillAliases(root, skillNames),
     removed_codex_skill_mirrors: await removeGeneratedCodexSkillMirrors(root, skillNames)
   };
@@ -846,8 +846,29 @@ async function removeStaleGeneratedSkillsFromManifest(root, skillNames) {
   return removed.sort();
 }
 
+async function removeGeneratedPluginSkillCollisions(root) {
+  const removed = [];
+  for (const name of RESERVED_CODEX_PLUGIN_SKILL_NAMES) {
+    const dir = path.join(root, '.agents', 'skills', name);
+    const skillPath = path.join(dir, 'SKILL.md');
+    const text = await readText(skillPath, null);
+    if (!isGeneratedSksPluginCollisionSkill(text, name)) continue;
+    await fsp.rm(dir, { recursive: true, force: true });
+    removed.push(path.relative(root, dir));
+  }
+  return removed.sort();
+}
+
+function isGeneratedSksPluginCollisionSkill(text, name) {
+  if (typeof text !== 'string') return false;
+  const s = String(text);
+  if (!new RegExp(`^name:\\s*${escapeRegExp(name)}\\s*$`, 'm').test(s)) return false;
+  if (/\bnot generated by SKS\b/i.test(s)) return false;
+  return /Maximum-speed \$Computer-Use\/\$CU lane|Codex App pipeline activation:|Sneakoscope generated|Dollar-command route generated by SKS/i.test(s);
+}
+
 function enrichSkillContent(name, content) {
-  if (!['sks', 'answer', 'wiki', 'team', 'qa-loop', 'ppt', 'image-ux-review', 'ux-review', 'visual-review', 'ui-ux-review', '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;
+  if (!['sks', 'answer', 'wiki', 'team', 'qa-loop', 'ppt', 'image-ux-review', 'ux-review', 'visual-review', 'ui-ux-review', '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();
   const activation = pipelineActivationText(name);
   if (text.includes('TriWiki context-tracking SSOT')) {
@@ -865,7 +886,7 @@ Context tracking:
 }
 
 function pipelineActivationText(name) {
-  const stateful = new Set(['sks', 'team', 'qa-loop', 'ppt', 'image-ux-review', 'ux-review', 'visual-review', 'ui-ux-review', 'computer-use', 'computer-use-fast', 'cu', 'goal', 'research', 'autoresearch', 'db', 'gx', 'prompt-pipeline', 'pipeline-runner']);
+  const stateful = new Set(['sks', 'team', 'qa-loop', 'ppt', 'image-ux-review', 'ux-review', 'visual-review', 'ui-ux-review', 'computer-use-fast', 'cu', 'goal', 'research', 'autoresearch', 'db', 'gx', 'prompt-pipeline', 'pipeline-runner']);
   if (!stateful.has(name)) return '';
   return `Codex App pipeline activation:
 - If the SKS UserPromptSubmit hook already injected route context, follow that context.
@@ -875,7 +896,7 @@ function pipelineActivationText(name) {
 }
 
 async function writeSkillMetadata(dir, name) {
-  const effort = ['computer-use', 'computer-use-fast', 'cu'].includes(name)
+  const effort = ['computer-use-fast', 'cu'].includes(name)
     ? 'low'
     : ['research', 'autoresearch', 'research-discovery', 'autoresearch-loop', 'from-chat-img'].includes(name)
     ? 'xhigh'

