@ngockhoale/ukit 1.1.7 → 1.1.8

package/CHANGELOG.md

@@ -4,6 +4,17 @@ All notable changes to UKit are documented here.
 
 ## Unreleased
 
+## 1.1.8 - 2026-05-05
+
+### Living Project Status
+
+- Added `docs/STATUS.md` as a compact living project-state baseline for active work, debug threads, blockers, verification, and next candidates.
+- Added `next-step` and `update-status` skills so Claude/Codex/OpenCode can use project status automatically without adding any user-facing commands beyond `ukit install`.
+- Made next-step routing freshness-aware: stale or missing status must be treated as orientation only and verified against source/index before recommendations.
+- Added concrete-task precedence so prompts like “fix login bug but not sure next step” stay on the debug/implementation/review workflow instead of being hijacked by global roadmap suggestions.
+- Registered status docs/skills in the manifest with skip semantics for the living doc, and kept source route catalogs aligned with installed helper mirrors.
+- Updated install/routing/manifest regression coverage for open-ended status prompts, explicit handoff updates, concrete debug edge cases, and default skill installation.
+
 ## 1.1.7 - 2026-04-25
 
 ### Impact Confidence

package/README.md

@@ -32,6 +32,7 @@ ukit install
 4. Fill in the generated docs baseline:
    - `docs/PROJECT.md`
    - `docs/MEMORY.md`
+   - `docs/STATUS.md`
    - `docs/WORKLOG.md`
 5. Open your AI tool and work in natural language.
 
@@ -64,9 +65,9 @@ If maintainers roll out a newer CLI build, the in-project workflow still stays t
 **Project support files**
 - `.claude/ukit/.ukit/` — installer manifests, metadata, backups
 - `.ukit/` — hidden shared runtime storage for config, cache, and cross-agent memory
-- `docs/` — PROJECT / MEMORY / WORKLOG baseline
+- `docs/` — PROJECT / MEMORY / STATUS / WORKLOG baseline
 
-## UKit v1.1.7 Runtime
+## UKit v1.1.8 Runtime
 
 UKit now installs a hidden shared local runtime at `.ukit/` for production-oriented state that should survive across agent sessions:
 
@@ -83,15 +84,17 @@ When long sessions approach the compact threshold, UKit now uses a conservative
 - compact only safe-zone history/noise
 - preserve active task, rules, decisions, and current code focus
 
-UKit v1.1.7 keeps the same shared runtime contract while adding impact-confidence routing for shared runtime/template changes:
+UKit v1.1.8 keeps the same shared runtime contract while adding living project status routing for continuity-safe AI sessions:
 
 - install globally with `npm install -g @ngockhoale/ukit`
 - keep using the exact same human workflow inside projects: `ukit install`
 - preserve the same `ukit` binary, hooks, and install-first orchestration while standardizing the runtime root as hidden `.ukit/`
-- route shared index/helper/hook/template edits as higher-impact work instead of treating them like ordinary simple changes
-- surface mirror-counterpart and impact-test hints so agents verify source/runtime/template changes with better confidence
+- install `docs/STATUS.md` as a compact living state file for active work, debug threads, blockers, verification, and next candidates
+- auto-route open-ended “what next?” / “continue” prompts to the `next-step` skill with a visible freshness cue when status may be stale
+- auto-route explicit handoff/wrap-up requests to the `update-status` skill while skipping trivial/no-state-change tasks
+- keep concrete debug/implementation/review prompts primary, so project status never replaces source/index-first task work
 
-UKit v1.1.7 also keeps the fast path improvements from the recent runtime releases:
+UKit v1.1.8 also keeps the fast path improvements from the recent runtime releases:
 
 - Vietnamese prompts now normalize more effectively for English-heavy code symbols and paths
 - localized simple direct-target lanes skip extra previous-context / recent-output work when it would not change the next action

package/manifests/platform.full.yaml

@@ -143,6 +143,22 @@ items:
     packs:
       - core
 
+  - id: docs-status
+    type: config
+    sourceTemplate: docs/STATUS.md
+    targetPath: docs/STATUS.md
+    requires:
+      - docs-project
+      - docs-memory
+      - docs-worklog
+      - docs-code-map
+    mergeStrategy: skip
+    variables:
+      - project.name
+    enabledByDefault: true
+    packs:
+      - core
+
   - id: docs-bugfix
     type: config
     sourceTemplate: docs/BUGFIX.md
@@ -460,6 +476,32 @@ items:
     packs:
       - core
 
+  - id: next-step-skill
+    type: skill
+    sourceTemplate: .claude/skills/next-step/SKILL.md
+    targetPath: .claude/skills/next-step/SKILL.md
+    requires:
+      - docs-quality-skill
+      - docs-status
+    mergeStrategy: overwrite_with_backup
+    variables: []
+    enabledByDefault: true
+    packs:
+      - core
+
+  - id: update-status-skill
+    type: skill
+    sourceTemplate: .claude/skills/update-status/SKILL.md
+    targetPath: .claude/skills/update-status/SKILL.md
+    requires:
+      - docs-quality-skill
+      - docs-status
+    mergeStrategy: overwrite_with_backup
+    variables: []
+    enabledByDefault: true
+    packs:
+      - core
+
   - id: docs-manager-skill
     type: skill
     sourceTemplate: .claude/skills/docs-manager

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ngockhoale/ukit",
-  "version": "1.1.7",
+  "version": "1.1.8",
   "description": "Install/update an index-first AI workspace for Claude Code, Antigravity, OpenAI Codex, and OpenCode.",
   "license": "MIT",
   "type": "module",

package/src/cli/commands/doctor.js

@@ -62,6 +62,7 @@ export async function runDoctor({ packageRoot, projectRoot, argv = [] }) {
     sessionMemoryDirExists: await pathExists(runtimePaths.sessionsDir),
     docsProjectExists: await pathExists(path.join(projectRoot, 'docs', 'PROJECT.md')),
     docsMemoryExists: await pathExists(path.join(projectRoot, 'docs', 'MEMORY.md')),
+    docsStatusExists: await pathExists(path.join(projectRoot, 'docs', 'STATUS.md')),
     docsWorklogExists: await pathExists(path.join(projectRoot, 'docs', 'WORKLOG.md')),
     allProvidersConfigured: providers.allSupported,
     ...(codexAdapterTracked
@@ -103,6 +104,7 @@ export async function runDoctor({ packageRoot, projectRoot, argv = [] }) {
   console.log(`[UKit]   ${ok(checks.sessionMemoryDirExists)}  .ukit/storage/memory/sessions/`);
   console.log(`[UKit]   ${ok(checks.docsProjectExists)}  docs/PROJECT.md`);
   console.log(`[UKit]   ${ok(checks.docsMemoryExists)}  docs/MEMORY.md`);
+  console.log(`[UKit]   ${ok(checks.docsStatusExists)}  docs/STATUS.md`);
   console.log(`[UKit]   ${ok(checks.docsWorklogExists)}  docs/WORKLOG.md`);
   if (codexAdapterTracked) {
     console.log(`[UKit]   ${ok(checks.codexReadmeExists)}  .codex/README.md`);

