sneakoscope 0.6.96 → 0.6.100

package/README.md

@@ -2,7 +2,7 @@
 
 ![](https://github.com/mandarange/Sneakoscope-Codex/raw/dev/docs/assets/sneakoscope-codex-logo.png)
 
-Sneakoscope Codex (`sks`, displayed as `ㅅㅋㅅ`) is a Codex CLI/App harness for repeatable agent workflows. It adds terminal commands, Codex App `$` prompt commands, warp-native CLI workspaces, Team/QA/Research routes, a maximum-speed Computer Use lane, a fast Goal bridge for native `/goal` persistence, Context7 evidence checks, DB safety, TriWiki context tracking, Honest Mode, and release-readiness gates.
+Sneakoscope Codex (`sks`, displayed as `ㅅㅋㅅ`) is a Codex CLI/App harness for repeatable agent workflows. It adds terminal commands, Codex App `$` prompt commands, warp-native CLI workspaces, Team/QA/Research routes, a maximum-speed Computer Use lane, a fast Goal bridge for native `/goal` persistence, Context7 evidence checks, DB safety, TriWiki context tracking, lightweight skill dreaming, Honest Mode, and release-readiness gates.
 
 ## Quick Start
 
@@ -45,7 +45,8 @@ sks selftest --mock
 | --- | --- |
 | CLI runtime | `sks warp open` and `sks --mad` explicitly launch Codex CLI with Warp; bare `sks` only prints help/readiness surfaces. |
 | Codex App commands | Installs generated skills so `$Team`, `$From-Chat-IMG`, `$DFix`, `$QA-LOOP`, `$Goal`, `$DB`, `$Wiki`, `$Help`, and related routes are visible in prompt workflows. |
-| Team orchestration | Runs substantial work through ambiguity handling, scouts, TriWiki refresh, debate, runtime task graphs, worker inboxes, implementation, review, cleanup, reflection, and Honest Mode. |
+| Team orchestration | Runs substantial work through ambiguity handling, scouts, TriWiki refresh, debate, runtime task graphs, worker inboxes, implementation, review, cleanup, reflection, and Honest Mode; narrow work should use Proof Field evidence to skip unrelated pipeline work instead of expanding Team. |
+| Skill dreaming | Records cheap generated-skill usage counters in JSON and only periodically scans `.agents/skills` for keep, merge, prune, and improvement candidates. Reports are recommendation-only and never delete skills automatically. |
 | From-Chat-IMG | Turns chat screenshots plus original attachments into source-bound work orders, then requires scoped QA evidence before completion. |
 | QA loop | Dogfoods UI/API behavior with safety gates, Codex Computer Use-only UI evidence, safe fixes, and rechecks. |
 | Computer Use fast lane | Uses `$Computer-Use` / `$CU` for UI/browser/visual work that needs maximum speed: skip Team debate and upfront TriWiki loops, use Codex Computer Use directly, then refresh/validate TriWiki and run Honest Mode at final closeout. |
@@ -220,9 +221,15 @@ sks validate-artifacts latest --json
 sks perf run --json
 sks perf workflow --json --intent "small CLI change" --changed src/cli/main.mjs,src/core/routes.mjs
 sks proof-field scan --json --intent "small CLI change"
+sks skill-dream status
+sks skill-dream run --json
 sks code-structure scan --json
 ```
 
+`sks proof-field scan` is SKS's lightweight outcome rubric: it maps the goal to proof cones, records unrelated work that can be skipped with evidence, reports a simplicity score, and names escalation triggers for when the route must return to the full Team/Honest proof path. When `execution_lane.lane` is `proof_field_fast_lane`, SKS can keep the parent-owned minimal patch plus listed verification and skip Team debate, fresh executor teams, broad route rework, and unrelated checks. Database, security, visual-forensic, unknown, broad, failed, or unsupported-claim signals fail closed to the normal Team/Honest path.
+
+`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 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.

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "sneakoscope",
   "displayName": "ㅅㅋㅅ",
-  "version": "0.6.96",
+  "version": "0.6.100",
   "description": "Sneakoscope Codex: database-safe Codex CLI/App harness with Team, Goal, AutoResearch, TriWiki, and Honest Mode.",
   "type": "module",
   "homepage": "https://github.com/mandarange/Sneakoscope-Codex#readme",

package/src/cli/main.mjs

@@ -25,7 +25,7 @@ import { defaultEvaluationScenario, runEvaluationBenchmark } from '../core/evalu
 import { buildResearchPrompt, evaluateResearchGate, writeMockResearchResult, writeResearchPlan } from '../core/research.mjs';
 import { contextCapsule } from '../core/triwiki-attention.mjs';
 import { rgbaKey, rgbaToWikiCoord, validateWikiCoordinateIndex } from '../core/wiki-coordinate.mjs';
-import { ALLOWED_REASONING_EFFORTS, CODEX_COMPUTER_USE_EVIDENCE_SOURCE, CODEX_COMPUTER_USE_ONLY_POLICY, COMMAND_CATALOG, DOLLAR_COMMAND_ALIASES, DOLLAR_COMMANDS, DOLLAR_SKILL_NAMES, FROM_CHAT_IMG_CHECKLIST_ARTIFACT, FROM_CHAT_IMG_COVERAGE_ARTIFACT, FROM_CHAT_IMG_QA_LOOP_ARTIFACT, FROM_CHAT_IMG_SOURCE_INVENTORY_ARTIFACT, FROM_CHAT_IMG_TEMP_TRIWIKI_ARTIFACT, FROM_CHAT_IMG_TEMP_TRIWIKI_SESSIONS, FROM_CHAT_IMG_VISUAL_MAP_ARTIFACT, FROM_CHAT_IMG_WORK_ORDER_ARTIFACT, RECOMMENDED_SKILLS, ROUTES, USAGE_TOPICS, context7ConfigToml, hasContext7ConfigText, hasFromChatImgSignal, looksLikeAnswerOnlyRequest, noUnrequestedFallbackCodePolicyText, reflectionRequiredForRoute, reasoningInstruction, routePrompt, routeReasoning, routeRequiresSubagents, stackCurrentDocsPolicy, triwikiContextTracking } from '../core/routes.mjs';
+import { ALLOWED_REASONING_EFFORTS, CODEX_COMPUTER_USE_EVIDENCE_SOURCE, CODEX_COMPUTER_USE_ONLY_POLICY, COMMAND_CATALOG, DOLLAR_COMMAND_ALIASES, DOLLAR_COMMANDS, DOLLAR_SKILL_NAMES, FROM_CHAT_IMG_CHECKLIST_ARTIFACT, FROM_CHAT_IMG_COVERAGE_ARTIFACT, FROM_CHAT_IMG_QA_LOOP_ARTIFACT, FROM_CHAT_IMG_SOURCE_INVENTORY_ARTIFACT, FROM_CHAT_IMG_TEMP_TRIWIKI_ARTIFACT, FROM_CHAT_IMG_TEMP_TRIWIKI_SESSIONS, FROM_CHAT_IMG_VISUAL_MAP_ARTIFACT, FROM_CHAT_IMG_WORK_ORDER_ARTIFACT, RECOMMENDED_SKILLS, ROUTES, USAGE_TOPICS, context7ConfigToml, hasContext7ConfigText, hasFromChatImgSignal, looksLikeAnswerOnlyRequest, noUnrequestedFallbackCodePolicyText, reflectionRequiredForRoute, reasoningInstruction, routePrompt, routeReasoning, routeRequiresSubagents, speedLanePolicyText, stackCurrentDocsPolicy, triwikiContextTracking } from '../core/routes.mjs';
 import { context7Evidence, evaluateStop, recordContext7Evidence, recordSubagentEvidence } from '../core/pipeline.mjs';
 import { TEAM_DECOMPOSITION_ARTIFACT, TEAM_GRAPH_ARTIFACT, TEAM_INBOX_DIR, TEAM_RUNTIME_TASKS_ARTIFACT, validateTeamRuntimeArtifacts, writeTeamRuntimeArtifacts } from '../core/team-dag.mjs';
 import { appendTeamEvent, initTeamLive, parseTeamSpecText, readTeamDashboard, readTeamLive, readTeamTranscriptTail, renderTeamAgentLane } from '../core/team-live.mjs';
@@ -34,7 +34,7 @@ import { selectEffort, writeEffortDecision } from '../core/effort-orchestrator.m
 import { createWorkOrderLedger } from '../core/work-order-ledger.mjs';
 import { buildFromChatImgVisualMap } from '../core/from-chat-img-forensics.mjs';
 import { classifyDogfoodFinding, createDogfoodReport, writeDogfoodReport } from '../core/dogfood-loop.mjs';
-import { createSkillCandidate, decideSkillInjection, writeSkillCandidate, writeSkillForgeReport, writeSkillInjectionDecision } from '../core/skill-forge.mjs';
+import { createSkillCandidate, decideSkillInjection, skillDreamFixture, writeSkillCandidate, writeSkillForgeReport, writeSkillInjectionDecision } from '../core/skill-forge.mjs';
 import { classifyToolError, harnessGrowthReport } from '../core/evaluation.mjs';
 import { runWorkflowPerfBench, validateWorkflowPerfReport } from '../core/perf-bench.mjs';
 import { proofFieldFixture, validateProofFieldReport } from '../core/proof-field.mjs';
@@ -45,7 +45,7 @@ import { GOAL_WORKFLOW_ARTIFACT } from '../core/goal-workflow.mjs';
 import { CODEX_APP_DOCS_URL, codexAppIntegrationStatus, formatCodexAppStatus } from '../core/codex-app.mjs';
 import { buildWarpLaunchConfigYaml, buildWarpLaunchPlan, buildWarpOpenArgs, isWarpShellSession, runWarpLaunchConfigSyntaxCheck, warpOpenLaunchDecision, warpReadiness, warpStatusKind, defaultWarpWorkspaceName, formatWarpBanner, launchWarpTeamView, launchWarpUi, platformWarpInstallHint, runWarpStatus, sanitizeWarpWorkspaceName, teamLaneStyle, writeWarpLaunchConfig } from '../core/warp-ui.mjs';
 import { autoReviewProfileName, autoReviewStatus, autoReviewSummary, enableAutoReview, disableAutoReview, enableMadHighProfile, madHighProfileName } from '../core/auto-review.mjs';
-import { buildTeamPlan, codeStructureCommand, dbCommand, defaultBeta, defaultVGraph, evalCommand, gcCommand, goalCommand, gxCommand, harnessCommand, hproofCommand, memoryCommand, migrateWikiContextPack, parseTeamCreateArgs, perfCommand, profileCommand, projectWikiClaims, proofFieldCommand, qaLoopCommand, quickstartCommand, researchCommand, statsCommand, team, teamWorkflowMarkdown, validateArtifactsCommand, wikiCommand, wikiVoxelRowCount, writeWikiContextPack } from './maintenance-commands.mjs';
