sneakoscope 6.1.0 → 6.1.2

package/README.md

@@ -13,7 +13,7 @@ sneakoscope is a proof-first Codex trust layer for bounded agent workflows, sear
 
 # Sneakoscope Codex
 
-**The proof-first swarm harness for Codex. Machine-verified completion, not vibes.**
+**The proof-first workflow harness for Codex. Machine-verified completion, not vibes.**
 
 [![npm version](https://img.shields.io/npm/v/sneakoscope?color=cb3837&logo=npm)](https://www.npmjs.com/package/sneakoscope)
 [![node](https://img.shields.io/badge/node-%3E%3D20.11-339933?logo=node.js&logoColor=white)](#requirements)
@@ -23,9 +23,9 @@ sneakoscope is a proof-first Codex trust layer for bounded agent workflows, sear
 
 </div>
 
-Sneakoscope Codex (`sks`) is a Codex CLI and Codex App harness for people who want parallel AI coding without losing proof. It gives Codex a simple front door, a dynamic worker swarm, a local dashboard, TriWiki project memory, and release gates that separate machine evidence from LLM opinion.
+Sneakoscope Codex (`sks`) is a Codex CLI and Codex App harness for people who want parallel AI coding without losing proof. It gives Codex a simple front door, an official subagent workflow, a local dashboard, TriWiki project memory, and release gates that separate machine evidence from LLM opinion.
 
-Current release: SKS **6.1.0**. Normal Codex sessions continue to inherit the complete Codex catalog without silent replacement. Naruto workers now use a scoped, live-catalog-verified GPT-5.6 policy: Terra `xhigh/max` for coding, Sol `max` for refactoring/planning/strategy/integration, and Luna `xhigh/max` for E2E/browser/Computer Use/GUI verification. This release restores the Codex Desktop Fast selector under codex-lb; its `1.5x` multiplier follows the [official Codex Speed documentation](https://learn.chatgpt.com/docs/agent-configuration/speed), not an SKS benchmark. It also self-repairs native capability plugins and hardens Voxel TriWiki retention: command help stays read-only, closed routes are not kept active, recent sessions receive a two-hour grace window, mission compaction preserves durable evidence byte-for-byte and deletes only known disposable runtime files, legacy gzip archives are transparently SHA-256-verified when read, full state-budget scans cover the complete top-level state surface, and release-gate history retains five runs by default. See [CHANGELOG.md](CHANGELOG.md).
+Current release: SKS **6.1.2**. `$Naruto` is the SKS alias for the Codex official subagent workflow. The parent runs on GPT-5.6 Sol Max, clear bounded subagents use GPT-5.6 Luna Max, and reasoning-sensitive work such as UI, review, debugging, planning, integration, security, database, and release judgment uses GPT-5.6 Sol Max. Official `SubagentStart`/`SubagentStop` events prove lifecycle only; successful completion additionally requires a structured parent summary with an explicit outcome for every thread. Preparation context alone is never completion proof. Normal non-Naruto Codex sessions continue to preserve explicit user model choices. See [CHANGELOG.md](CHANGELOG.md).
 