package/src/cli/commands/install.js

@@ -244,9 +244,10 @@ export async function runInstall({ packageRoot, projectRoot, packageVersion, arg
   const docsPaths = [
     path.join(projectRoot, 'docs', 'PROJECT.md'),
     path.join(projectRoot, 'docs', 'MEMORY.md'),
+    path.join(projectRoot, 'docs', 'STATUS.md'),
     path.join(projectRoot, 'docs', 'WORKLOG.md'),
   ];
-  const docsLabels = ['docs/PROJECT.md', 'docs/MEMORY.md', 'docs/WORKLOG.md'];
+  const docsLabels = ['docs/PROJECT.md', 'docs/MEMORY.md', 'docs/STATUS.md', 'docs/WORKLOG.md'];
   const missingDocs = [];
   for (let i = 0; i < docsPaths.length; i++) {
     if (!(await pathExists(docsPaths[i]))) {
@@ -257,7 +258,7 @@ export async function runInstall({ packageRoot, projectRoot, packageVersion, arg
   if (missingDocs.length > 0) {
     console.log(`[UKit] Missing docs — fill these in before first use: ${missingDocs.join(', ')}`);
   } else {
-    console.log('[UKit] Docs baseline ready: docs/PROJECT.md, docs/MEMORY.md, docs/WORKLOG.md');
+    console.log('[UKit] Docs baseline ready: docs/PROJECT.md, docs/MEMORY.md, docs/STATUS.md, docs/WORKLOG.md');
     console.log('[UKit] Fill them once with real project context for the best results.');
   }
 

package/src/cli/commands/uninstall.js

@@ -47,5 +47,5 @@ export async function runUninstall({ projectRoot, argv = [] }) {
   }
 
   console.log(`[UKit] Uninstall complete. Removed ${result.removed}/${result.attempted} managed paths.`);
-  console.log('[UKit] Note: docs/PROJECT.md, docs/MEMORY.md, docs/WORKLOG.md contain user content and were preserved. Delete manually if needed.');
+  console.log('[UKit] Note: docs/PROJECT.md, docs/MEMORY.md, docs/STATUS.md, docs/WORKLOG.md contain user content and were preserved. Delete manually if needed.');
 }

package/src/core/runtimeConfig.js

@@ -42,7 +42,7 @@ export function buildDefaultRuntimeConfig(overrides = {}) {
   const safeOverrides = isPlainObject(overrides) ? overrides : {};
 
   return mergeObjects({
-    version: '1.1.7',
+    version: '1.1.8',
     agent: 'claude-code',
     compact: {
       enabled: true,

package/src/core/uninstall.js

@@ -200,7 +200,7 @@ export async function uninstallUkit({ projectRoot, dryRun = false }) {
     }
   } else {
     // Old format (no files list): fall back to hardcoded managed paths.
-    // NOTE: docs/PROJECT.md, MEMORY.md, WORKLOG.md are intentionally excluded.
+    // NOTE: docs/PROJECT.md, MEMORY.md, STATUS.md, WORKLOG.md are intentionally excluded.
     // These are user-created content (mergeStrategy: skip) — deleting them
     // would cause data loss. Users must remove them manually if desired.
     const fallback = buildFallbackPaths(projectRoot);

package/src/index/routeCatalog.js

@@ -223,8 +223,30 @@ export const ROUTE_CATALOG = [
     path: '.claude/skills/docs-quality/SKILL.md',
     order: 12,
     signals: [
-      { type: 'prompt', regex: /\b(docs|documentation|readme|changelog|handoff|worklog|memory|code map)\b/i, score: 4 },
-      { type: 'file', regex: /\bdocs\/|readme\.md$|project\.md$|memory\.md$|worklog\.md$|code_map\.md$/i, score: 4 },
+      { type: 'prompt', regex: /\b(docs|documentation|readme|changelog|handoff|worklog|memory|code map|status\.md)\b/i, score: 4 },
+      { type: 'file', regex: /\bdocs\/|readme\.md$|project\.md$|memory\.md$|status\.md$|worklog\.md$|code_map\.md$/i, score: 4 },
+    ],
+  },
+  {
+    id: 'next-step',
+    path: '.claude/skills/next-step/SKILL.md',
+    order: 12.1,
+    contextMode: 'standalone',
+    signals: [
+      { type: 'prompt', regex: /\b(what(?:'s| is)? next|next steps?|project status|current status|where are we|continue(?: from)?(?: last session)?|roadmap|status\.md)\b/i, score: 7 },
+      { type: 'prompt', regex: /\b(làm gì tiếp|bước tiếp theo|tiếp theo làm gì|làm tiếp|đang ở đâu|trạng thái project|tình trạng project)\b/i, score: 7 },
+    ],
+  },
+  {
+    id: 'update-status',
+    path: '.claude/skills/update-status/SKILL.md',
+    order: 12.2,
+    contextMode: 'standalone',
+    signals: [
+      { type: 'prompt', regex: /\b(update|refresh|write|sync|record|capture|summari[sz]e).{0,48}\b(status\.md|project status|current state|next candidates?|session state)\b/i, score: 9 },
+      { type: 'prompt', regex: /\b(status\.md|project status).{0,48}\b(update|refresh|write|sync|record|capture|summari[sz]e)\b/i, score: 9 },
+      { type: 'prompt', regex: /\b(wrap up|handoff|end(?:ing)? this session|session summary|before final)\b/i, score: 7 },
+      { type: 'prompt', regex: /\b(cập nhật|ghi lại|tổng kết|chốt session|bàn giao).{0,48}\b(status|trạng thái|việc tiếp theo)\b/i, score: 9 },
     ],
   },
   {

package/src/index/taskRouting.js

@@ -22,11 +22,17 @@ export async function deriveTaskRoute({
   const normalizedPrompt = String(promptText || '').trim();
   const normalizedCommand = String(commandText || '').trim();
   const normalizedTarget = normalizeRelativeFile(absoluteRoot, targetFile);
+  const intentMode = deriveIntentMode({
+    promptText: normalizedPrompt,
+    commandText: normalizedCommand,
+    targetFile: normalizedTarget,
+  });
   const activeSkills = await selectActiveSkills({
     rootDir: absoluteRoot,
     promptText: normalizedPrompt,
     commandText: normalizedCommand,
     targetFile: normalizedTarget,
+    intentMode,
   });
   const useIndexedContext = shouldUseIndexedContext({
     activeSkills,
@@ -102,6 +108,7 @@ export async function deriveTaskRoute({
       targetFile: normalizedTarget,
       contextIntent,
       taskType: inferredTaskType,
+      intentMode,
     },
     contextRecommendation,
     verificationRecommendation,
@@ -117,6 +124,7 @@ export async function deriveTaskRoute({
       targetFile: normalizedTarget,
       contextIntent,
       taskType: inferredTaskType,
+      intentMode,
     },
     contextRecommendation,
     verificationRecommendation,
@@ -175,6 +183,7 @@ export function buildRouteSummary({
     fallbackCommands,
     preferredOrder,
     policyMode,
+    intentMode: routingContext.intentMode ?? null,
     delegateHint: delegationRecommendation?.hint ?? null,
     nextActionType: nextAction?.type ?? null,
     nextActionCommand,
@@ -183,7 +192,7 @@ export function buildRouteSummary({
   };
 }
 