package/src/core/routes.mjs

@@ -14,6 +14,7 @@ export const CODEX_APP_IMAGE_GENERATION_DOC_URL = 'https://developers.openai.com
 export const OPENAI_IMAGE_GENERATION_DOC_URL = 'https://developers.openai.com/api/docs/guides/image-generation';
 export const CODEX_COMPUTER_USE_ONLY_POLICY = 'Pipeline UI/browser verification and visual inspection must use Codex Computer Use only. Do not use Playwright, Chrome MCP, Browser Use, Selenium, Puppeteer, or any other browser automation substitute; if Codex Computer Use is unavailable, mark the UI/browser evidence unverified instead of substituting another tool. In Codex App prompts, invoke @Computer or @AppName in a new thread when live Computer Use tools are needed; SKS hooks and skills can require the policy but cannot attach missing host tools to an already-started turn.';
 export const CODEX_IMAGEGEN_REQUIRED_POLICY = 'Pipeline image generation, raster asset creation/editing, and generated image-review evidence must use real Codex App imagegen/$imagegen with gpt-image-2 when that evidence is required. Do not substitute placeholder SVG/HTML/CSS, prose-only critique, stock-like stand-ins, manually fabricated files, or missing-output ledgers for requested/generated raster assets or required generated review images. If imagegen/gpt-image-2 is unavailable, record the blocker and mark the image asset or review evidence unverified instead of passing the gate. In Codex App prompts, invoke $imagegen when live image generation is needed; SKS hooks and skills can require the policy but cannot attach missing host image-generation tools to an already-started turn.';
+export const RESERVED_CODEX_PLUGIN_SKILL_NAMES = Object.freeze(['computer-use', 'browser', 'browser-use']);
 export const FORBIDDEN_BROWSER_AUTOMATION_RE = /\b(playwright|chrome\s+mcp|browser\s+use|selenium|puppeteer)\b/i;
 
 export function evidenceMentionsForbiddenBrowserAutomation(value, seen = new Set()) {
@@ -115,7 +116,6 @@ export const RECOMMENDED_SKILLS = [
   'getdesign-reference',
   'imagegen',
   'image-ux-review',
-  'computer-use',
   'computer-use-fast',
   'db-safety-guard',
   REFLECTION_SKILL_NAME,
@@ -323,7 +323,7 @@ export const ROUTES = [
     mode: 'IMAGE_UX_REVIEW',
     route: 'image-generation UI/UX review loop',
     description: 'Review UI/UX through the imagegen/gpt-image-2 visual critique loop: source screenshots become generated annotated review images, those images become issue ledgers, then fixes are rechecked.',
-    requiredSkills: ['image-ux-review', 'imagegen', 'computer-use', 'pipeline-runner', REFLECTION_SKILL_NAME, 'honest-mode'],
+    requiredSkills: ['image-ux-review', 'imagegen', 'cu', 'pipeline-runner', REFLECTION_SKILL_NAME, 'honest-mode'],
     dollarAliases: ['$UX-Review'],
     appSkillAliases: ['ux-review', 'visual-review', 'ui-ux-review'],
     lifecycle: ['target_and_capture_inventory', 'source_screenshots', 'gpt_image_2_annotated_review_image', 'generated_image_text_extraction', 'issue_ledger', 'optional_safe_fixes', 'changed_screen_recheck', 'post_route_reflection', 'honest_mode'],
@@ -339,7 +339,7 @@ export const ROUTES = [
     mode: 'COMPUTER_USE',
     route: 'Computer Use fast lane',
     description: 'Maximum-speed Codex Computer Use lane for UI/browser/visual tasks: skip Team debate and upfront TriWiki loops, run only focused Computer Use steps, then finish with evidence, TriWiki refresh/validate, and Honest Mode.',
-    requiredSkills: ['computer-use', 'honest-mode'],
+    requiredSkills: ['cu', 'honest-mode'],
     dollarAliases: ['$CU'],
     appSkillAliases: ['computer-use-fast', 'cu'],
     lifecycle: ['fast_intake', 'focused_computer_use_steps', 'evidence_summary', 'final_triwiki_refresh_validate', 'honest_mode'],
@@ -467,13 +467,17 @@ export const DOLLAR_COMMANDS = ROUTES.flatMap(({ command, route, description, do
   { command, route, description },
   ...dollarAliases.map((alias) => ({ command: alias, route, description }))
 ]);
-export const DOLLAR_SKILL_NAMES = ROUTES.flatMap((route) => [
-  dollarSkillName(route.command),
-  ...(route.appSkillAliases || [])
-]);
+export function routeAppSkillNames(route) {
+  const canonical = dollarSkillName(route.command);
+  return [
+    ...(RESERVED_CODEX_PLUGIN_SKILL_NAMES.includes(canonical) ? [] : [canonical]),
+    ...(route.appSkillAliases || [])
+  ];
+}
+
+export const DOLLAR_SKILL_NAMES = ROUTES.flatMap((route) => routeAppSkillNames(route));
 export const DOLLAR_COMMAND_ALIASES = ROUTES.flatMap((route) => [
-  { canonical: route.command, app_skill: `$${dollarSkillName(route.command)}` },
-  ...(route.appSkillAliases || []).map((alias) => ({ canonical: route.command, app_skill: `$${alias}` }))
+  ...routeAppSkillNames(route).map((alias) => ({ canonical: route.command, app_skill: `$${alias}` }))
 ]);
 