 ## Install
 
@@ -42,19 +42,33 @@ npm i -g sneakoscope
 sks doctor --fix
 ```
 
+The SKS menu bar shows the installed Codex CLI version and latest known version. An `⬆` marker appears when an update is available; **Update Codex CLI Now** uses native `codex update` when the selected CLI advertises it, otherwise it verifies the installation provenance and invokes the matching official standalone-installer, npm-global, or Homebrew-cask update method. If the method cannot be verified, it fails closed instead of guessing. This is an explicit global tool mutation. **Run sks doctor --fix** performs the global-only menu repair flow without treating the user's home directory as a project.
+
 ## The Front Door
 
 | Command | What it does |
 | --- | --- |
 | `$Plan "task"` | Planning only. Writes `.sneakoscope/plans/<slug>.md`; no code edits. |
-| `$Work` | Executes the latest plan through evidence-gated SKS work. |
-| `$Swarm "task"` | Runs the Naruto dynamic parallel swarm with machine verification. |
+| Explicit `$Work` | Executes the latest plan through evidence-gated SKS work. Ordinary prose containing “work” is not treated as this alias. |
+| `$Swarm "task"` | Compatibility alias for the Naruto Codex official subagent workflow. |
 | `$Team "task"` | Deprecated v5 compatibility alias. New execution redirects to `$Naruto`; legacy Team observe/watch commands remain available for old missions. |
 | `$MAD-SKS` / `sks mad-sks` | Single high-risk MAD route for scoped permission widening plus SQL-plane execution, including read-back proof and profile closure. |
 | `$MAD-DB` / `sks mad-db` | Deprecated compatibility alias. Translates to `$MAD-SKS` sql-plane commands for one release. |
 | `$Review` / `sks review --staged` | Reviews diffs with `evidence: machine` findings sorted above `evidence: llm`. |
 | `sks ui` | Opens the local live dashboard at `http://127.0.0.1:4477`. |
 
+## Naruto In 6.1.2
+
+`$Naruto` and `sks naruto run "task" --agents 8 --max-threads 12` use Codex official subagents. The parent is GPT-5.6 Sol Max; clear bounded `worker`/exploration slices use GPT-5.6 Luna Max; UI, testing, debugging, architecture, integration, security, database, research, release, and other judgment-sensitive work use narrow GPT-5.6 Sol Max custom specialists.
+
+Fresh SKS-owned project config uses `max_threads = 12`, `max_depth = 1`, `job_max_runtime_seconds = 1200`, and `interrupt_message = true`. `max_depth = 1` means subagents cannot spawn nested subagents. Explicit user limits are preserved, and larger requests run in waves.
+
+Gates are task-profile aware: greetings and answer-only turns create no mission gate; tiny work gets minimal verification; parallel work gets scoped ownership and verification; high-risk work keeps the full safety gates. `SubagentStart`/`SubagentStop` prove lifecycle only. Completion also requires `subagent-parent-summary.json` with one trustworthy structured outcome per thread, correlated with `subagent-events.jsonl` and `subagent-evidence.json`.
+
+SKS installs sixteen narrow project custom agents and recommends only the roles relevant to the task. Automatic fan-out is one child by default, two for explicit parallel work or independent risk domains, and three only for critical multi-domain work; explicit `--agents N` is still supported. In CLI Zellij mode, the right side is a live observability surface rather than a static lane reservation: one monitor plus one viewport by default (maximum three) shows official thread role/model, redacted live phase/task/file updates from exact-agent Codex 0.144.1+ rollouts, `running`, `verifying`, and trustworthy parent-verdict completion/failure states. Rollout activity is display-only and never completion proof.
+
+`--clones` and `workers` remain one-release spelling aliases for official subagent behavior. The historical Naruto process swarm and its environment opt-in are removed; legacy backend, scheduler, pool, and model flags fail closed.
+
 ## Why Not Just An LLM Reviewer?
 
 | Question | Oracle-style LLM review | SKS gate/review |
@@ -62,14 +76,14 @@ sks doctor --fix
 | Did tests/typecheck fail? | Another model may say so. | Machine check output is tagged `evidence: machine`. |
 | Are findings ranked? | Usually one blended opinion. | Machine evidence sorts before LLM findings. |
 | Can work stop? | The model decides. | Stop gates, Completion Proof, and Honest Mode decide. |
-| Can I watch the swarm? | Usually no runtime UI. | Zellij panes plus `sks ui` SSE dashboard. |
+| Can I inspect agent-thread progress? | Usually no runtime UI. | `sks ui` plus the official Codex subagent/thread surfaces. |
 
 ## Dashboard
 
 `sks ui` serves a dependency-free localhost dashboard with:
 
 - mission, route, elapsed time, and gate badge
-- live worker slot grid with role, backend/model badge, progress, and current task
+- live official subagent thread grid with role/model badge, progress, and current task
 - run/verify/queue/done/fail counters
 - recent mission events
 - current gate checklist
@@ -84,19 +98,20 @@ The reproducible VHS script lives at [docs/demo.tape](docs/demo.tape).
 vhs docs/demo.tape
 ```
 
-It shows the v5 flow: one-line install, `$Plan`, `$Work`/`$Swarm`, `sks review`, and `sks ui`.
+It shows the current quickstart flow: one-line install, `$Plan`, `sks review`, `sks ui`, and an official `$Naruto` subagent run.
 