+import { buildTeamPlan, codeStructureCommand, dbCommand, defaultBeta, defaultVGraph, evalCommand, gcCommand, goalCommand, gxCommand, harnessCommand, hproofCommand, memoryCommand, migrateWikiContextPack, parseTeamCreateArgs, perfCommand, profileCommand, projectWikiClaims, proofFieldCommand, qaLoopCommand, quickstartCommand, researchCommand, skillDreamCommand, statsCommand, team, teamWorkflowMarkdown, validateArtifactsCommand, wikiCommand, wikiVoxelRowCount, writeWikiContextPack } from './maintenance-commands.mjs';
 
 const flag = (args, name) => args.includes(name);
 const promptOf = (args) => args.filter((x) => !String(x).startsWith('--')).join(' ').trim();
@@ -104,6 +104,7 @@ export async function main(args) {
   if (cmd === 'validate-artifacts') return validateArtifactsCommand(tail);
   if (cmd === 'perf') return perfCommand(sub, rest);
   if (cmd === 'proof-field') return proofFieldCommand(sub, rest);
+  if (cmd === 'skill-dream') return skillDreamCommand(sub, rest);
   if (cmd === 'code-structure') return codeStructureCommand(sub, rest);
   if (cmd === 'memory') return memoryCommand(sub, rest);
   if (cmd === 'gx') return gxCommand(sub, rest);
@@ -182,6 +183,7 @@ Usage:
   sks eval compare --baseline old.json --candidate new.json [--json]
   sks perf run|workflow [--json] [--intent "task"] [--changed file1,file2]
   sks proof-field scan [--json] [--intent "task"]
+  sks skill-dream status|run|record [--json]
   sks harness fixture [--json]
   sks code-structure scan [--json]
   sks wiki coords --rgba 12,34,56,255
@@ -1426,6 +1428,7 @@ function usage(args = []) {
     dollar: ['Dollar Commands', '', formatDollarCommandsCompact('  '), '', 'Terminal: sks dollar-commands [--json]'],
     wiki: ['TriWiki', '', '  sks wiki pack', '  sks wiki refresh [--prune]', '  sks wiki sweep latest --json', '  sks wiki validate .sneakoscope/wiki/context-pack.json', '  sks wiki prune --dry-run --json', '', 'Packs include attention.use_first and attention.hydrate_first for compact recall plus source hydration. Sweep records intentional forgetting and promotion candidates.'],
     harness: ['Harness Growth', '', '  sks harness fixture --json', '  sks harness review --json', '', 'Runs deterministic fixtures for deliberate forgetting, skill cards, harness experiments, tool error taxonomy, permission profiles, MultiAgentV2, and Warp cockpit views.'],
+    'skill-dream': ['Skill Dreaming', '', '  sks skill-dream status', '  sks skill-dream run --json', '  sks skill-dream record --route team --skills team,prompt-pipeline', '', 'Records cheap JSON usage counters in .sneakoscope/skills/dream-state.json and periodically writes recommendation-only keep/merge/prune/improve reports. It never deletes or merges skills automatically.'],
     'code-structure': ['Code Structure', '', '  sks code-structure scan', '  sks code-structure scan --json', '', 'Flags handwritten source files above 1000/2000/3000-line thresholds and records split-review exceptions.'],
     gx: ['GX', '', '  sks gx init architecture-atlas', '  sks gx render architecture-atlas --format all', '  sks gx validate architecture-atlas']
   };
@@ -2748,10 +2751,10 @@ async function selftest() {
   await writeJsonAtomic(path.join(fromChatCoverageDir, 'team-gate.json'), { ...passedTeamGate, from_chat_img_required: true, from_chat_img_request_coverage: true });
   const coveredFromChatStop = await evaluateStop(fromChatCoverageTmp, fromChatCoverageState, { last_assistant_message: 'SKS Honest Mode verification evidence gap' }, { noQuestion: false });
   if (coveredFromChatStop?.decision !== 'block' || String(coveredFromChatStop.reason || '').includes('from-chat-img') || !String(coveredFromChatStop.reason || '').includes(TEAM_SESSION_CLEANUP_ARTIFACT)) throw new Error('selftest failed: valid From-Chat-IMG artifacts did not hand off to session cleanup gate');
-  await recordContext7Evidence(routeGateTmp, gateState, { tool_name: 'resolve-library-id', library: 'react' });
+  await recordContext7Evidence(routeGateTmp, gateState, { tool_name: 'mcp__context7__resolve_library_id', library: 'react' });
   const resolveOnlyStop = await evaluateStop(routeGateTmp, gateState, { last_assistant_message: 'SKS Honest Mode verification evidence gap' }, { noQuestion: false });
   if (resolveOnlyStop?.decision !== 'block') throw new Error('selftest failed: resolve-only Context7 evidence unblocked route');
-  await recordContext7Evidence(routeGateTmp, gateState, { tool_name: 'query-docs', library_id: '/facebook/react' });
+  await recordContext7Evidence(routeGateTmp, gateState, { tool_name: 'mcp__context7__query_docs', library_id: '/facebook/react' });
   const missingCleanupStop = await evaluateStop(routeGateTmp, gateState, { last_assistant_message: 'SKS Honest Mode verification evidence gap' }, { noQuestion: false });
   if (missingCleanupStop?.decision !== 'block' || !String(missingCleanupStop.reason || '').includes(TEAM_SESSION_CLEANUP_ARTIFACT)) throw new Error('selftest failed: Team route did not block missing session cleanup gate');
   await writeJsonAtomic(path.join(gateDir, TEAM_SESSION_CLEANUP_ARTIFACT), passedTeamSessionCleanup);
@@ -2863,6 +2866,8 @@ async function selftest() {
   if (!validateSkillCandidate(skillCandidate).ok) throw new Error('selftest failed: active skill candidate rejected');
   const injection = decideSkillInjection({ route: 'from-chat-img', task_signature: 'reference images', skills: [skillCandidate, { ...skillCandidate, id: 'deprecated', status: 'deprecated' }] });
   if (!validateSkillInjectionDecision(injection).ok || injection.injected.length !== 1) throw new Error('selftest failed: skill injection did not respect active/top-K filtering');
+  const skillDream = await skillDreamFixture(path.join(tmp, 'skill-dream-fixture'));
+  if (!skillDream.passed) throw new Error('selftest failed: skill dreaming did not keep used skills, recommend unused generated skills, and preserve custom skills');
   const promptContext = buildPromptContext({ stable: ['stable'], policies: ['policy'], dynamic: ['dynamic'] });
   if (promptContext.blocks[0]?.cache_region !== 'stable_prefix' || promptContext.blocks.at(-1)?.cache_region !== 'dynamic_suffix') throw new Error('selftest failed: prompt context did not place dynamic context last');
   const repeatedMistake = await recordMistake(teamDir, { route: 'from-chat-img', gate: 'visual-map', reason: 'unmatched-reference' });
@@ -2961,13 +2966,14 @@ async function selftest() {
   if (!harnessReport.forgetting.fixture.passed || !harnessReport.warp.views.includes('Harness Experiments View') || !harnessReport.reliability.tool_error_taxonomy.includes('Unknown')) throw new Error('selftest failed: harness growth fixture incomplete');
   const proofField = await proofFieldFixture();
   if (!proofField.validation.ok || !validateProofFieldReport(proofField.report).ok) throw new Error('selftest failed: proof field report invalid');
-  if (!proofField.checks.route_cone_selected || !proofField.checks.cli_cone_selected || !proofField.checks.catastrophic_guard_present || !proofField.checks.negative_release_work_recorded) throw new Error('selftest failed: proof field fixture checks incomplete');
+  if (!proofField.checks.route_cone_selected || !proofField.checks.cli_cone_selected || !proofField.checks.catastrophic_guard_present || !proofField.checks.negative_release_work_recorded || !proofField.checks.outcome_rubric_present || !proofField.checks.simplicity_score_usable || !proofField.checks.execution_fast_lane_selected) throw new Error('selftest failed: proof field fixture checks incomplete');
+  if (!speedLanePolicyText().includes('proof_field_fast_lane') || !proofField.report.execution_lane?.skip_when_fast?.includes('planning_debate')) throw new Error('selftest failed: Proof Field speed lane policy missing');
   const workflowPerf = await runWorkflowPerfBench(tmp, {
     iterations: 2,
     intent: 'small CLI help surface update',
     changedFiles: ['src/cli/maintenance-commands.mjs', 'src/core/routes.mjs']
   });
-  if (!validateWorkflowPerfReport(workflowPerf).ok || workflowPerf.metrics.decision_mode !== 'fast_lane' || !workflowPerf.metrics.fast_lane_eligible) throw new Error('selftest failed: workflow perf proof field did not produce a valid fast lane report');
+  if (!validateWorkflowPerfReport(workflowPerf).ok || workflowPerf.metrics.decision_mode !== 'fast_lane' || workflowPerf.metrics.execution_lane !== 'proof_field_fast_lane' || !workflowPerf.metrics.fast_lane_eligible || !workflowPerf.metrics.fast_lane_allowed || Number(workflowPerf.metrics.simplicity_score) < 0.75 || Number(workflowPerf.metrics.outcome_criteria_passed) < 3) throw new Error('selftest failed: workflow perf proof field did not produce a valid outcome-scored fast lane report');
   if (classifyToolError({ message: 'operation timed out' }) !== 'Timeout' || classifyToolError({ message: 'unclassified weirdness' }) !== 'Unknown') throw new Error('selftest failed: tool error taxonomy classification');
   const coord = rgbaToWikiCoord({ r: 12, g: 34, b: 56, a: 255 });
   if (coord.schema !== 'sks.wiki-coordinate.v1' || coord.xyzw.length !== 4) throw new Error('selftest failed: RGBA wiki coordinate conversion');