-async function selectActiveSkills({ rootDir, promptText, commandText, targetFile }) {
+async function selectActiveSkills({ rootDir, promptText, commandText, targetFile, intentMode = null }) {
   const routeSignals = {
     promptRawText: String(promptText || '').toLowerCase(),
     promptNormalizedText: buildRouteSignalText(promptText),
@@ -194,6 +203,7 @@ async function selectActiveSkills({ rootDir, promptText, commandText, targetFile
   const scoredEntries = ROUTE_CATALOG
     .map((entry) => scoreSkillRouteEntry(entry, routeSignals))
     .filter((entry) => entry.score > 0)
+    .filter((entry) => shouldKeepRouteEntryForIntent(entry, intentMode))
     .sort((a, b) => b.score - a.score || a.order - b.order);
   const active = [];
 
@@ -209,6 +219,22 @@ async function selectActiveSkills({ rootDir, promptText, commandText, targetFile
   return active.map(({ order, ...rest }) => rest);
 }
 
+function shouldKeepRouteEntryForIntent(entry, intentMode) {
+  if (entry.id === 'next-step' && ['scoped-advice', 'docs-specific'].includes(intentMode)) {
+    return false;
+  }
+
+  if (entry.id === 'update-status' && intentMode === 'docs-specific') {
+    return false;
+  }
+
+  if (entry.id === 'docs-quality' && ['open-ended-status', 'status-update'].includes(intentMode)) {
+    return false;
+  }
+
+  return true;
+}
+
 function scoreSkillRouteEntry(entry, routeSignals = {}) {
   let score = 0;
   const reasons = [];
@@ -282,6 +308,116 @@ function getSignalTexts(signalType, routeSignals = {}) {
   };
 }
 
+function deriveIntentMode({ promptText = '', commandText = '', targetFile = null } = {}) {
+  const lower = buildRouteSignalText(promptText, commandText);
+  const raw = `${promptText ?? ''}\n${commandText ?? ''}`.toLowerCase();
+  const docsSpecific = hasDocsSpecificTaskSignal(lower, raw, targetFile);
+  const statusUpdate = hasStatusUpdateSignal(lower, raw);
+  const openEndedStatus = hasOpenEndedStatusSignal(lower, raw);
+  const concreteTask = hasConcreteTaskSignal(lower, raw, targetFile);
+
+  if (docsSpecific) {
+    return 'docs-specific';
+  }
+
+  if (statusUpdate) {
+    return 'status-update';
+  }
+
+  if (concreteTask && openEndedStatus) {
+    return 'scoped-advice';
+  }
+
+  if (openEndedStatus) {
+    return 'open-ended-status';
+  }
+
+  if (concreteTask) {
+    if (/\b(bug|debug|error|crash|broken|failing|stack trace|triage|fix|login|timeout)\b/.test(lower)) {
+      return 'debug-specific';
+    }
+    if (/\b(review|audit|diff|pr feedback|code review|kiem tra|soat)\b/.test(lower)) {
+      return 'review-specific';
+    }
+    if (/\b(implement|build|create|add|ship|deliver|refactor|integrate|integration|scaffold|feature)\b/.test(lower)) {
+      return 'implement-specific';
+    }
+  }
+
+  return null;
+}
+
+function hasStatusUpdateSignal(lower, raw) {
+  return /\b(update|refresh|write|sync|record|capture|summarize|summarise).{0,64}\b(status\.md|project status|current state|next candidates|session state)\b/.test(lower)
+    || /\b(status\.md|project status).{0,64}\b(update|refresh|write|sync|record|capture|summarize|summarise)\b/.test(lower)
+    || /\b(wrap up|handoff|end this session|ending this session|session summary|before final)\b/.test(lower)
+    || /\b(cap nhat|ghi lai|tong ket|chot session|ban giao).{0,64}\b(status|trang thai|viec tiep theo)\b/.test(lower)
+    || /\b(cập nhật|ghi lại|tổng kết|chốt session|bàn giao).{0,64}\b(status|trạng thái|việc tiếp theo)\b/.test(raw);
+}
+
+function hasOpenEndedStatusSignal(lower, raw) {
+  return /\b(what next|what is next|what's next|next step|next steps|project status|current status|where are we|continue|continue from last session|roadmap|status\.md)\b/.test(lower)
+    || /\b(lam gi tiep|buoc tiep theo|tiep theo lam gi|lam tiep|dang o dau|trang thai project|tinh trang project)\b/.test(lower)
+    || /\b(làm gì tiếp|bước tiếp theo|tiếp theo làm gì|làm tiếp|đang ở đâu|trạng thái project|tình trạng project)\b/.test(raw);
+}
+
+function hasConcreteTaskSignal(lower, raw, targetFile) {
+  if (targetFile && !isStatusFileTarget(targetFile)) {
+    return true;
+  }
+
+  return /\b(bug|debug|error|crash|broken|failing|stack trace|triage|fix|implement|build|create|add|ship|deliver|refactor|integrate|integration|scaffold|feature|review|audit|diff|pr feedback|code review|auth|login|api|endpoint|test|spec)\b/.test(lower)
+    || /\b(sửa|fix|lỗi|bug|debug|implement|cài|thêm|review|kiểm tra|soát|đăng nhập)\b/.test(raw);
+}
+
+function hasDocsSpecificTaskSignal(lower, raw, targetFile) {
+  if (!targetFile || !isDocsTarget(targetFile)) {
+    return false;
+  }
+
+  const targetName = path.posix.basename(String(targetFile || '').replaceAll('\\', '/')).toLowerCase();
+  const explicitStatusUpdate = hasExplicitStatusUpdateSignal(lower, raw);
+
+  if (!isStatusFileTarget(targetFile)) {
+    if (explicitStatusUpdate && !mentionsTargetDoc(lower, targetName)) {
+      return false;
+    }
+
+    return mentionsTargetDoc(lower, targetName)
+      || /\b(edit|write|improve|document|docs?|readme|changelog|worklog|memory|code map|template|wording|copy|grammar|format|structure|heading|section|handoff notes?)\b/.test(lower)
+      || /\b(câu chữ|chỉnh|sửa chữ|ngữ pháp|định dạng|cấu trúc|tài liệu|ghi chú bàn giao)\b/.test(raw);
+  }
+
+  return /\b(template|wording|edit|copy|grammar|format|structure|heading|section|docs?)\b/.test(lower)
+    || /\b(mẫu|câu chữ|chỉnh|sửa chữ|ngữ pháp|định dạng|cấu trúc|tài liệu)\b/.test(raw);
+}
+
+function hasExplicitStatusUpdateSignal(lower, raw) {
+  return /\b(update|refresh|write|sync|record|capture|summarize|summarise).{0,64}\b(status\.md|project status|current state|next candidates|session state)\b/.test(lower)
+    || /\b(status\.md|project status).{0,64}\b(update|refresh|write|sync|record|capture|summarize|summarise)\b/.test(lower)
+    || /\b(cap nhat|ghi lai|tong ket|chot session|ban giao).{0,64}\b(status|trang thai|viec tiep theo)\b/.test(lower)
+    || /\b(cập nhật|ghi lại|tổng kết|chốt session|bàn giao).{0,64}\b(status|trạng thái|việc tiếp theo)\b/.test(raw);
+}
+
+function mentionsTargetDoc(lower, targetName) {
+  if (!targetName) {
+    return false;
+  }
+
+  const escaped = targetName.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
+  const withoutExt = escaped.replace(/\\\.md$/i, '');
+  return new RegExp(`\\b(?:${escaped}|${withoutExt})\\b`, 'i').test(lower);
+}
+
+function isStatusFileTarget(targetFile) {
+  return /(?:^|\/)docs\/STATUS\.md$|(?:^|\/)STATUS\.md$/i.test(String(targetFile || ''));
+}
+
+function isDocsTarget(targetFile) {
+  const normalized = String(targetFile || '').replaceAll('\\', '/');
+  return /(?:^|\/)docs\/.+\.md$|(?:^|\/)(?:README|CHANGELOG|AGENTS|CLAUDE|STATUS)\.md$/i.test(normalized);
+}
+
 function shouldUseIndexedContext({ activeSkills = [], targetFile = null } = {}) {
   if (activeSkills.length === 0) {
     return Boolean(targetFile);