 ## Proof Surfaces
 
-- Dynamic swarm: `sks naruto run "task" --clones 14 --json`
+- Official subagents: `sks naruto run "task" --agents 14 --max-threads 12 --json`
 - Review report: `.sneakoscope/reports/review-report.json`
 - Harness benchmark: `.sneakoscope/reports/harness-benchmark.json`
 - Project memory: `sks memory build`
 - Codebase index/pack for LLM context: `sks wiki refresh --code`, `sks wiki validate --json` (code-pack freshness)
 - Native capability repair: `sks doctor --fix` (imagegen/Computer Use/Browser Use), `.sneakoscope/reports/native-capability-readiness.json`
+- codex-lb continuity: `sks codex-lb status --json` verifies the selected proxy's unauthenticated `/health` `X-App-Version`. Tool-heavy continuation requires codex-lb `1.21.0-beta.3` or later; older or unverified deployments block setup, doctor, and launch instead of silently falling back.
 - Agent bridge for any agent system: `sks mcp-server`, `sks agent-bridge setup`, `SKS_AGENT_MODE=1` — see [docs/AGENT-BRIDGE.md](docs/AGENT-BRIDGE.md)
-- Release gates: `node ./dist/scripts/release-gate-dag-runner.js --preset release --full`
-- Lifecycle-disabled npm release: run `npm run release:check:full`, then `npm run publish:prep-ignore-scripts`, and verify with `npm publish --dry-run --ignore-scripts --json` before the intentional `npm run publish:ignore-scripts` publication wrapper.
+- Release gates: `npm run release:check:affected` for ordinary change-aware verification and `npm run release:check:confidence` for the final local confidence pass.
+- Release preparation handoff: run `npm run typecheck --silent`, one `npm run build:clean --silent`, focused tests for the changed surfaces, `npm run release:check:affected`, `npm run release:check:confidence`, and finally `npm pack --dry-run --ignore-scripts --json`. Publish authorization and publication remain a distinct repository-maintainer workflow.
 - Release readiness notes: [docs/release-readiness.md](docs/release-readiness.md) and [CHANGELOG.md](CHANGELOG.md)
 - Image generation review routes require Codex App `$imagegen`/`gpt-image-2` evidence with recorded output hashes; direct API fallback and mock fixtures do not satisfy full route gates.
 
@@ -111,6 +126,8 @@ It shows the v5 flow: one-line install, `$Plan`, `$Work`/`$Swarm`, `sks review`,
   - Update installs always rebuild the companion with the newly installed SKS package, preventing a previous-version updater from restoring a stale menu binary.
   - The menubar dropdown's `View Last Log` item opens the most recent background action's log file, so you don't need to keep a Terminal window open to see command output.
   - `sks menubar status --json` reports a `codex_sync` object with `bundle_id`, `codex_running`, and `icon_visible_expected` to show Codex-lifecycle detection state.
+  - The menu displays the installed Codex CLI version, adds an `⬆` status icon when `sks codex update-status` sees a newer release, runs the official self-updater through `Update Codex CLI Now`, and exposes `Run sks doctor --fix` as a background repair action.
+- If Codex shows `[No tool output found for custom tool call ...]`, SKS blocks reuse of that structurally ambiguous thread. Upgrade codex-lb (or explicitly run `sks codex-lb use-oauth`), inspect possible side effects, then continue the persisted mission in a fresh Codex task. SKS never rewrites session JSONL or fabricates a successful tool output.
 - Zellij optional but recommended for terminal worker panes
 
 ## License

package/crates/sks-core/Cargo.lock

@@ -76,7 +76,7 @@ dependencies = [
 
 [[package]]
 name = "sks-core"
-version = "6.1.0"
+version = "6.1.2"
 dependencies = [
  "serde_json",
 ]

package/crates/sks-core/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "sks-core"
-version = "6.1.0"
+version = "6.1.2"
 edition = "2021"
 