@@ -3001,6 +3007,33 @@ async function selftest() {
   if (!wikiPack.claims?.some((claim) => claim.id === 'selftest-memory-priority')) throw new Error('selftest failed: memory required_weight claim was not selected in TriWiki pack');
   if (!wikiPack.claims?.some((claim) => claim.id === 'wiki-stack-current-docs-policy')) throw new Error('selftest failed: stack current-docs policy claim missing from TriWiki pack');
   if (!wikiPack.claims?.some((claim) => claim.id === 'wiki-stack-current-docs-vercel-duration')) throw new Error('selftest failed: Vercel duration current-docs claim missing from TriWiki pack');
+  const cacheHitPack = contextCapsule({
+    mission: { id: 'cache-hit-selftest', coord: { rgba: { r: 24, g: 24, b: 24, a: 255 } } },
+    role: 'worker',
+    claims: [
+      { id: 'cache-hit-core-1', text: 'Selected high-similarity claim must keep an anchor for attention cache hits.', authority: 'code', risk: 'low', status: 'supported', freshness: 'fresh', trust_score: 0.82, coord: { rgba: { r: 24, g: 24, b: 24, a: 255 } } },
+      { id: 'cache-hit-core-2', text: 'Second selected high-similarity claim must keep an anchor for attention cache hits.', authority: 'code', risk: 'low', status: 'supported', freshness: 'fresh', trust_score: 0.82, coord: { rgba: { r: 24, g: 24, b: 25, a: 255 } } },
+      ...Array.from({ length: 8 }, (_, i) => ({ id: `cache-hit-distractor-${i}`, text: `High-priority distractor ${i}`, authority: 'code', risk: 'critical', status: 'supported', freshness: 'fresh', trust_score: 0.99, coord: { rgba: { r: 180 + i, g: 180, b: 180, a: 255 } } }))
+    ],
+    q4: { mode: 'cache-hit-selftest' },
+    q3: ['triwiki', 'cache-hit'],
+    budget: { maxClaims: 2, maxWikiAnchors: 2, maxAttentionUse: 2 }
+  });
+  const cacheHitUseIds = new Set(cacheHitPack.attention?.use_first?.map((row) => row[0]) || []);
+  if (!cacheHitUseIds.has('cache-hit-core-1') || !cacheHitUseIds.has('cache-hit-core-2')) throw new Error('selftest failed: selected TriWiki claims were not pinned as attention cache-hit anchors');
+  const primingPack = contextCapsule({
+    mission: { id: 'positive-recall-selftest', coord: { rgba: { r: 64, g: 96, b: 128, a: 255 } } },
+    role: 'worker',
+    claims: [
+      { id: 'positive-recall-guard', text: 'Do not imagine elephant during TriWiki recall.', authority: 'code', risk: 'high', status: 'supported', freshness: 'fresh', required_weight: 1.4, trust_score: 0.95, coord: { rgba: { r: 64, g: 96, b: 128, a: 255 } } }
+    ],
+    q4: { mode: 'positive-recall-selftest' },
+    q3: ['triwiki', 'positive-recall'],
+    budget: { maxClaims: 1, maxWikiAnchors: 1, maxAttentionUse: 1, maxAttentionHydrate: 1 }
+  });
+  const primingClaim = primingPack.claims?.find((claim) => claim.id === 'positive-recall-guard');
+  if (!primingClaim || /elephant|do\s+not/i.test(primingClaim.text || '') || primingClaim.text_policy !== 'positive_recall_negation_suppressed') throw new Error('selftest failed: TriWiki compact recall did not suppress negative priming text');
+  if (!primingPack.attention?.hydrate_first?.some((row) => row[0] === 'positive-recall-guard' && String(row[1]).includes('negative_priming'))) throw new Error('selftest failed: negative priming claim was not source-hydration gated');
   const dryRunPack = await writeWikiContextPack(tmp, ['--max-anchors', '4'], { dryRun: true });
   if (wikiVoxelRowCount(dryRunPack.pack.wiki) !== 4) throw new Error('selftest failed: dry-run wiki pack did not build voxel rows');
   if (await exists(dryRunPack.file)) throw new Error('selftest failed: wiki refresh dry-run wrote context pack');

package/src/cli/maintenance-commands.mjs

@@ -15,7 +15,7 @@ import { renderCartridge, validateCartridge, driftCartridge, snapshotCartridge }
 import { DEFAULT_EVAL_THRESHOLDS, compareEvaluationReports, runEvaluationBenchmark } from '../core/evaluation.mjs';
 import { contextCapsule } from '../core/triwiki-attention.mjs';
 import { rgbaKey, rgbaToWikiCoord, validateWikiCoordinateIndex } from '../core/wiki-coordinate.mjs';
-import { ALLOWED_REASONING_EFFORTS, CODEX_COMPUTER_USE_ONLY_POLICY, FROM_CHAT_IMG_CHECKLIST_ARTIFACT, FROM_CHAT_IMG_COVERAGE_ARTIFACT, FROM_CHAT_IMG_QA_LOOP_ARTIFACT, FROM_CHAT_IMG_SOURCE_INVENTORY_ARTIFACT, FROM_CHAT_IMG_TEMP_TRIWIKI_ARTIFACT, FROM_CHAT_IMG_TEMP_TRIWIKI_SESSIONS, FROM_CHAT_IMG_VISUAL_MAP_ARTIFACT, FROM_CHAT_IMG_WORK_ORDER_ARTIFACT, ROUTES, hasFromChatImgSignal, routePrompt, stackCurrentDocsPolicy, triwikiContextTracking } from '../core/routes.mjs';
+import { ALLOWED_REASONING_EFFORTS, CODEX_COMPUTER_USE_ONLY_POLICY, DOLLAR_SKILL_NAMES, FROM_CHAT_IMG_CHECKLIST_ARTIFACT, FROM_CHAT_IMG_COVERAGE_ARTIFACT, FROM_CHAT_IMG_QA_LOOP_ARTIFACT, FROM_CHAT_IMG_SOURCE_INVENTORY_ARTIFACT, FROM_CHAT_IMG_TEMP_TRIWIKI_ARTIFACT, FROM_CHAT_IMG_TEMP_TRIWIKI_SESSIONS, FROM_CHAT_IMG_VISUAL_MAP_ARTIFACT, FROM_CHAT_IMG_WORK_ORDER_ARTIFACT, RECOMMENDED_SKILLS, ROUTES, hasFromChatImgSignal, routePrompt, stackCurrentDocsPolicy, triwikiContextTracking } from '../core/routes.mjs';
 import { TEAM_DECOMPOSITION_ARTIFACT, TEAM_GRAPH_ARTIFACT, TEAM_INBOX_DIR, TEAM_RUNTIME_TASKS_ARTIFACT, teamRuntimePlanMetadata, teamRuntimeRequiredArtifacts, writeTeamRuntimeArtifacts } from '../core/team-dag.mjs';
 import { appendTeamEvent, formatRoleCounts, initTeamLive, normalizeTeamSpec, parseTeamSpecArgs, readTeamControl, readTeamDashboard, readTeamLive, readTeamTranscriptTail, renderTeamAgentLane, renderTeamCleanupSummary, renderTeamWatch, requestTeamSessionCleanup, teamCleanupRequested } from '../core/team-live.mjs';
 import { ARTIFACT_FILES, writeValidationReport } from '../core/artifact-schemas.mjs';
@@ -29,7 +29,7 @@ import { GOAL_BRIDGE_ARTIFACT, GOAL_WORKFLOW_ARTIFACT, updateGoalWorkflow, write
 import { scanCodeStructure, writeCodeStructureReport } from '../core/code-structure.mjs';
 import { writeMemorySweepReport } from '../core/memory-governor.mjs';
 import { cleanupWarpTeamView, launchWarpTeamView } from '../core/warp-ui.mjs';
-import { writeSkillForgeReport } from '../core/skill-forge.mjs';
+import { loadSkillDreamState, recordSkillDreamEvent, runSkillDream, writeSkillForgeReport } from '../core/skill-forge.mjs';
 import { writeMistakeMemoryReport } from '../core/mistake-memory.mjs';
 import { checkDbOperation, checkSqlFile, classifyCommand, classifySql, loadDbSafetyPolicy, safeSupabaseMcpConfig, scanDbSafety } from '../core/db-safety.mjs';
 import { harnessGrowthReport, writeHarnessGrowthReport } from '../core/evaluation.mjs';
@@ -573,6 +573,58 @@ export async function proofFieldCommand(sub, args = []) {
   console.log(`Report: ${path.relative(root, report.report_path)}`);
 }
 
+export async function skillDreamCommand(sub, args = []) {
+  const action = sub && !String(sub).startsWith('--') ? sub : 'status';
+  const actionArgs = action === sub ? args : [sub, ...args].filter(Boolean);
+  if (!['status', 'run', 'record', 'help', '--help'].includes(action)) {
+    console.error('Usage: sks skill-dream status|run|record [--json]');
+    process.exitCode = 1;
+    return;
+  }
+  if (action === 'help' || action === '--help') {
+    console.log('Usage: sks skill-dream status|run|record [--json]');
+    console.log('Records cheap generated-skill usage counters and periodically reports keep, merge, prune, and improvement candidates. Reports never delete skills automatically.');
+    return;
+  }
+  const root = await sksRoot();
+  if (action === 'record') {
+    const skills = readFlagValue(actionArgs, '--skills', '').split(',').map((x) => x.trim()).filter(Boolean);
+    const result = await recordSkillDreamEvent(root, {
+      route: readFlagValue(actionArgs, '--route', positionalArgs(actionArgs).join(' ') || 'manual'),
+      command: readFlagValue(actionArgs, '--command', null),
+      required_skills: skills,
+      prompt_signature: readFlagValue(actionArgs, '--prompt-signature', null)
+    }, { known_skill_names: knownGeneratedSkillNames() });
+    if (flag(actionArgs, '--json')) return console.log(JSON.stringify(result, null, 2));
+    console.log('SKS Skill Dream Record');
+    console.log(`Events since last run: ${result.state.counters.events_since_last_run}`);
+    console.log(`Due: ${result.due.due ? 'yes' : 'no'} (${result.due.reason_codes.join(', ')})`);
+    if (result.report) console.log(`Report: ${path.relative(root, result.report.report_path)}`);
+    return;
+  }
+  if (action === 'run') {
+    const report = await runSkillDream(root, { force: true, known_skill_names: knownGeneratedSkillNames() });
+    if (flag(actionArgs, '--json')) return console.log(JSON.stringify(report, null, 2));
+    console.log('SKS Skill Dream');
+    console.log(`Inventory: ${report.inventory.total} skills (${report.inventory.generated} generated, ${report.inventory.unknown_or_user} unknown/user)`);
+    console.log(`Keep: ${report.keep.length}`);
+    console.log(`Merge candidates: ${report.merge_candidates.length}`);
+    console.log(`Prune candidates: ${report.prune_candidates.length}`);
+    console.log(`Improve candidates: ${report.improve_candidates.length}`);