package/templates/.claude/skills/docs-quality/SKILL.md

@@ -61,7 +61,7 @@ Docs should **not** become:
 
 - update README / docs after code changes
 - fix source-vs-doc drift
-- improve `docs/PROJECT.md`, `docs/MEMORY.md`, `docs/WORKLOG.md`, `docs/CODE_MAP.md`
+- improve `docs/PROJECT.md`, `docs/MEMORY.md`, `docs/STATUS.md`, `docs/WORKLOG.md`, `docs/CODE_MAP.md`
 - prepare durable handoff notes
 - tighten or remove stale setup instructions
 - document newly discovered module boundaries, dangerous areas, or bug patterns
@@ -97,6 +97,14 @@ Use for durable knowledge:
 
 Prefer short entries that future sessions can scan in seconds.
 
+#### `docs/STATUS.md`
+Use for compact current state:
+- current focus / active work
+- live debug threads, blockers, and verification status
+- next candidates for open-ended continuation
+
+Do **not** treat it as source truth or duplicate full session history here.
+
 #### `docs/WORKLOG.md`
 Use for session-level execution history:
 - what changed

package/templates/.claude/skills/next-step/SKILL.md

@@ -0,0 +1,78 @@
+---
+name: next-step
+description: Use when the user asks what to do next, asks for project status, says continue/làm tiếp without a concrete target, or needs a lightweight session-start orientation from docs/STATUS.md. Do not use as the primary skill for concrete debug, implementation, review, or docs tasks.
+---
+
+# Next Step
+
+## Purpose
+
+Suggest the next useful project action without scanning the whole repository.
+
+This skill is for open-ended continuity prompts such as:
+- "what next?", "project status?", "where are we?"
+- "continue", "continue from last session"
+- "làm gì tiếp?", "làm tiếp", "project đang ở đâu?"
+
+It is **not** a replacement for concrete workflows. If the user names a bug, feature, file, test, PR, or review target, keep the concrete workflow primary and use this skill only as background if useful.
+
+## Hard Guardrails
+
+- End users should not need to know this skill name.
+- Do not ask users to run a `next-step` command. The human workflow remains `ukit install` + natural language.
+- `docs/STATUS.md` is orientation, not truth. Source code, tests, and the UKit index win.
+- Concrete task beats open-ended wording. Example: "I'm fixing login bug but unsure next step" is a debug approach question, not a global roadmap request.
+- Do not scan the whole repo unless `docs/STATUS.md` is missing/stale and the user still wants project-level direction.
+
+## Freshness Check
+
+Before relying on status content, check both:
+1. filesystem modified time for `docs/STATUS.md` (fallback: root `STATUS.md` if present)
+2. the `Last meaningful update` field inside the file
+
+Use this cue in your response:
+
+- 🟢 fresh: modified within 24h
+- 🟡 possibly stale: 24-72h old
+- 🔴 stale: older than 72h
+- ⚪ missing: no status file yet
+
+If stale or missing, downgrade confidence and verify with the smallest current tree/index/context signal before recommending work.
+
+## Input Order
+
+Read only what is needed:
+1. `docs/STATUS.md` (or existing root `STATUS.md` fallback)
+2. `docs/CODE_MAP.md` only when navigation is needed
+3. `docs/MEMORY.md` only when constraints/decisions affect the suggestion
+4. routed index/tree summary only if status is stale, missing, or contradicted
+
+## Output Shape
+
+Keep output compact:
+
+```md
+STATUS freshness: 🟡 possibly stale
+- last modified: YYYY-MM-DD HH:mm
+- confidence: medium-low
+
+Suggested next steps:
+1. Candidate — why now — likely files — verification — risk
+2. Candidate — why now — likely files — verification — risk
+
+Recommended: ...
+Why: ...
+First check: ...
+```
+
+## Intent Handling
+
+- `open-ended-status`: read status and suggest 1-3 candidates.
+- `continue-existing-work`: prefer Active Work / Current Debug Threads, then Next Candidates.
+- `scoped-advice`: do not produce a global roadmap; hand off to the concrete skill and suggest the immediate approach only.
+- `debug-specific`, `implement-specific`, `review-specific`: do not use this skill as primary.
+
+## Missing or Stale Status
+
+If missing, suggest creating/updating `docs/STATUS.md` after the current task, but do not block the user.
+If stale, say so visibly and treat old Next Candidates as hypotheses, not fact.