 [dependencies]

package/dist/bin/fast-inline.js

@@ -32,6 +32,21 @@ function doctorJsonFastInline() {
             hook_evidence_policy: 'unknown-do-not-count',
             agent_role_strategy: 'message-role'
         },
+        zellij_readiness: {
+            schema: 'sks.zellij-readiness.v1',
+            binary: 'zellij',
+            status: 'skipped',
+            min_version: '0.41.0',
+            version: null,
+            required_for: ['sks --mad', 'interactive lane UI'],
+            layout_proof: 'unavailable',
+            pane_proof: 'unavailable',
+            screen_proof: 'unavailable',
+            tmux_removed_runtime: true,
+            mad_ready: false,
+            cli_ready: false,
+            ready_for_interactive_runtime: false
+        },
         codex: { bin: null, version: null, available: null, skipped: true, reason: 'fast_readonly_json' },
         repair: {
             setup: null,
@@ -42,15 +57,9 @@ function doctorJsonFastInline() {
         warnings: ['fast_readonly_doctor_skipped_optional_deep_diagnostics']
     }, null, 2)}\n`);
 }
-function narutoHelpJsonFastInline() {
-    process.stdout.write(`${JSON.stringify({
-        schema: 'sks.naruto-command-result.v1',
-        ok: true,
-        action: 'help',
-        fast_path: true,
-        usage: 'sks naruto run "<prompt>" [--json] [--mock] [--readonly] [--clones N]',
-        commands: ['help', 'status', 'dashboard', 'workers', 'proof', 'run']
-    }, null, 2)}\n`);
+async function narutoHelpJsonFastInline() {
+    const { buildNarutoHelpResult } = await import('../core/subagents/naruto-help-contract.js');
+    process.stdout.write(`${JSON.stringify(buildNarutoHelpResult(), null, 2)}\n`);
 }
 async function hookUserPromptSubmitPerfInline() {
     const raw = await readStdinInline();

package/dist/bin/sks-dispatch.js

@@ -39,9 +39,9 @@ async function runSks(args) {
         const { hookDaemonInline } = await import('../core/daemon/sksd-hook-dispatch.js');
         await hookDaemonInline(args[1]);
     }
-    else if (args[0] === 'naruto' && (args[1] === 'help' || args.includes('--help')) && args.includes('--json')) {
+    else if (args.length === 3 && args[0] === 'naruto' && args[1] === 'help' && args[2] === '--json') {
         const { narutoHelpJsonFastInline } = await import('./fast-inline.js');
-        narutoHelpJsonFastInline();
+        await narutoHelpJsonFastInline();
     }
     else if (args[0] === 'help' || args[0] === '--help' || args[0] === '-h') {
         if (args.length > 1) {

package/dist/cli/args.js

@@ -29,6 +29,8 @@ export function positionalArgs(args = []) {
         '--project-ref',
         '--agent',
         '--agents',
+        '--clones',
+        '--max-threads',
         '--target-active-slots',
         '--work-items',
         '--minimum-work-items',

package/dist/cli/command-manifest-lite.js

@@ -20,7 +20,7 @@ export const COMMAND_MANIFEST_LITE = [
     { name: 'wizard', summary: 'Open setup wizard help', maturity: 'stable' },
     { name: 'usage', summary: 'Show focused usage topic', maturity: 'stable', readonly: true, allowedDuringActiveRoute: true, diagnostic: true },
     { name: 'quickstart', summary: 'Show quickstart flow', maturity: 'stable' },
-    { name: 'setup', summary: 'Initialize SKS state', maturity: 'stable' },
+    { name: 'setup', summary: 'Initialize SKS state', maturity: 'stable', skipMigrationGate: true },
     { name: 'bootstrap', summary: 'Initialize SKS project files', maturity: 'stable' },
     { name: 'init', summary: 'Initialize local control surface', maturity: 'stable' },
     { name: 'deps', summary: 'Check local dependencies', maturity: 'stable' },
@@ -55,7 +55,7 @@ export const COMMAND_MANIFEST_LITE = [
     { name: 'team', summary: 'Deprecated alias. New execution redirects to Naruto; legacy observe/watch remains.', maturity: 'beta', mutatesRouteState: true, deprecated: true },
     { name: 'agent', summary: 'Run native multi-session agent missions', maturity: 'beta', mutatesRouteState: true },
     { name: 'with-local-llm', summary: 'Enable or inspect local Ollama worker backend', maturity: 'beta' },
-    { name: 'naruto', summary: 'Run $Naruto shadow-clone swarm (up to 100 parallel sessions)', maturity: 'labs', mutatesRouteState: true },
+    { name: 'naruto', summary: 'Run the $Naruto Codex official subagent workflow', maturity: 'labs', mutatesRouteState: true },
     { name: 'stop-gate', summary: 'Check canonical stop-gate resolution for a route/mission', maturity: 'beta', readonly: true, skipMigrationGate: true, allowedDuringActiveRoute: true, diagnostic: true },
     { name: 'route', summary: 'Inspect or close active route state', maturity: 'beta', skipMigrationGate: true, allowedDuringActiveRoute: true, diagnostic: true },
     { name: 'loop', summary: 'Dynamic Loop Runtime: plan/run/status/proof loop graphs.', maturity: 'labs', mutatesRouteState: true },
@@ -90,7 +90,6 @@ export const COMMAND_MANIFEST_LITE = [
     { name: 'code-structure', summary: 'Scan source structure', maturity: 'labs' },
     { name: 'rust', summary: 'Inspect optional Rust accelerator status and smoke parity', maturity: 'beta' },
     { name: 'gx', summary: 'Render/validate GX cartridges', maturity: 'labs' },
-    { name: 'db', summary: 'Inspect DB safety policy', maturity: 'beta' },
     { name: 'eval', summary: 'Run eval reports', maturity: 'labs' },
     { name: 'harness', summary: 'Run harness fixtures', maturity: 'labs' },
     { name: 'wiki', summary: 'Manage TriWiki and image voxel ledgers', maturity: 'beta', skipMigrationGate: true, allowedDuringActiveRoute: true, diagnostic: true },