+    console.log(`Apply mode: ${report.apply_mode}; no auto delete: ${report.no_auto_delete ? 'yes' : 'no'}`);
+    console.log(`Report: ${path.relative(root, report.report_path)}`);
+    return;
+  }
+  const state = await loadSkillDreamState(root);
+  if (flag(actionArgs, '--json')) return console.log(JSON.stringify(state, null, 2));
+  console.log('SKS Skill Dream Status');
+  console.log(`State: .sneakoscope/skills/dream-state.json`);
+  console.log(`Events since last run: ${state.counters.events_since_last_run}/${state.policy.min_events_between_runs}`);
+  console.log(`Cooldown: ${state.policy.min_interval_hours}h`);
+  console.log(`Last run: ${state.last_run_at || 'never'}`);
+  console.log(`Next: ${state.next_run?.due ? 'due' : (state.next_run?.reason_codes || ['not due']).join(', ')}`);
+}
+
 export async function harnessCommand(sub, args = []) {
   const action = sub || 'fixture';
   if (!['fixture', 'review'].includes(action)) {
@@ -901,6 +953,19 @@ export async function projectWikiClaims(root) {
     required_weight: 1.45,
     trust_score: 0.95
   });
+  out.push({
+    id: 'wiki-positive-recall-priming-guard',
+    text: 'TriWiki compact recall should phrase selected guidance as the positive target behavior; anti-goal or failure-pattern wording should stay hydratable by source/hash instead of being pasted into the active recall text.',
+    authority: 'code',
+    risk: 'high',
+    status: 'supported',
+    freshness: 'fresh',
+    source: 'src/core/triwiki-attention.mjs',
+    file: 'src/core/triwiki-attention.mjs',
+    evidence_count: 3,
+    required_weight: 1.42,
+    trust_score: 0.94
+  });
   out.push(...(await memoryWikiClaims(root)));
   out.push(...(await userRequestSignalWikiClaims(root)));
   out.push(...(await teamAnalysisWikiClaims(root)));
@@ -1236,7 +1301,7 @@ export async function statsCommand(args) {
 
 function positionalArgs(args = []) {
   const out = [];
-  const valueFlags = new Set(['--format', '--iterations', '--out', '--baseline', '--candidate', '--install-scope', '--max-cycles', '--depth', '--scope', '--transport', '--query', '--topic', '--tokens', '--timeout-ms', '--sql', '--command', '--project-ref', '--agent', '--phase', '--message', '--role', '--max-anchors', '--lines', '--intent', '--changed']);
+  const valueFlags = new Set(['--format', '--iterations', '--out', '--baseline', '--candidate', '--install-scope', '--max-cycles', '--depth', '--scope', '--transport', '--query', '--topic', '--tokens', '--timeout-ms', '--sql', '--command', '--project-ref', '--agent', '--phase', '--message', '--role', '--max-anchors', '--lines', '--intent', '--changed', '--route', '--skills', '--prompt-signature']);
   for (let i = 0; i < args.length; i++) {
     const arg = String(args[i]);
     if (valueFlags.has(arg)) {
@@ -1253,6 +1318,10 @@ function readFlagValue(args, name, fallback) {
   return i >= 0 && args[i + 1] ? args[i + 1] : fallback;
 }
 
+function knownGeneratedSkillNames() {
+  return Array.from(new Set([...DOLLAR_SKILL_NAMES, ...RECOMMENDED_SKILLS]));
+}
+
 function cartridgeName(args, fallback = 'architecture-atlas') {
   const raw = positionalArgs(args)[0] || fallback;
   return String(raw).trim().replace(/[\\/]+/g, '-').replace(/[^A-Za-z0-9_.-]+/g, '-').replace(/^-+|-+$/g, '') || fallback;

package/src/core/fsx.mjs

@@ -5,7 +5,7 @@ import os from 'node:os';
 import crypto from 'node:crypto';
 import { spawn } from 'node:child_process';
 
-export const PACKAGE_VERSION = '0.6.96';
+export const PACKAGE_VERSION = '0.6.100';
 export const DEFAULT_PROCESS_TAIL_BYTES = 256 * 1024;
 export const DEFAULT_PROCESS_TIMEOUT_MS = 30 * 60 * 1000;
 

package/src/core/init.mjs

@@ -6,7 +6,8 @@ import { DEFAULT_DB_SAFETY_POLICY } from './db-safety.mjs';
 import { isHarnessSourceProject, writeHarnessGuardPolicy } from './harness-guard.mjs';
 import { repairSksGeneratedArtifacts } from './harness-conflicts.mjs';
 import { installVersionGitHook } from './version-manager.mjs';
-import { CODEX_COMPUTER_USE_ONLY_POLICY, 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, RECOMMENDED_MCP_SERVERS, RECOMMENDED_SKILLS, chatCaptureIntakeText, context7ConfigToml, stackCurrentDocsPolicyText, triwikiContextTracking, triwikiContextTrackingText, triwikiStagePolicyText } from './routes.mjs';
+import { CODEX_COMPUTER_USE_ONLY_POLICY, 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, RECOMMENDED_MCP_SERVERS, RECOMMENDED_SKILLS, chatCaptureIntakeText, context7ConfigToml, outcomeRubricPolicyText, 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';
 const SKS_GENERATED_GIT_PATTERNS = ['.sneakoscope/', '.codex/', '.agents/', 'AGENTS.md'];
@@ -90,7 +91,7 @@ function isSksManagedHook(hook) {
   return hook.type === 'command' && /\bhook\s+(?:user-prompt-submit|pre-tool|post-tool|permission-request|stop)\b/.test(command) && /\b(?:sks|sneakoscope|sks\.mjs)\b/.test(command);
 }
 
-const AGENTS_BLOCK = "\n# Sneakoscope Codex Managed Rules\n\nThis repository uses Sneakoscope Codex.\n\n## Core Rules\n\n- Codex native `/goal` workflows are the persisted continuation surface; Ralph is removed from the user-facing SKS surface.\n- Keep runtime state bounded: raw logs go to files, prompts get tails/summaries, and `sks gc` may prune stale artifacts.\n- Before substantive work, SKS checks npm for a newer package. If newer, ask update-now vs skip-for-this-conversation.\n- Versioning is managed by the SKS pre-commit hook; check `sks versioning status`. Bypass only with `SKS_DISABLE_VERSIONING=1`.\n- Installed harness files are immutable to LLM edits: `.codex/*`, `.agents/skills/`, `.codex/agents/`, `.sneakoscope/*policy*.json`, `AGENTS.md`, and `node_modules/sneakoscope`. The Sneakoscope engine source repo is the only automatic exception.\n- OMX/DCodex conflicts block setup/doctor. Show `sks conflicts prompt`; cleanup requires explicit human approval.\n- Do not stop at a plan when implementation was requested. Finish, verify, or report the hard blocker.\n- Do not create unrequested fallback implementation code. If the requested path is impossible, block with evidence instead of inventing substitute behavior.\n\n## Routes\n\n- General execution/code-changing prompts default to `$Team`: analysis scouts, TriWiki refresh/validate, read-only debate, consensus, concrete runtime task graph/inboxes, fresh executor team, review, integration, Honest Mode.\n- `$Computer-Use` / `$CU` is the maximum-speed Codex Computer Use lane for UI/browser/visual tasks: skip Team debate and upfront TriWiki loops, use Codex Computer Use directly, then refresh/validate TriWiki and run Honest Mode at final closeout.\n- `$Goal` is a fast bridge/overlay for Codex native `/goal` create/pause/resume/clear persistence controls; implementation continues through the selected SKS execution route.\n- TriWiki recall must stay bounded. Use `sks wiki sweep` to record demote, soft-forget, archive, delete, promote-to-skill, and promote-to-rule candidates instead of injecting every old claim.\n- Team missions must keep schema-backed evidence current: `work-order-ledger.json`, `effort-decision.json`, `team-dashboard-state.json`, and route-specific visual/dogfood artifacts where applicable. Use `sks validate-artifacts latest` before claiming those artifacts pass.\n- `$DFix` is only for tiny design/content edits and bypasses the main pipeline, Team, TriWiki/TriFix/reflection recording, and persistent route state; it still uses a one-line DFix-specific Honest check before final. `$Answer`, `$Help`, and `$Wiki` stay lightweight.\n- For code work, surface route/guard/write scopes first, split independent worker scopes when available, and keep parent-owned integration and verification.\n- Design work reads `design.md`; if missing, use `design-system-builder`. Image/logo/raster assets use `imagegen`.\n- Research, AutoResearch, performance, token, accuracy, SEO/GEO, or workflow-improvement claims need experiment/eval evidence. Do not claim live model accuracy without a scored dataset.\n- Treat handwritten files above 3000 lines as split-review risks. Run `sks code-structure scan` and prefer extraction before adding substantial logic.\n\n## Evidence And Context\n\n- Context7 is required for external libraries, APIs, MCPs, package managers, SDKs, and generated docs: resolve-library-id then query-docs.\n- When tech stack, framework, package, runtime, or deployment-platform versions change, use Context7 or official vendor web docs, record current syntax/security/limit guidance as high-priority TriWiki claims, then refresh and validate before coding.\n- TriWiki is the context-tracking SSOT for long-running missions, Team handoffs, and context-pressure recovery. Read `.sneakoscope/wiki/context-pack.json` before each stage, use `attention.use_first` for compact high-trust recall, hydrate `attention.hydrate_first` from source before risky or lower-trust decisions, refresh after findings or artifact changes, and validate before handoffs/final claims.\n- Source priority: current code/tests/config, decision contract, vgraph, beta, GX render/snapshot metadata, LLM Wiki coordinate index, then model knowledge only if allowed.\n- Final response before stop: summarize what was done, what changed for the user/repo, what was verified, and what remains unverified or blocked; then run Honest Mode. Say what passed and what was not verified.\n- `$From-Chat-IMG` uses forensic visual effort, not ordinary Team effort. Completion is blocked until source inventory, visual mapping, work-order coverage, scoped dogfood/QA, and post-fix verification artifacts are present and valid.\n\n## Safety\n\n- Database access is high risk. Use read-only inspection by default; live data mutation is out of scope unless a sealed contract allows local or branch-only migration files.\n- MAD and MAD-SKS widen only explicit scoped permissions; they still do not authorize unrequested fallback implementation code.\n- Task completion requires relevant tests or justification, zero unsupported critical claims, accepted visual/wiki drift, and final evidence.\n\n## Codex App\n\nUse `.codex/SNEAKOSCOPE.md`, generated `.agents/skills`, `.codex/hooks.json`, and SKS dollar commands (`$sks`, `$team`, `$computer-use`, `$cu`, `$goal`, `$dfix`, `$qa-loop`, etc.) as the app control surface.\n";