package/templates/.claude/skills/update-status/SKILL.md

@@ -0,0 +1,88 @@
+---
+name: update-status
+description: Use near the end of a meaningful session or explicit handoff/status request to update docs/STATUS.md with compact current state, verification, blockers, and next candidates. Skip trivial/no-state-change tasks.
+---
+
+# Update Status
+
+## Purpose
+
+Keep `docs/STATUS.md` useful as a compact living state document for future AI sessions.
+
+This skill should run when:
+- the user explicitly asks to update status / handoff / wrap up
+- meaningful source/docs/tests/package state changed
+- a task is paused, blocked, completed, or has a new verified next action
+- a bug root cause, verification result, or durable blocker was discovered
+
+Do **not** run for trivial typo-only edits, pure Q&A, or exploration with no durable finding.
+
+## Hard Guardrails
+
+- End users should not need to know this skill name.
+- Do not ask users to run a `update-status` command. The human workflow remains `ukit install` + natural language.
+- Keep `docs/STATUS.md` compact. It is not `docs/WORKLOG.md` and not a raw session transcript.
+- Source code and tests are truth. If status conflicts with source, update status to match source or mark uncertainty.
+- Do not invent verification. Record only commands actually run and their outcome.
+- Preserve user edits and rewrite the smallest relevant section.
+
+## Update Decision
+
+Before editing, ask internally:
+
+1. Did project state actually change?
+2. Is any work still active/blocked?
+3. Was a root cause, decision, blocker, or next action confirmed?
+4. What verification ran?
+5. Will future sessions be faster if this is recorded?
+
+If all answers are no, skip the update and mention that no status change was needed.
+
+## Freshness Fields
+
+When updating meaningful state, update the header:
+
+```md
+## Freshness
+
+- Last meaningful update: YYYY-MM-DD HH:mm
+- Updated by: Claude / Codex / OpenCode / human
+- Status confidence: high / medium / low
+- Stale after: 72h
+```
+
+Confidence guide:
+- `high`: implementation/fix verified by targeted tests or stronger
+- `medium`: state changed but verification was partial or docs-only
+- `low`: investigation/hypothesis only, blocked, or stale recovery
+
+## Section Rules
+
+- `Snapshot`: only current focus, health, branch/state, release/version.
+- `Active Work`: only live unfinished work.
+- `Current Debug Threads`: compact bug state; detailed context should link to future `docs/context/<slug>.md` files when available.
+- `Decisions Pending`: unresolved choices only.
+- `Next Candidates`: max 3-5 actionable candidates.
+- `Recently Completed`: max 10 compact lines; detailed session history belongs in `docs/WORKLOG.md`.
+
+## What to Record
+
+Prefer concrete bullets:
+
+- files changed or likely involved
+- verification commands and pass/fail/blocked result
+- current blocker
+- next action that can be started immediately
+- uncertainty labels (`unknown`, `unverified`, `suspected`) when needed
+
+Avoid:
+
+- raw command output
+- every file opened/read
+- speculative TODO spam
+- duplicate history already better suited for WORKLOG
+- global roadmap changes caused by a concrete one-file task
+
+## Future Context Note
+
+Do not create task-scoped `CONTEXT.md` as part of v1.1.8 unless the project already has that convention. If detailed bug/feature context is needed, note it as a v1.2 candidate or link to an existing `docs/context/<slug>.md` file.

package/templates/.claude/ukit/index/route-catalog.mjs

@@ -223,8 +223,30 @@ export const ROUTE_CATALOG = [
     path: '.claude/skills/docs-quality/SKILL.md',
     order: 12,
     signals: [
-      { type: 'prompt', regex: /\b(docs|documentation|readme|changelog|handoff|worklog|memory|code map)\b/i, score: 4 },
-      { type: 'file', regex: /\bdocs\/|readme\.md$|project\.md$|memory\.md$|worklog\.md$|code_map\.md$/i, score: 4 },
+      { type: 'prompt', regex: /\b(docs|documentation|readme|changelog|handoff|worklog|memory|code map|status\.md)\b/i, score: 4 },
+      { type: 'file', regex: /\bdocs\/|readme\.md$|project\.md$|memory\.md$|status\.md$|worklog\.md$|code_map\.md$/i, score: 4 },
+    ],
+  },
+  {
+    id: 'next-step',
+    path: '.claude/skills/next-step/SKILL.md',
+    order: 12.1,
+    contextMode: 'standalone',
+    signals: [
+      { type: 'prompt', regex: /\b(what(?:'s| is)? next|next steps?|project status|current status|where are we|continue(?: from)?(?: last session)?|roadmap|status\.md)\b/i, score: 7 },
+      { type: 'prompt', regex: /\b(làm gì tiếp|bước tiếp theo|tiếp theo làm gì|làm tiếp|đang ở đâu|trạng thái project|tình trạng project)\b/i, score: 7 },
+    ],
+  },
+  {
+    id: 'update-status',
+    path: '.claude/skills/update-status/SKILL.md',
+    order: 12.2,
+    contextMode: 'standalone',
+    signals: [
+      { type: 'prompt', regex: /\b(update|refresh|write|sync|record|capture|summari[sz]e).{0,48}\b(status\.md|project status|current state|next candidates?|session state)\b/i, score: 9 },
+      { type: 'prompt', regex: /\b(status\.md|project status).{0,48}\b(update|refresh|write|sync|record|capture|summari[sz]e)\b/i, score: 9 },
+      { type: 'prompt', regex: /\b(wrap up|handoff|end(?:ing)? this session|session summary|before final)\b/i, score: 7 },
+      { type: 'prompt', regex: /\b(cập nhật|ghi lại|tổng kết|chốt session|bàn giao).{0,48}\b(status|trạng thái|việc tiếp theo)\b/i, score: 9 },
     ],
   },
   {

package/templates/.claude/ukit/index/route-task.mjs

@@ -230,11 +230,17 @@ async function prepareTaskRoute({
   const normalizedPrompt = String(promptText || '').trim();
   const normalizedCommand = String(commandText || '').trim();
   const normalizedTarget = normalizeRelativeFile(absoluteRoot, targetFile);
+  const intentMode = deriveIntentMode({
+    promptText: normalizedPrompt,
+    commandText: normalizedCommand,
+    targetFile: normalizedTarget,
+  });
   const activeSkills = await selectActiveSkills({
     rootDir: absoluteRoot,
     promptText: normalizedPrompt,
     commandText: normalizedCommand,
     targetFile: normalizedTarget,
+    intentMode,
   });
   const selectedIds = activeSkills.map((entry) => entry.id);
   const contextIntent = deriveContextIntent({
@@ -262,6 +268,7 @@ async function prepareTaskRoute({
       targetFile: normalizedTarget,
       contextIntent,
       taskType: inferredTaskType,
+      intentMode,
     },
   };
 }
@@ -624,7 +631,7 @@ async function readHelperCacheSnapshot({
   };
 }
 
-async function selectActiveSkills({ rootDir, promptText, commandText, targetFile }) {
+async function selectActiveSkills({ rootDir, promptText, commandText, targetFile, intentMode = null }) {
   const routeSignals = {
     promptRawText: String(promptText || '').toLowerCase(),
     promptNormalizedText: buildNormalizedRouteSignalText(promptText),
@@ -635,6 +642,7 @@ async function selectActiveSkills({ rootDir, promptText, commandText, targetFile
   const scoredEntries = ROUTE_CATALOG
     .map((entry) => scoreSkillRouteEntry(entry, routeSignals))
     .filter((entry) => entry.score > 0)
+    .filter((entry) => shouldKeepRouteEntryForIntent(entry, intentMode))
     .sort((a, b) => b.score - a.score || a.order - b.order);
   const active = [];
 