package/dist/cli/command-registry.js

@@ -115,7 +115,7 @@ export const COMMANDS = {
     wizard: entry('stable', 'Open setup wizard help', 'dist/core/commands/basic-cli.js', basicNoArgs('quickstartCommand')),
     usage: readOnly(entry('stable', 'Show focused usage topic', 'dist/core/commands/basic-cli.js', basicArgs('usageCommand'))),
     quickstart: entry('stable', 'Show quickstart flow', 'dist/core/commands/basic-cli.js', basicNoArgs('quickstartCommand')),
-    setup: entry('stable', 'Initialize SKS state', 'dist/core/commands/basic-cli.js', basicArgs('setupCommand')),
+    setup: skipMigrationGate(entry('stable', 'Initialize SKS state', 'dist/core/commands/basic-cli.js', basicArgs('setupCommand'))),
     bootstrap: entry('stable', 'Initialize SKS project files', 'dist/core/commands/basic-cli.js', basicArgs('bootstrapCommand')),
     init: entry('stable', 'Initialize local control surface', 'dist/core/commands/basic-cli.js', basicArgs('initCommand')),
     deps: entry('stable', 'Check local dependencies', 'dist/core/commands/basic-cli.js', subcommand(() => import(basicModule), 'depsCommand', 'dist/core/commands/basic-cli.js', 'check')),
@@ -150,7 +150,7 @@ export const COMMANDS = {
     team: routeStateMutator(entry('beta', 'Deprecated alias. New execution redirects to Naruto; legacy observe/watch remains.', 'dist/core/commands/team-command.js', argsCommand(() => import('../core/commands/team-command.js'), 'team', 'dist/core/commands/team-command.js')), ['team-gate.json', 'naruto-gate.json']),
     agent: routeStateMutator(entry('beta', 'Run native multi-session agent missions', 'dist/core/commands/agent-command.js', argsCommand(() => import('../core/commands/agent-command.js'), 'agentCommand', 'dist/core/commands/agent-command.js')), ['agent-gate.json']),
     'with-local-llm': entry('beta', 'Enable or inspect local Ollama worker backend', 'dist/core/commands/local-model-command.js', argsCommand(() => import('../core/commands/local-model-command.js'), 'localModelCommand', 'dist/core/commands/local-model-command.js')),
-    naruto: routeStateMutator(entry('labs', 'Run $Naruto shadow-clone swarm (up to 100 parallel sessions)', 'dist/core/commands/naruto-command.js', argsCommand(() => import('../core/commands/naruto-command.js'), 'narutoCommand', 'dist/core/commands/naruto-command.js')), ['naruto-gate.json', 'stop-gate.json']),
+    naruto: routeStateMutator(entry('labs', 'Run the $Naruto Codex official subagent workflow', 'dist/core/commands/naruto-command.js', argsCommand(() => import('../core/commands/naruto-command.js'), 'narutoCommand', 'dist/core/commands/naruto-command.js')), ['naruto-gate.json', 'stop-gate.json']),
     'stop-gate': readOnly(entry('beta', 'Check canonical stop-gate resolution for a route/mission', 'dist/core/commands/stop-gate-command.js', commandArgsCommand(() => import('../core/commands/stop-gate-command.js'), 'stopGateCommand', 'dist/core/commands/stop-gate-command.js'))),
     route: activeRouteDiagnostic(entry('beta', 'Inspect or close active route state', 'dist/core/commands/route-command.js', subcommand(() => import('../core/commands/route-command.js'), 'routeCommand', 'dist/core/commands/route-command.js', 'status'))),
     loop: routeStateMutator(entry('labs', 'Dynamic Loop Runtime: plan/run/status/proof loop graphs.', 'dist/core/commands/loop-command.js', subcommand(() => import('../core/commands/loop-command.js'), 'loopCommand', 'dist/core/commands/loop-command.js', 'help')), ['loop-graph-proof.json']),