+const AGENTS_BLOCK = "\n# Sneakoscope Codex Managed Rules\n\nThis repository uses Sneakoscope Codex.\n\n## Core Rules\n\n- Codex native `/goal` workflows are the persisted continuation surface; Ralph is removed from the user-facing SKS surface.\n- Keep runtime state bounded: raw logs go to files, prompts get tails/summaries, and `sks gc` may prune stale artifacts.\n- Before substantive work, SKS checks npm for a newer package. If newer, ask update-now vs skip-for-this-conversation.\n- Versioning is managed by the SKS pre-commit hook; check `sks versioning status`. Bypass only with `SKS_DISABLE_VERSIONING=1`.\n- Installed harness files are immutable to LLM edits: `.codex/*`, `.agents/skills/`, `.codex/agents/`, `.sneakoscope/*policy*.json`, `AGENTS.md`, and `node_modules/sneakoscope`. The Sneakoscope engine source repo is the only automatic exception.\n- OMX/DCodex conflicts block setup/doctor. Show `sks conflicts prompt`; cleanup requires explicit human approval.\n- Do not stop at a plan when implementation was requested. Finish, verify, or report the hard blocker.\n- Do not create unrequested fallback implementation code. If the requested path is impossible, block with evidence instead of inventing substitute behavior.\n\n## Routes\n\n- General execution/code-changing prompts default to `$Team`: analysis scouts, TriWiki refresh/validate, read-only debate, consensus, concrete runtime task graph/inboxes, fresh executor team, review, integration, Honest Mode.\n- `$Computer-Use` / `$CU` is the maximum-speed Codex Computer Use lane for UI/browser/visual tasks: skip Team debate and upfront TriWiki loops, use Codex Computer Use directly, then refresh/validate TriWiki and run Honest Mode at final closeout.\n- `$Goal` is a fast bridge/overlay for Codex native `/goal` create/pause/resume/clear persistence controls; implementation continues through the selected SKS execution route.\n- TriWiki recall must stay bounded. Use `sks wiki sweep` to record demote, soft-forget, archive, delete, promote-to-skill, and promote-to-rule candidates instead of injecting every old claim.\n- Team missions must keep schema-backed evidence current: `work-order-ledger.json`, `effort-decision.json`, `team-dashboard-state.json`, and route-specific visual/dogfood artifacts where applicable. Use `sks validate-artifacts latest` before claiming those artifacts pass.\n- `$DFix` is only for tiny design/content edits and bypasses the main pipeline, Team, TriWiki/TriFix/reflection recording, and persistent route state; it still uses a one-line DFix-specific Honest check before final. `$Answer`, `$Help`, and `$Wiki` stay lightweight.\n- For code work, surface route/guard/write scopes first, split independent worker scopes when available, and keep parent-owned integration and verification.\n- Design work reads `design.md`; if missing, use `design-system-builder`. Image/logo/raster assets use `imagegen`.\n- Research, AutoResearch, performance, token, accuracy, SEO/GEO, or workflow-improvement claims need experiment/eval evidence. Do not claim live model accuracy without a scored dataset.\n- Treat handwritten files above 3000 lines as split-review risks. Run `sks code-structure scan` and prefer extraction before adding substantial logic.\n- 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`, `$cu`, `$goal`, `$dfix`, `$qa-loop`, etc.) as the app control surface.\n";
 
 export async function initProject(root, opts = {}) {
   const created = [];
@@ -105,7 +106,7 @@ export async function initProject(root, opts = {}) {
     if (repair.removed.length) created.push(`repaired generated SKS files (${repair.removed.length})`);
   }
   const dirs = [
-    '.sneakoscope/state', '.sneakoscope/missions', '.sneakoscope/db', '.sneakoscope/bus', '.sneakoscope/hproof', '.sneakoscope/db', '.sneakoscope/wiki', '.sneakoscope/memory/q0_raw', '.sneakoscope/memory/q1_evidence', '.sneakoscope/memory/q2_facts', '.sneakoscope/memory/q3_tags', '.sneakoscope/memory/q4_bits', '.sneakoscope/gx/cartridges', '.sneakoscope/model/fingerprints', '.sneakoscope/genome/candidates', '.sneakoscope/trajectories/raw', '.sneakoscope/locks', '.sneakoscope/tmp', '.sneakoscope/arenas', '.sneakoscope/reports', '.codex', '.codex/agents', '.agents/skills'
+    '.sneakoscope/state', '.sneakoscope/missions', '.sneakoscope/db', '.sneakoscope/bus', '.sneakoscope/hproof', '.sneakoscope/db', '.sneakoscope/wiki', '.sneakoscope/skills', '.sneakoscope/memory/q0_raw', '.sneakoscope/memory/q1_evidence', '.sneakoscope/memory/q2_facts', '.sneakoscope/memory/q3_tags', '.sneakoscope/memory/q4_bits', '.sneakoscope/gx/cartridges', '.sneakoscope/model/fingerprints', '.sneakoscope/genome/candidates', '.sneakoscope/trajectories/raw', '.sneakoscope/locks', '.sneakoscope/tmp', '.sneakoscope/arenas', '.sneakoscope/reports', '.codex', '.codex/agents', '.agents/skills'
   ];
   for (const d of dirs) await ensureDir(path.join(root, d));
   const localExclude = localOnly ? await ensureLocalOnlyGitExclude(root) : null;
@@ -145,6 +146,14 @@ export async function initProject(root, opts = {}) {
     },
     recommended_skills: RECOMMENDED_SKILLS,
     recommended_mcp_servers: RECOMMENDED_MCP_SERVERS,
+    skill_dreaming: {
+      state: SKILL_DREAM_POLICY.state_path,
+      latest_report: SKILL_DREAM_POLICY.latest_report_path,
+      min_events_between_runs: SKILL_DREAM_POLICY.min_events_between_runs,
+      min_interval_hours: SKILL_DREAM_POLICY.min_interval_hours,
+      apply_mode: SKILL_DREAM_POLICY.apply_mode,
+      no_auto_delete: SKILL_DREAM_POLICY.no_auto_delete
+    },
     harness_guard: {
       enabled: true,
       policy: '.sneakoscope/harness-guard.json',
@@ -529,24 +538,24 @@ export async function installSkills(root) {
   const skills = {
     'dfix': `---\nname: dfix\ndescription: Ultralight fast design/content fix mode for $DFix or $dfix requests and inferred simple edits such as text color, copy, labels, spacing, or translation.\n---\n\nUse for tiny copy/color/label/spacing/translation edits. List exact micro-edits, inspect only needed files, apply only those edits, and run cheap verification. Bypass broad SKS routing, mission state, TriWiki/TriFix/reflection/state recording, Goal, Research, eval, redesign, and repeated full-route Honest Mode loops. Start the final answer with \`DFix 완료 요약:\` and include one \`DFix 솔직모드:\` line covering verified, not verified, and remaining issues. Read \`design.md\` for UI work when present; use imagegen for image/logo/raster assets.\n`,
     'answer': `---\nname: answer\ndescription: Answer-only research route for ordinary questions that should not start implementation.\n---\n\nUse for explanations, comparisons, status, facts, source-backed research, or docs guidance. Use repo/TriWiki first for project-local facts; hydrate low-trust claims from source. Browse or use Context7 for current external package/API/framework/MCP docs. End with a concise answer summary plus Honest Mode; do not create missions, subagents, or file edits.\n`,
-    'sks': `---\nname: sks\ndescription: General Sneakoscope Codex command route for $SKS or $sks usage, setup, status, and workflow help.\n---\n\nUse local SKS commands: bootstrap, deps, commands, quickstart, codex-app, context7, guard, conflicts, reasoning, wiki, pipeline. Promote code-changing work to Team unless Answer/DFix/Help/Wiki/safety route fits. Surface route/guard/scope, use TriWiki, do not edit installed harness files outside this engine repo, and require human-approved conflict cleanup.\n`,
+    'sks': `---\nname: sks\ndescription: General Sneakoscope Codex command route for $SKS or $sks usage, setup, status, and workflow help.\n---\n\nUse local SKS commands: bootstrap, deps, commands, quickstart, codex-app, context7, guard, conflicts, reasoning, wiki, pipeline, skill-dream. Promote code-changing work to Team unless Answer/DFix/Help/Wiki/safety route fits. Surface route/guard/scope, use TriWiki, do not edit installed harness files outside this engine repo, and require human-approved conflict cleanup. ${skillDreamPolicyText()}\n`,