@@ -650,6 +658,22 @@ async function selectActiveSkills({ rootDir, promptText, commandText, targetFile
   return active.map(({ order, ...rest }) => rest);
 }
 
+function shouldKeepRouteEntryForIntent(entry, intentMode) {
+  if (entry.id === 'next-step' && ['scoped-advice', 'docs-specific'].includes(intentMode)) {
+    return false;
+  }
+
+  if (entry.id === 'update-status' && intentMode === 'docs-specific') {
+    return false;
+  }
+
+  if (entry.id === 'docs-quality' && ['open-ended-status', 'status-update'].includes(intentMode)) {
+    return false;
+  }
+
+  return true;
+}
+
 function scoreSkillRouteEntry(entry, routeSignals = {}) {
   let score = 0;
   const reasons = [];
@@ -718,6 +742,116 @@ function getSignalTexts(signalType, routeSignals = {}) {
   };
 }
 
+function deriveIntentMode({ promptText = '', commandText = '', targetFile = null } = {}) {
+  const lower = buildNormalizedRouteSignalText(promptText, commandText);
+  const raw = `${promptText ?? ''}\n${commandText ?? ''}`.toLowerCase();
+  const docsSpecific = hasDocsSpecificTaskSignal(lower, raw, targetFile);
+  const statusUpdate = hasStatusUpdateSignal(lower, raw);
+  const openEndedStatus = hasOpenEndedStatusSignal(lower, raw);
+  const concreteTask = hasConcreteTaskSignal(lower, raw, targetFile);
+
+  if (docsSpecific) {
+    return 'docs-specific';
+  }
+
+  if (statusUpdate) {
+    return 'status-update';
+  }
+
+  if (concreteTask && openEndedStatus) {
+    return 'scoped-advice';
+  }
+
+  if (openEndedStatus) {
+    return 'open-ended-status';
+  }
+
+  if (concreteTask) {
+    if (/\b(bug|debug|error|crash|broken|failing|stack trace|triage|fix|login|timeout)\b/.test(lower)) {
+      return 'debug-specific';
+    }
+    if (/\b(review|audit|diff|pr feedback|code review|kiem tra|soat)\b/.test(lower)) {
+      return 'review-specific';
+    }
+    if (/\b(implement|build|create|add|ship|deliver|refactor|integrate|integration|scaffold|feature)\b/.test(lower)) {
+      return 'implement-specific';
+    }
+  }
+
+  return null;
+}
+
+function hasStatusUpdateSignal(lower, raw) {
+  return /\b(update|refresh|write|sync|record|capture|summarize|summarise).{0,64}\b(status\.md|project status|current state|next candidates|session state)\b/.test(lower)
+    || /\b(status\.md|project status).{0,64}\b(update|refresh|write|sync|record|capture|summarize|summarise)\b/.test(lower)
+    || /\b(wrap up|handoff|end this session|ending this session|session summary|before final)\b/.test(lower)
+    || /\b(cap nhat|ghi lai|tong ket|chot session|ban giao).{0,64}\b(status|trang thai|viec tiep theo)\b/.test(lower)
+    || /\b(cập nhật|ghi lại|tổng kết|chốt session|bàn giao).{0,64}\b(status|trạng thái|việc tiếp theo)\b/.test(raw);
+}
+
+function hasOpenEndedStatusSignal(lower, raw) {
+  return /\b(what next|what is next|what's next|next step|next steps|project status|current status|where are we|continue|continue from last session|roadmap|status\.md)\b/.test(lower)
+    || /\b(lam gi tiep|buoc tiep theo|tiep theo lam gi|lam tiep|dang o dau|trang thai project|tinh trang project)\b/.test(lower)
+    || /\b(làm gì tiếp|bước tiếp theo|tiếp theo làm gì|làm tiếp|đang ở đâu|trạng thái project|tình trạng project)\b/.test(raw);
+}
+
+function hasConcreteTaskSignal(lower, raw, targetFile) {
+  if (targetFile && !isStatusFileTarget(targetFile)) {
+    return true;
+  }
+
+  return /\b(bug|debug|error|crash|broken|failing|stack trace|triage|fix|implement|build|create|add|ship|deliver|refactor|integrate|integration|scaffold|feature|review|audit|diff|pr feedback|code review|auth|login|api|endpoint|test|spec)\b/.test(lower)
+    || /\b(sửa|fix|lỗi|bug|debug|implement|cài|thêm|review|kiểm tra|soát|đăng nhập)\b/.test(raw);
+}
+
+function hasDocsSpecificTaskSignal(lower, raw, targetFile) {
+  if (!targetFile || !isDocsTarget(targetFile)) {
+    return false;
+  }
+
+  const targetName = path.posix.basename(String(targetFile || '').replaceAll('\\', '/')).toLowerCase();
+  const explicitStatusUpdate = hasExplicitStatusUpdateSignal(lower, raw);
+
+  if (!isStatusFileTarget(targetFile)) {
+    if (explicitStatusUpdate && !mentionsTargetDoc(lower, targetName)) {
+      return false;
+    }
+
+    return mentionsTargetDoc(lower, targetName)
+      || /\b(edit|write|improve|document|docs?|readme|changelog|worklog|memory|code map|template|wording|copy|grammar|format|structure|heading|section|handoff notes?)\b/.test(lower)
+      || /\b(câu chữ|chỉnh|sửa chữ|ngữ pháp|định dạng|cấu trúc|tài liệu|ghi chú bàn giao)\b/.test(raw);
+  }
+
+  return /\b(template|wording|edit|copy|grammar|format|structure|heading|section|docs?)\b/.test(lower)
+    || /\b(mẫu|câu chữ|chỉnh|sửa chữ|ngữ pháp|định dạng|cấu trúc|tài liệu)\b/.test(raw);
+}
+
+function hasExplicitStatusUpdateSignal(lower, raw) {
+  return /\b(update|refresh|write|sync|record|capture|summarize|summarise).{0,64}\b(status\.md|project status|current state|next candidates|session state)\b/.test(lower)
+    || /\b(status\.md|project status).{0,64}\b(update|refresh|write|sync|record|capture|summarize|summarise)\b/.test(lower)
+    || /\b(cap nhat|ghi lai|tong ket|chot session|ban giao).{0,64}\b(status|trang thai|viec tiep theo)\b/.test(lower)
+    || /\b(cập nhật|ghi lại|tổng kết|chốt session|bàn giao).{0,64}\b(status|trạng thái|việc tiếp theo)\b/.test(raw);
+}
+
+function mentionsTargetDoc(lower, targetName) {
+  if (!targetName) {
+    return false;
+  }
+
+  const escaped = targetName.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
+  const withoutExt = escaped.replace(/\\\.md$/i, '');
+  return new RegExp(`\\b(?:${escaped}|${withoutExt})\\b`, 'i').test(lower);
+}
+
+function isStatusFileTarget(targetFile) {
+  return /(?:^|\/)docs\/STATUS\.md$|(?:^|\/)STATUS\.md$/i.test(String(targetFile || ''));
+}
+
+function isDocsTarget(targetFile) {
+  const normalized = String(targetFile || '').replaceAll('\\', '/');
+  return /(?:^|\/)docs\/.+\.md$|(?:^|\/)(?:README|CHANGELOG|AGENTS|CLAUDE|STATUS)\.md$/i.test(normalized);
+}
+
 function shouldUseIndexedContext({ activeSkills = [], targetFile = null } = {}) {
   if (activeSkills.length === 0) {
     return Boolean(targetFile);
@@ -1063,6 +1197,7 @@ function buildRouteSummary({
     fallbackCommands,
     preferredOrder,
     policyMode,
+    intentMode: routingContext.intentMode ?? null,
     delegateHint: delegationRecommendation?.hint ?? null,
     nextActionType: nextAction?.type ?? null,
     nextActionCommand,
@@ -1580,6 +1715,7 @@ function compactRoutingContext(routingContext = {}) {
     adapter: routingContext.adapter ?? 'claude',
     lastExplicitUserPromptText: routingContext.lastExplicitUserPromptText ?? '',
     taskType: routingContext.taskType ?? null,
+    intentMode: routingContext.intentMode ?? null,
   };
 }
 