 export const COMMAND_CATALOG = [

package/src/core/skill-forge.mjs

@@ -8,7 +8,7 @@ export const SKILL_DREAM_POLICY = Object.freeze({
   schema_version: 1,
   state_path: '.sneakoscope/skills/dream-state.json',
   latest_report_path: '.sneakoscope/reports/skill-dream-latest.json',
-  min_events_between_runs: 12,
+  min_events_between_runs: 10,
   min_interval_hours: 24,
   max_events_retained: 160,
   max_skill_lines_before_compression: 80,
@@ -34,12 +34,12 @@ const PROTECTED_SKILL_NAMES = new Set([
 ]);
 
 const MERGE_GROUPS = [
-  { id: 'computer-use-aliases', skills: ['computer-use', 'computer-use-fast', 'cu'], action: 'keep_one_canonical_and_alias_the_rest_when_user_approves' },
+  { id: 'computer-use-aliases', skills: ['computer-use-fast', 'cu'], action: 'keep_one_canonical_and_alias_the_rest_when_user_approves; reserve computer-use for the first-party Codex plugin' },
   { id: 'research-loop-family', skills: ['research', 'research-discovery', 'autoresearch', 'autoresearch-loop'], action: 'compress_overlap_without_removing_distinct_route_semantics' }
 ];
 
 export function skillDreamPolicyText() {
-  return 'Skill dreaming policy: record only cheap route/skill usage counters in `.sneakoscope/skills/dream-state.json`; do not evaluate every conversation. Run `sks skill-dream run` or the automatic due check only after the configured event count and cooldown. Reports are recommendation-only: keep/merge/prune/improve candidates may update future generated skill wording, but skill deletion or merge requires explicit user approval.';
+  return 'Skill dreaming policy: record only cheap route/skill usage counters in `.sneakoscope/skills/dream-state.json`; do not evaluate every conversation. Run `sks skill-dream run` or the automatic due check only after the configured event count and cooldown, defaulting to one due check every 10 route events subject to cooldown. Reports are recommendation-only: keep/merge/prune/improve candidates may update future generated skill wording, but skill deletion or merge requires explicit user approval.';
 }
 