     'wiki': `---\nname: wiki\ndescription: Dollar-command route for $Wiki TriWiki refresh, pack, validate, and prune commands.\n---\n\nUse for $Wiki or Korean wiki-refresh requests. Refresh/update/갱신: run sks wiki refresh, then validate .sneakoscope/wiki/context-pack.json. Pack: run sks wiki pack, then validate. Prune/clean/정리: use sks wiki refresh --prune, or sks wiki prune --dry-run for inspection. Report claims, anchors, trust, attention.use_first/hydrate_first, validation, and blockers. Do not start ambiguity-gated implementation, subagents, or unrelated work.\n`,
-    'team': `---\nname: team\ndescription: SKS Team orchestration for $Team/code work; $From-Chat-IMG is the explicit chat-image alias.\n---\n\nUse for $Team/code work. Ambiguity gate first. Write team-roster.json; team-gate.json needs team_roster_confirmed=true. executor:N means N scouts, N debate voices, then fresh N executors. After consensus, compile team-graph.json, team-runtime-tasks.json, team-decomposition-report.json, and team-inbox/ so worker handoff uses concrete runtime task ids with role/path/domain/lane hints. Refresh/validate TriWiki before debate, implementation, review, and final; consume attention.use_first and hydrate attention.hydrate_first before risky decisions. Log events and use sks team message for bounded inter-agent communication in transcript/lane panes. Color-coded Warp lanes distinguish overview/scout/planning/execution/review/safety sessions. End with cleanup-warp or a cleanup event so follow panes show cleanup and stop; pass team-session-cleanup.json, then reflection and Honest Mode. Parent integrates/verifies.\n\n${chatCaptureIntakeText()}\n`,
+    'team': `---\nname: team\ndescription: SKS Team orchestration for $Team/code work; $From-Chat-IMG is the explicit chat-image alias.\n---\n\nUse for $Team/code work. Ambiguity gate first. Write team-roster.json; team-gate.json needs team_roster_confirmed=true. executor:N means N scouts, N debate voices, then fresh N executors. After consensus, compile team-graph.json, team-runtime-tasks.json, team-decomposition-report.json, and team-inbox/ so worker handoff uses concrete runtime task ids with role/path/domain/lane hints. Refresh/validate TriWiki before debate, implementation, review, and final; consume attention.use_first and hydrate attention.hydrate_first before risky decisions. ${outcomeRubricPolicyText()} ${speedLanePolicyText()} ${skillDreamPolicyText()} Log events and use sks team message for bounded inter-agent communication in transcript/lane panes. Color-coded Warp lanes distinguish overview/scout/planning/execution/review/safety sessions. End with cleanup-warp or a cleanup event so follow panes show cleanup and stop; pass team-session-cleanup.json, then reflection and Honest Mode. Parent integrates/verifies.\n\n${chatCaptureIntakeText()}\n`,
     'from-chat-img': `---\nname: from-chat-img\ndescription: Explicit $From-Chat-IMG Team alias for chat screenshot plus attachment analysis.\n---\n\nUse only for From-Chat-IMG/$From-Chat-IMG. It enters the normal Team pipeline. Treat uploads as chat screenshot plus originals. Use Codex Computer Use visual inspection when available, list requirements first, match regions to attachments with confidence, write ${FROM_CHAT_IMG_COVERAGE_ARTIFACT}, ${FROM_CHAT_IMG_CHECKLIST_ARTIFACT}, ${FROM_CHAT_IMG_TEMP_TRIWIKI_ARTIFACT}, and ${FROM_CHAT_IMG_QA_LOOP_ARTIFACT}, then continue Team gates, review, reflection, and Honest Mode. ${CODEX_COMPUTER_USE_ONLY_POLICY} The ledger must account for every visible customer request, screenshot image region, and separate attachment; ${FROM_CHAT_IMG_CHECKLIST_ARTIFACT} must have a checked item for each request, image-region/attachment match, work item, scoped QA-LOOP, and verification step; ${FROM_CHAT_IMG_TEMP_TRIWIKI_ARTIFACT} stores temporary TriWiki-backed session context with expires_after_sessions=${FROM_CHAT_IMG_TEMP_TRIWIKI_SESSIONS}. ${FROM_CHAT_IMG_QA_LOOP_ARTIFACT} must prove QA-LOOP ran over the exact customer-request work-order range after implementation, with every work item covered, post-fix verification complete, and zero unresolved findings. team-gate.json cannot pass From-Chat-IMG completion until unresolved_items is empty, every checklist box is checked, and scoped_qa_loop_completed=true.\n`,
     'qa-loop': `---\nname: qa-loop\ndescription: $QA-LOOP dogfoods UI/API as human proxy with safety gates, Codex Computer Use-only UI evidence, safe fixes, rechecks, and a QA report.\n---\n\nUse only $QA-LOOP. Ask scope, target, mutation, login. Credentials are runtime-only; never save secrets. UI-level E2E needs Codex Computer Use evidence or must be marked unverified; Chrome MCP, Browser Use, Playwright, Selenium, Puppeteer, and other browser automation do not satisfy UI/browser verification. Deployed targets are read-only; destructive removal is forbidden. After answer/run, dogfood real flows, apply safe contract-allowed code/test/docs fixes, recheck, and do not pass qa-gate.json with unresolved findings or without post_fix_verification_complete. Finish qa-ledger, date/version report, gate, completion summary, and Honest Mode.\n`,
     'computer-use': `---\nname: computer-use\ndescription: Maximum-speed $Computer-Use/$CU lane for Codex Computer Use UI/browser/visual tasks.\n---\n\nUse only when the user invokes $Computer-Use/$CU or asks for a Computer Use-specific fast lane. Skip Team debate, QA-LOOP clarification, upfront TriWiki refresh, Context7, subagents, and reflection unless explicitly requested. Infer the smallest target, use Codex Computer Use directly, and never substitute Playwright, Chrome MCP, Browser Use, Selenium, Puppeteer, or other browser automation for UI/browser evidence. If Computer Use is unavailable, mark UI/browser evidence unverified and stop with the blocker. At the end only, refresh or pack TriWiki, validate it, then provide a concise completion summary plus Honest Mode.\n`,
     'computer-use-fast': `---\nname: computer-use-fast\ndescription: Alias for the maximum-speed $Computer-Use/$CU Codex Computer Use lane.\n---\n\nUse the same rules as computer-use: skip Team debate, QA-LOOP clarification, upfront TriWiki refresh, Context7, subagents, and reflection unless explicitly requested. Use Codex Computer Use directly; never substitute Playwright, Chrome MCP, Browser Use, Selenium, Puppeteer, or other browser automation for UI/browser evidence. At the end only, refresh/pack TriWiki, validate it, then provide a concise completion summary plus Honest Mode.\n`,
     'cu': `---\nname: cu\ndescription: Short alias for the maximum-speed $Computer-Use Codex Computer Use lane.\n---\n\nUse the same rules as computer-use. This is a speed lane for focused UI/browser/visual tasks that require Codex Computer Use evidence, with TriWiki refresh/validate and Honest Mode deferred to final closeout.\n`,
     'goal': `---\nname: goal\ndescription: Fast $Goal/$goal bridge overlay for Codex native persisted /goal workflows.\n---\n\nUse when the user invokes $Goal/$goal or asks to persist a workflow with Codex native /goal continuation. Prepare with sks goal create or the $Goal route, write only the lightweight bridge artifacts, then use native Codex /goal create, pause, resume, and clear controls where available. Goal does not replace Team, QA, DB, or other SKS execution routes; continue implementation through the selected route and use Context7 only when external API/library docs are involved. Do not recreate the old no-question loop.\n`,
-    'research': `---\nname: research\ndescription: Dollar-command route for $Research or $research frontier discovery workflows.\n---\n\nUse when the user invokes $Research/$research or asks for research, hypotheses, new mechanisms, falsification, or testable predictions. Prefer sks research prepare and sks research run. Do not use for ordinary code edits.\n`,
+    'research': `---\nname: research\ndescription: Dollar-command route for $Research or $research frontier discovery workflows.\n---\n\nUse when the user invokes $Research/$research or asks for research, hypotheses, new mechanisms, falsification, or testable predictions. Prefer sks research prepare and sks research run. Keep the loop short: frame outcome, compare a few mechanisms, falsify, keep the smallest useful probe, and avoid adding background process unless it reduces net route weight. Do not use for ordinary code edits.\n`,
     'autoresearch': `---\nname: autoresearch\ndescription: Dollar-command route for $AutoResearch or $autoresearch iterative experiment loops.\n---\n\nUse for $AutoResearch, iterative improvement, SEO/GEO, ranking, workflow, benchmark, or experiments. Define program, hypothesis, experiment, metric, keep/discard, falsification, next step, and Honest Mode. Load seo-geo-optimizer for README/npm/GitHub/schema/AI-search work.\n`,