package/templates/.codex/README.md

@@ -12,7 +12,7 @@ Auto-generated by UKit for OpenAI Codex.
 - Do not make end users memorize skill names, helper scripts, or routing internals unless they are debugging UKit itself.
 - **Treat helper commands as internal orchestration. Do not ask end users to run them.**
 
-## UKit v1.1.7 Shared Runtime
+## UKit v1.1.8 Shared Runtime
 
 - Shared runtime state lives in `.ukit/storage/`.
 - Treat `.ukit/storage/config.json` as the source of compact, token-pipeline, router, memory, and validation toggles.
@@ -29,6 +29,7 @@ Auto-generated by UKit for OpenAI Codex.
 - **Trivial**: no docs.
 - **Simple**: `docs/MEMORY.md` only.
 - **Non-trivial**: `docs/MEMORY.md` + `docs/PROJECT.md` + `docs/CODE_MAP.md`.
+- `docs/STATUS.md`: read for open-ended status/continue prompts or meaningful continuation context; stale status is orientation only.
 - Read `docs/WORKLOG.md` only when recent continuation/debug context matters.
 - Source is truth; if docs are stale, update docs and continue.
 
@@ -52,6 +53,9 @@ For clearly non-code specialist lanes, avoid dragging the source-code index into
 - Match from prompt wording plus tool/file evidence.
 - Use the smallest useful set, usually 1-2 skills.
 - If docs work is detected, prefer `.codex/skills/docs-quality/SKILL.md`.
+- For open-ended “what next?” / “continue” / project-status prompts, prefer `.codex/skills/next-step/SKILL.md` and show a status freshness cue.
+- For explicit handoff/wrap-up/status updates, prefer `.codex/skills/update-status/SKILL.md`.
+- Concrete debug/implementation/review prompts beat open-ended wording; do not let `next-step` replace the concrete workflow.
 - If routing is complex or ambiguous, prefer `node .codex/ukit/index/route-task.mjs "<prompt>" [--tool-command <cmd>] [--target <file>]`.
 - That helper should keep shared route memory in `.claude/ukit/skill-router-state.json` so Claude and Codex continue from the same compact route state.
 - When route memory already includes `previous-context` or `recent-output`, reuse it before widening reads or logs.
@@ -68,6 +72,7 @@ For clearly non-code specialist lanes, avoid dragging the source-code index into
 ## Docs Discipline
 
 After significant work, update only what changed:
+- `docs/STATUS.md` — compact current state, blockers, verification, next candidates
 - `docs/WORKLOG.md`
 - `docs/MEMORY.md`
 - `docs/CODE_MAP.md`

package/templates/.codex/settings.json

@@ -65,6 +65,12 @@
       ],
       "maintenance": [
         "repo-maintenance"
+      ],
+      "nextStep": [
+        "next-step"
+      ],
+      "statusUpdate": [
+        "update-status"
       ]
     },
     "toolSignals": {
@@ -89,7 +95,8 @@
     },
     "routingRule": {
       "endUserShouldNotNeedSkillNames": true,
-      "selectSmallestUsefulSkillSet": true
+      "selectSmallestUsefulSkillSet": true,
+      "concreteTaskBeatsOpenEndedStatus": true
     },
     "delegationBridge": {
       "enabled": true,

package/templates/AGENTS.md

@@ -31,6 +31,8 @@
 - bug / error / crash / triage / failing path → `.claude/skills/debugging-toolkit/SKILL.md`
 - test / spec / coverage / fixture → `.claude/skills/testing-quality/SKILL.md`
 - docs / README / changelog / handoff / editing `docs/` → `.claude/skills/docs-quality/SKILL.md`
+- open-ended next step / project status / continue with no concrete target → `.claude/skills/next-step/SKILL.md`
+- explicit handoff / wrap up / update `docs/STATUS.md` → `.claude/skills/update-status/SKILL.md`
 - auth / security / token / permission / validation / risky shell-path-delete-db work → `.claude/skills/discover-security/SKILL.md`
 - stale workspace / reinstall / cleanup / maintenance → `.claude/skills/repo-maintenance/SKILL.md`
 
@@ -41,7 +43,7 @@
 - If a concrete verification lane is needed, prefer `node .claude/ukit/index/verify-context.mjs ...`.
 - These helper/index commands are internal orchestration. Run them yourself when needed; never turn them into required end-user workflow.
 
-## UKit v1.1.7 Shared Runtime
+## UKit v1.1.8 Shared Runtime
 
 - Shared runtime state lives in `.ukit/storage/`.
 - Treat `.ukit/storage/config.json` as the source of runtime toggles for compact, token pipeline, router, memory, and validation behavior.
@@ -59,9 +61,18 @@
 - **Trivial**: no docs, no index query unless the file target is unclear.
 - **Simple**: default to `docs/MEMORY.md` only; pull related files/tests with the resolver.
 - **Non-trivial**: read `docs/MEMORY.md` + `docs/PROJECT.md` + `docs/CODE_MAP.md`.
+- `docs/STATUS.md`: read for open-ended status/continue prompts or meaningful continuation context; treat stale status as orientation only and verify against source/index.
 - `docs/WORKLOG.md`: only recent, relevant entries for continuation/debugging.
 - Follow routed verification policy: targeted first when localized, widen in order for shared/risky scope, ask before blanket broad runs when no related-test evidence exists.
 