@@ -185,7 +185,6 @@ export const COMMANDS = {
     'code-structure': entry('labs', 'Scan source structure', 'dist/core/commands/code-structure-command.js', subcommand(() => import('../core/commands/code-structure-command.js'), 'codeStructureCommand', 'dist/core/commands/code-structure-command.js', 'scan')),
     rust: entry('beta', 'Inspect optional Rust accelerator status and smoke parity', 'dist/commands/rust.js', directCommand(() => import('../commands/rust.js'), 'dist/commands/rust.js')),
     gx: entry('labs', 'Render/validate GX cartridges', 'dist/core/commands/gx-command.js', subcommand(() => import('../core/commands/gx-command.js'), 'gxCommand', 'dist/core/commands/gx-command.js', 'validate')),
-    db: entry('beta', 'Inspect DB safety policy', 'dist/core/commands/db-command.js', subcommand(() => import('../core/commands/db-command.js'), 'dbCommand', 'dist/core/commands/db-command.js', 'policy')),
     eval: entry('labs', 'Run eval reports', 'dist/core/commands/eval-command.js', subcommand(() => import('../core/commands/eval-command.js'), 'evalCommand', 'dist/core/commands/eval-command.js', 'run')),
     harness: entry('labs', 'Run harness fixtures', 'dist/core/commands/harness-command.js', subcommand(() => import('../core/commands/harness-command.js'), 'harnessCommand', 'dist/core/commands/harness-command.js', 'fixture')),
     wiki: activeRouteDiagnostic(entry('beta', 'Manage TriWiki and image voxel ledgers', 'dist/commands/wiki.js', directCommand(() => import('../commands/wiki.js'), 'dist/commands/wiki.js'))),
@@ -196,7 +195,7 @@ export const COMMANDS = {
     'all-features': entry('beta', 'Run all-features selftest', 'dist/commands/all-features.js', directCommand(() => import('../commands/all-features.js'), 'dist/commands/all-features.js')),
     perf: entry('beta', 'Run performance checks', 'dist/commands/perf.js', directCommand(() => import('../commands/perf.js'), 'dist/commands/perf.js')),
     bench: entry('beta', 'Run core trust-kernel benchmark budgets', 'dist/core/commands/bench-command.js', argsCommand(() => import('../core/commands/bench-command.js'), 'benchCommand', 'dist/core/commands/bench-command.js')),
-    'mcp-server': entry('beta', 'Run a stdio MCP server exposing SKS commands as tools for any MCP-capable agent host', 'dist/core/commands/mcp-server-command.js', argsCommand(() => import('../core/commands/mcp-server-command.js'), 'mcpServerCommand', 'dist/core/commands/mcp-server-command.js'), {
+    'mcp-server': entry('beta', 'Run a stdio MCP server exposing SKS commands as tools for MCP-capable agent hosts', 'dist/core/commands/mcp-server-command.js', argsCommand(() => import('../core/commands/mcp-server-command.js'), 'mcpServerCommand', 'dist/core/commands/mcp-server-command.js'), {
         skipMigrationGate: true,
         allowedDuringActiveRoute: true,
         activeRoutePolicy: 'always'

package/dist/cli/help-fast.js

@@ -8,7 +8,7 @@ SNEAKOSCOPE CODEX v${PACKAGE_VERSION}
 
   $Plan "task"              plan only; writes .sneakoscope/plans, no code edits
   $Work                     execute the latest plan with evidence gates
-  $Swarm "task"             dynamic Naruto swarm with machine verification
+  $Swarm "task"             Naruto alias for the Codex official subagent workflow
 
 Local surfaces