     'db': `---\nname: db\ndescription: Dollar-command route for $DB or $db database and Supabase safety checks.\n---\n\nUse when the user invokes $DB/$db or the task touches SQL, Supabase, Postgres, migrations, Prisma, Drizzle, Knex, MCP database tools, or production data. Run or follow sks db policy, sks db scan, sks db classify, and sks db check. Destructive database operations remain forbidden.\n`,
     'mad-sks': `---\nname: mad-sks\ndescription: Explicit high-risk authorization modifier for $MAD-SKS scoped Supabase MCP DB permission widening.\n---\n\nUse only when the user explicitly invokes $MAD-SKS. It can be combined with another route, such as $MAD-SKS $Team or $DB ... $MAD-SKS; in that case the other command remains the primary workflow and MAD-SKS is only the temporary permission grant. The widened DB permission applies only while the active mission gate is open, must be deactivated when the task ends, and opens Supabase MCP column/schema cleanup, direct execute SQL, and normal DB write permissions. Keep only catastrophic database-wipe safeguards: whole database/table removal, all-row delete/update, reset, and dangerous project/branch management remain blocked. Do not carry MAD-SKS permission into later prompts or routes.\n`,
     'gx': `---\nname: gx\ndescription: Dollar-command route for $GX or $gx deterministic GX visual context cartridges.\n---\n\nUse when the user invokes $GX/$gx or asks for architecture/context visualization through SKS. Prefer sks gx init, render, validate, drift, and snapshot. vgraph.json remains the source of truth.\n`,
     'help': `---\nname: help\ndescription: Dollar-command route for $Help or $help explaining installed SKS commands and workflows.\n---\n\nUse when the user invokes $Help/$help or asks what commands exist. Prefer concise output from sks commands, sks usage <topic>, sks quickstart, sks aliases, and sks codex-app.\n`,
-    'prompt-pipeline': `---\nname: prompt-pipeline\ndescription: Default SKS prompt optimization pipeline for execution prompts; Answer and DFix bypass it.\n---\n\nClassify intent: Answer only for real questions; question-shaped implicit instructions, complaints, and mandatory-policy statements route to Team. DFix handles tiny design/content; code defaults to Team unless safety/research/GX route fits. Infer goal, target, constraints, acceptance, risk, and smallest safe route. Ask only scope/safety/behavior/acceptance-changing questions; otherwise seal inferred answers. Code work surfaces route/guard/scopes, materializes team-roster.json from default or explicit counts before implementation, compiles concrete Team runtime graph/inbox artifacts after consensus, and parent owns integration/tests/Context7/Honest Mode.\n\n${chatCaptureIntakeText()}\n\nDesign: read design.md; if missing use design-system-builder; use imagegen for image/logo/raster. TriWiki context-tracking SSOT: .sneakoscope/wiki/context-pack.json; read only the latest coordinate+voxel overlay pack before every route stage, run sks wiki refresh/pack after changes, validate before handoffs/final.\n`,
+    'prompt-pipeline': `---\nname: prompt-pipeline\ndescription: Default SKS prompt optimization pipeline for execution prompts; Answer and DFix bypass it.\n---\n\nClassify intent: Answer only for real questions; question-shaped implicit instructions, complaints, and mandatory-policy statements route to Team. DFix handles tiny design/content; code defaults to Team unless safety/research/GX route fits. Infer goal, target, constraints, acceptance, risk, and smallest safe route. Ask only scope/safety/behavior/acceptance-changing questions; otherwise seal inferred answers. Code work surfaces route/guard/scopes, materializes team-roster.json from default or explicit counts before implementation, compiles concrete Team runtime graph/inbox artifacts after consensus, and parent owns integration/tests/Context7/Honest Mode. ${outcomeRubricPolicyText()} ${speedLanePolicyText()} ${skillDreamPolicyText()}\n\n${chatCaptureIntakeText()}\n\nDesign: read design.md; if missing use design-system-builder; use imagegen for image/logo/raster. TriWiki context-tracking SSOT: .sneakoscope/wiki/context-pack.json; read only the latest coordinate+voxel overlay pack before every route stage, run sks wiki refresh/pack after changes, validate before handoffs/final.\n`,
     'reasoning-router': `---\nname: reasoning-router\ndescription: Temporary SKS reasoning-effort routing for every command and pipeline route.\n---\n\nmedium: simple copy/color/discovery/setup/mechanical edits. high: logic, safety, architecture, DB, orchestration, refactor, multi-file work. xhigh: research, AutoResearch, falsification, benchmarks, SEO/GEO, open-ended discovery, and From-Chat-IMG image work-order analysis. Routing is temporary; return to default after the gate. Inspect with sks reasoning and sks pipeline status.\n`,
-    'pipeline-runner': `---\nname: pipeline-runner\ndescription: Execute SKS dollar-command routes as stateful pipelines with mission artifacts, route gates, Context7 evidence, temporary reasoning routing, reflection, and Honest Mode.\n---\n\nEvery $ command is a route. Use current.json and mission artifacts, temporary reasoning, TriWiki before stages, source hydration, Context7 when required, Team cleanup before reflection, reflection for full routes, and completion summary plus Honest Mode before final. Surface guard/scopes, record evidence, refresh/pack/validate TriWiki, and check sks pipeline status/resume.\n`,
+    'pipeline-runner': `---\nname: pipeline-runner\ndescription: Execute SKS dollar-command routes as stateful pipelines with mission artifacts, route gates, Context7 evidence, temporary reasoning routing, reflection, and Honest Mode.\n---\n\nEvery $ command is a route. Use current.json and mission artifacts, temporary reasoning, TriWiki before stages, source hydration, Context7 when required, Team cleanup before reflection, reflection for full routes, and completion summary plus Honest Mode before final. Surface guard/scopes, record evidence, refresh/pack/validate TriWiki, and check sks pipeline status/resume. ${speedLanePolicyText()} ${skillDreamPolicyText()}\n`,
     'context7-docs': `---\nname: context7-docs\ndescription: Enforce Context7 MCP documentation evidence for SKS routes that depend on external libraries, frameworks, APIs, MCPs, package managers, DB SDKs, or generated docs.\n---\n\nWhen required, resolve-library-id, then query-docs for the resolved id. Legacy get-library-docs evidence is accepted. Prefer sks context7 tools/resolve/docs/evidence and finish only after both evidence stages exist. Check setup with sks context7 check.\n`,
     'seo-geo-optimizer': `---\nname: seo-geo-optimizer\ndescription: SEO/GEO support for README, npm, GitHub, keywords, snippets, schema, and AI-search visibility.\n---\n\nUse for SEO/GEO, package metadata, README ranking, snippets, schema, and AI search. Optimize README, package.json, docs, badges, topics, quickstart, examples, command discovery, exact names, keywords, and AI Answer Snapshot. Do not invent metrics; use $AutoResearch unless it is a tiny copy edit.\n`,
     'reflection': `---\nname: reflection\ndescription: Post-route self-review for full SKS routes that records real misses, gaps, and corrective lessons into TriWiki memory.\n---\n\nUse after full route work/tests and before final. DFix, Answer, Help, Wiki, SKS discovery are exempt. Do not invent faults. Write reflection.md; append real lessons to ${REFLECTION_MEMORY_PATH}; refresh/pack, validate context-pack.json, pass reflection-gate.json.\n\n${reflectionInstructionText()}\n`,

package/src/core/perf-bench.mjs

@@ -86,10 +86,14 @@ export async function runWorkflowPerfBench(root, opts = {}) {
       proof_field_build_ms_p95: proofFieldMsP95,
       workflow_scan_ms_p95: workflowScanMsP95,
       decision_mode: proofField?.fast_lane_decision?.mode || null,
+      execution_lane: proofField?.execution_lane?.lane || null,
       fast_lane_eligible: Boolean(proofField?.fast_lane_decision?.eligible),
+      fast_lane_allowed: Boolean(proofField?.execution_lane?.fast_lane_allowed),
       proof_cone_count: proofField?.proof_cones?.length || 0,
       verification_count: verification.length,
       negative_work_skipped_count: estimatedSavedWork,
+      simplicity_score: Number(proofField?.simplicity_scorecard?.score || 0),
+      outcome_criteria_passed: (proofField?.simplicity_scorecard?.criteria || []).filter((item) => item.passed).length,
       proof_field_valid: proofValidation.ok
     },
     proof_field: proofField,
@@ -106,6 +110,8 @@ export function validateWorkflowPerfReport(report = {}) {
   if (report.theory !== 'Potential Proof Field') issues.push('theory');
   if (!report.metrics || !Number.isFinite(Number(report.metrics.proof_field_build_ms_p95))) issues.push('proof_field_build_ms_p95');
   if (!report.metrics?.decision_mode) issues.push('decision_mode');
+  if (!report.metrics?.execution_lane) issues.push('execution_lane');
+  if (!Number.isFinite(Number(report.metrics?.simplicity_score))) issues.push('simplicity_score');