 export function createSkillCandidate(opts = {}) {

package/src/core/tmux-ui.mjs

@@ -368,7 +368,7 @@ export function formatTmuxBanner(status = null) {
     'CLI-first runtime:',
     '  sks                 open or attach the default tmux Codex CLI session',
     '  sks tmux open       open or attach a tmux Codex CLI session with explicit flags',
-    '  sks --mad           open one-shot MAD full-access auto-review tmux cockpit',
+    '  sks --mad           open one-shot MAD full-access auto-review tmux session',
     '  sks team "task"     prepare Team mission and open the tmux multi-pane live view',
     '',
     'Useful terminal commands:',
@@ -506,36 +506,13 @@ export async function launchMadTmuxUi(args = [], opts = {}) {
   if (args.includes('--status-only')) return { plan };
   const missionId = opts.missionId || opts.madMissionId || 'latest';
   const mainCommand = codexLaunchCommand(plan.root, plan.codex.bin, plan.codexArgs);
-  const statusCommand = [
-    terminalTitleCommand('mad: permission gate'),
-    `cd ${shellEscape(plan.root)}`,
-    'while :; do clear',
-    `printf '\\033[1;35mSKS MAD permission gate\\033[0m\\nMission: %s\\n\\n' ${shellEscape(missionId)}`,
-    `node ${shellEscape(path.join(packageRoot(), 'bin', 'sks.mjs'))} pipeline status ${shellEscape(missionId)} || true`,
-    'printf "\\nRefreshes every 3s. Cleanup when done by closing the MAD gate.\\n"',
-    'sleep 3',
-    'done'
-  ].join('; ');
-  const helpCommand = [
-    terminalTitleCommand('mad: live guide'),
-    'clear',
-    colorizedLaneBannerCommand(['SKS MAD tmux cockpit', 'Panes: Codex CLI | permission gate | live guide', 'Guard: catastrophic DB wipe/all-row/project-management operations remain blocked', ''], 'magenta'),
-    `cd ${shellEscape(plan.root)}`,
-    `printf 'Attach: tmux attach-session -t %s\\n' ${shellEscape(plan.session)}`,
-    `printf 'Mission: %s\\n\\n' ${shellEscape(missionId)}`,
-    `printf 'Commands:\\n  sks pipeline status %s\\n  sks db scan\\n  sks doctor\\n\\n' ${shellEscape(missionId)}`,
-    'printf "This pane stays open so the tmux layout is visibly multi-pane.\\n"',
-    'while :; do sleep 3600; done'
-  ].join('; ');
   const panes = [
-    { cwd: plan.root, command: mainCommand, focused: true, role: 'codex', title: 'Codex CLI' },
-    { cwd: plan.root, command: statusCommand, role: 'mad_gate', title: 'MAD gate', vertical: false },
-    { cwd: plan.root, command: helpCommand, role: 'mad_guide', title: 'MAD guide', vertical: true }
+    { cwd: plan.root, command: mainCommand, focused: true, role: 'codex', title: 'Codex CLI' }
   ];
-  const created = await createTmuxSession({ ...plan, command: mainCommand }, panes, { layout: 'tiled', recreate: true });
-  if (created.ok) await writeTmuxSessionRecord(plan.root, { session: created.session, attach_command: created.attach_command, panes: created.panes, mode: 'mad_cockpit', mission_id: missionId }).catch(() => null);
+  const created = await createTmuxSession({ ...plan, command: mainCommand }, panes, { recreate: true });
+  if (created.ok) await writeTmuxSessionRecord(plan.root, { session: created.session, attach_command: created.attach_command, panes: created.panes, mode: 'mad_session', mission_id: missionId }).catch(() => null);
   if (!args.includes('--quiet')) {
-    console.log(`SKS MAD tmux cockpit: ${created.session || plan.session}`);
+    console.log(`SKS MAD tmux session: ${created.session || plan.session}`);
     if (created.ok) console.log(`tmux: opened ${created.panes.length} pane(s)`);
     else console.log(`tmux: not created (${created.stderr || 'tmux failed'})`);
     if (created.ok) console.log(`Attach: ${created.attach_command}`);
@@ -549,7 +526,7 @@ export async function launchMadTmuxUi(args = [], opts = {}) {
       process.exitCode = attached.status || 1;
     }
   }
-  return { plan, created: Boolean(created.ok), session: created.session || plan.session, opened: created, attached, mode: 'mad_cockpit', mission_id: missionId };
+  return { plan, created: Boolean(created.ok), session: created.session || plan.session, opened: created, attached, mode: 'mad_session', mission_id: missionId };
 }
 
 function printTmuxLaunchBlocked(plan, opts = {}) {