   if (!report.proof_field || !validateProofFieldReport(report.proof_field).ok) issues.push('proof_field');
   if (!report.recommendation?.mode) issues.push('recommendation');
   return { ok: issues.length === 0, issues };
@@ -128,7 +134,7 @@ function workflowRecommendation(proofField, validation) {
   if (decision.eligible) {
     return {
       mode: 'fast_lane',
-      reason: 'selected proof cones are narrow and all unrelated work is safely cached as negative work',
+      reason: `selected proof cones are narrow, execution lane ${proofField.execution_lane?.lane || 'unknown'}, outcome score ${proofField.simplicity_scorecard?.score ?? 'n/a'}, and unrelated work is cached as negative work`,
       next: decision.verification
     };
   }

package/src/core/pipeline.mjs

@@ -10,9 +10,9 @@ import { GOAL_WORKFLOW_ARTIFACT, writeGoalWorkflow } from './goal-workflow.mjs';
 import { writeCodeStructureReport } from './code-structure.mjs';
 import { writeMemorySweepReport } from './memory-governor.mjs';
 import { writeMistakeMemoryReport } from './mistake-memory.mjs';
-import { writeSkillForgeReport } from './skill-forge.mjs';
+import { recordSkillDreamEvent, skillDreamPolicyText, writeSkillForgeReport } from './skill-forge.mjs';
 import { writeResearchPlan } from './research.mjs';
-import { CODEX_COMPUTER_USE_EVIDENCE_SOURCE, CODEX_COMPUTER_USE_ONLY_POLICY, 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, chatCaptureIntakeText, context7RequirementText, dollarCommand, evidenceMentionsForbiddenBrowserAutomation, hasFromChatImgSignal, hasMadSksSignal, noUnrequestedFallbackCodePolicyText, reflectionRequiredForRoute, reasoningInstruction, routeNeedsContext7, routePrompt, routeReasoning, routeRequiresSubagents, stripDollarCommand, stripMadSksSignal, subagentExecutionPolicyText, stackCurrentDocsPolicyText, triwikiContextTracking, triwikiContextTrackingText, triwikiStagePolicyText } from './routes.mjs';
+import { CODEX_COMPUTER_USE_EVIDENCE_SOURCE, CODEX_COMPUTER_USE_ONLY_POLICY, 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, chatCaptureIntakeText, context7RequirementText, dollarCommand, evidenceMentionsForbiddenBrowserAutomation, hasFromChatImgSignal, hasMadSksSignal, noUnrequestedFallbackCodePolicyText, outcomeRubricPolicyText, reflectionRequiredForRoute, reasoningInstruction, routeNeedsContext7, routePrompt, routeReasoning, routeRequiresSubagents, speedLanePolicyText, stripDollarCommand, stripMadSksSignal, subagentExecutionPolicyText, stackCurrentDocsPolicyText, triwikiContextTracking, triwikiContextTrackingText, triwikiStagePolicyText } from './routes.mjs';
 import { TEAM_DECOMPOSITION_ARTIFACT, TEAM_GRAPH_ARTIFACT, TEAM_INBOX_DIR, TEAM_RUNTIME_TASKS_ARTIFACT, teamRuntimePlanMetadata, teamRuntimeRequiredArtifacts, validateTeamRuntimeArtifacts, writeTeamRuntimeArtifacts } from './team-dag.mjs';
 import { formatRoleCounts, initTeamLive, parseTeamSpecText } from './team-live.mjs';
 
@@ -52,6 +52,9 @@ export function promptPipelineContext(prompt, route = routePrompt(prompt)) {
     'Stance: infer the user intent aggressively from rough wording and local context, but ask short ambiguity-removal questions before work when a missing answer can change the target, scope, safety boundary, or acceptance criteria.',
     subagentExecutionPolicyText(route, prompt),
     noUnrequestedFallbackCodePolicyText(),
+    outcomeRubricPolicyText(),
+    speedLanePolicyText(),
+    skillDreamPolicyText(),
     'Design routing: UI/UX reads design.md first; if missing, use design-system-builder from docs/Design-Sys-Prompt.md with plan-tool clarification and a default font recommendation. Existing designs use design-ui-editor plus design-artifact-expert. Image/logo/raster assets use imagegen.',
     triwikiContextTrackingText(),
     triwikiStagePolicyText(),
@@ -110,25 +113,51 @@ export async function prepareRoute(root, prompt, state = {}) {
   const task = stripDollarCommand(stripMadSksSignal(prompt)) || stripMadSksSignal(stripDollarCommand(prompt)) || String(prompt || '').trim();
   const explicit = Boolean(dollarCommand(prompt));
   if (!route) return { route: null, additionalContext: promptPipelineContext(prompt, null) };
-  if (route.id === 'DFix') return prepareDfixQuickRoute(route, task);
-  if (route.id === 'Answer') return prepareAnswerOnlyRoute(route, task);
-  if (route.id === 'ComputerUse') return prepareComputerUseFastRoute(route, task);
-  if (route.id === 'Wiki') return prepareWikiQuickRoute(route, task);
-  if (route.id === 'Goal') return prepareGoal(root, route, task, routeNeedsContext7(route, prompt));
+  const dreamContext = await routeSkillDreamContext(root, route, task);
+  if (route.id === 'DFix') return withSkillDreamContext(await prepareDfixQuickRoute(route, task), dreamContext);
+  if (route.id === 'Answer') return withSkillDreamContext(await prepareAnswerOnlyRoute(route, task), dreamContext);
+  if (route.id === 'ComputerUse') return withSkillDreamContext(await prepareComputerUseFastRoute(route, task), dreamContext);
+  if (route.id === 'Wiki') return withSkillDreamContext(await prepareWikiQuickRoute(route, task), dreamContext);
+  if (route.id === 'Goal') return withSkillDreamContext(await prepareGoal(root, route, task, routeNeedsContext7(route, prompt)), dreamContext);
   const required = routeNeedsContext7(route, prompt);
   const reasoning = routeReasoning(route, prompt);
   const subagentsRequired = routeRequiresSubagents(route, prompt);
-  if (route.id !== 'Help') return prepareClarificationGate(root, route, task, required, { madSksAuthorization });
-  if (route.id === 'Team') return prepareTeam(root, route, task, required);
-  if (route.id === 'Research') return prepareResearch(root, route, task, required);
-  if (route.id === 'AutoResearch') return prepareAutoResearch(root, route, task, required);
-  if (route.id === 'DB') return prepareDb(root, route, task, required);
-  if (route.id === 'GX') return prepareGx(root, route, task, required);
-  if (explicit || required) return prepareLightRoute(root, route, task, required);
-  return {
+  if (route.id !== 'Help') return withSkillDreamContext(await prepareClarificationGate(root, route, task, required, { madSksAuthorization }), dreamContext);
+  if (route.id === 'Team') return withSkillDreamContext(await prepareTeam(root, route, task, required), dreamContext);
+  if (route.id === 'Research') return withSkillDreamContext(await prepareResearch(root, route, task, required), dreamContext);
+  if (route.id === 'AutoResearch') return withSkillDreamContext(await prepareAutoResearch(root, route, task, required), dreamContext);
+  if (route.id === 'DB') return withSkillDreamContext(await prepareDb(root, route, task, required), dreamContext);
+  if (route.id === 'GX') return withSkillDreamContext(await prepareGx(root, route, task, required), dreamContext);
+  if (explicit || required) return withSkillDreamContext(await prepareLightRoute(root, route, task, required), dreamContext);
+  return withSkillDreamContext({
     route,
     additionalContext: `${promptPipelineContext(prompt, route)}\n\nReasoning: ${reasoning.effort} (${reasoning.reason}); temporary profile ${reasoning.profile}.\nRequired skills: ${route.requiredSkills.join(', ')}.\nSubagents required: ${subagentsRequired ? 'yes' : 'no'}.`
-  };
+  }, dreamContext);
+}
+
+async function routeSkillDreamContext(root, route, task) {
+  try {
+    const result = await recordSkillDreamEvent(root, {
+      route: route.id,
+      command: route.command,
+      required_skills: route.requiredSkills || [],
+      prompt: task
+    });
+    if (!result.report) return '';
+    return [
+      'Skill dreaming threshold reached.',
+      `Report: ${path.relative(root, result.report.report_path)}`,
+      `Mode: ${result.report.apply_mode}; no_auto_delete=${result.report.no_auto_delete}.`,
+      'Review keep/merge/prune/improve candidates before adding more generated skills.'
+    ].join('\n');
+  } catch (err) {
+    return `Skill dreaming record failed: ${err.message || err}. Do not claim .sneakoscope/skills/dream-state.json was updated.`;
+  }
+}
+
+function withSkillDreamContext(result, dreamContext) {
+  if (!dreamContext) return result;
+  return { ...result, additionalContext: `${result.additionalContext || ''}\n\n${dreamContext}`.trim() };
 }
 
 async function prepareDfixQuickRoute(route, task) {
@@ -586,9 +615,9 @@ function context7ToolName(payload) {
 
 function context7Stage(payload) {
   const hay = JSON.stringify(payload || {});
-  if (!/(context7|resolve-library-id|get-library-docs|query-docs)/i.test(hay)) return null;
-  if (/resolve-library-id/i.test(hay)) return 'resolve-library-id';
-  if (/get-library-docs|query-docs/i.test(hay)) return 'get-library-docs';
+  if (!/(context7|resolve[-_]?library[-_]?id|get[-_]?library[-_]?docs|query[-_]?docs)/i.test(hay)) return null;
+  if (/resolve[-_]?library[-_]?id/i.test(hay)) return 'resolve-library-id';
+  if (/get[-_]?library[-_]?docs|query[-_]?docs/i.test(hay)) return 'get-library-docs';
   return 'context7';
 }