+## Living Status Workflow
+
+- `docs/STATUS.md` is compact current state, not a transcript and not source truth.
+- When the user asks “what next?”, “continue”, or “project đang ở đâu?” without a concrete target, use the `next-step` skill and show a freshness cue (fresh / possibly stale / stale / missing).
+- Concrete debug/implementation/review prompts beat open-ended wording; use the concrete skill first and only use status as background.
+- After meaningful work, use `update-status` to record state, verification, blockers, and next candidates; skip trivial/no-state-change tasks.
+- Detailed task context files such as `docs/context/<slug>.md` are a future extension, not required baseline workflow.
+
 ## Subagent Policy (internal only)
 
 - Default to direct execution for trivial/simple work.

package/templates/CLAUDE.md

@@ -29,6 +29,8 @@
 - bug / error / crash / triage → `.claude/skills/debugging-toolkit/SKILL.md`
 - test / spec / coverage → `.claude/skills/testing-quality/SKILL.md`
 - docs / README / changelog / handoff / editing `docs/` → `.claude/skills/docs-quality/SKILL.md`
+- open-ended next step / project status / continue with no concrete target → `.claude/skills/next-step/SKILL.md`
+- explicit handoff / wrap up / update `docs/STATUS.md` → `.claude/skills/update-status/SKILL.md`
 - auth / security / token / permission / validation → `.claude/skills/discover-security/SKILL.md`
 - stale workspace / reinstall / cleanup → `.claude/skills/repo-maintenance/SKILL.md`
 
@@ -40,7 +42,7 @@
 - **Do not ask normal contributors to run internal helper commands**; run them yourself or tell them to rerun `ukit install`.
 - Do not ask normal contributors to memorize `ukit doctor`, `ukit diff`, `ukit uninstall`, or `ukit index ...` unless they explicitly need maintainer/debug help.
 
-## UKit v1.1.7 Shared Runtime
+## UKit v1.1.8 Shared Runtime
 
 - Shared runtime state lives in `.ukit/storage/`.
 - Treat `.ukit/storage/config.json` as the source of runtime toggles for compact, token pipeline, router, memory, and validation behavior.
@@ -56,9 +58,18 @@
 - **Trivial**: no docs.
 - **Simple**: `docs/MEMORY.md` only, plus resolver-selected files/tests.
 - **Non-trivial**: `docs/MEMORY.md` + `docs/PROJECT.md` + `docs/CODE_MAP.md`.
+- `docs/STATUS.md`: use for open-ended status/continue prompts or meaningful continuation context; stale status is orientation only.
 - `docs/WORKLOG.md`: only recent relevant entries.
 - Follow routed verification policy: targeted first, widen only when risk/shared scope justifies it, ask before blanket broad runs.
 
+## Living Status Workflow
+
+- `docs/STATUS.md` captures compact current state, active work, debug threads, blockers, verification, and next candidates.
+- It is not source truth and must not replace source/index-first investigation.
+- For “what next?” / “continue” prompts without a concrete target, use `next-step` and show a freshness cue before relying on the status file.
+- For concrete debug/implementation/review prompts, keep the concrete workflow primary even if the user asks for an approach or next step.
+- After meaningful work, use `update-status`; skip trivial/no-state-change tasks and avoid transcript-style noise.
+
 ## Selective Subagent Policy (internal only)
 
 - Keep direct execution as the default for trivial/simple work.

package/templates/docs/INSTALL.md

@@ -47,6 +47,7 @@ End users do not need to manage any of that manually.
 Complete these files before first serious use:
 - `docs/PROJECT.md`
 - `docs/MEMORY.md`
+- `docs/STATUS.md`
 - `docs/WORKLOG.md`
 
 ### 4) Open your AI tool
@@ -96,6 +97,7 @@ ukit install
 Check that the docs baseline files exist and are filled in:
 - `docs/PROJECT.md`
 - `docs/MEMORY.md`
+- `docs/STATUS.md`
 - `docs/WORKLOG.md`
 
 ---

package/templates/docs/PROJECT.md

@@ -44,7 +44,8 @@
 
 1. Run `ukit memory recall "<current task>"` for non-trivial work; reuse relevant `## Previous Context` before asking the user to restate prior decisions
 2. Read `docs/MEMORY.md` — architecture decisions, active constraints, known bugs
-3. Read `docs/CODE_MAP.md` if it exists — structural navigation index
-4. Use the installed source-code index / routed helpers to localize the smallest relevant file + test set first
-5. Scan recent `docs/WORKLOG.md` entries if continuing prior work
-6. Verify understanding against source before acting — **docs orient, source is truth; keep the index-first workflow intact**
+3. Read `docs/STATUS.md` for open-ended status/continue prompts or meaningful continuation context; treat stale status as orientation only
+4. Read `docs/CODE_MAP.md` if it exists — structural navigation index
+5. Use the installed source-code index / routed helpers to localize the smallest relevant file + test set first
+6. Scan recent `docs/WORKLOG.md` entries if continuing prior work
+7. Verify understanding against source before acting — **docs orient, source is truth; keep the index-first workflow intact**

package/templates/docs/STATUS.md

@@ -0,0 +1,81 @@
+# Project Status — {{project.name}}
+
+> Living project state for AI sessions.
+> Keep this compact: current state only, not a session transcript.
+> Source code, tests, and the UKit index remain ground truth.
+
+## Freshness
+
+- Last meaningful update: TODO YYYY-MM-DD HH:mm
+- Updated by: TODO
+- Status confidence: low
+- Stale after: 72h
+
+If this file is stale, AI must treat it as orientation only and verify against source/index before recommending or editing.
+
+## Snapshot
+
+- Current focus: TODO
+- Health: unknown
+- Branch/state: TODO
+- Release/version: TODO
+
+## Active Work
+
+<!-- Keep only live work. Move finished work to Recently Completed or WORKLOG.md. -->
+
+### TODO work item
+
+- Status: planned / in-progress / blocked / done
+- Goal: TODO
+- Done: TODO
+- Remaining: TODO
+- Files involved: TODO
+- Verification: TODO
+- Next action: TODO
+
+## Current Debug Threads
+
+<!-- Detailed bug context belongs in docs/context/<task>.md when that exists. STATUS should only link/summarize. -->
+
+### TODO debug thread
+
+- Status: investigating / root cause found / fixed / blocked
+- Symptom: TODO
+- Root cause: unknown
+- Evidence: TODO
+- Changed files: TODO
+- Verification: TODO
+- Remaining risk: TODO
+- Next action: TODO
+
+## Decisions Pending
+
+- [ ] TODO decision
+  - Context: TODO
+  - Options: TODO
+  - Recommended: TODO
+
+## Next Candidates
+
+1. TODO candidate
+   - Why now: TODO
+   - Expected files: TODO
+   - Verification: TODO
+   - Risk: TODO
+
+## Recently Completed
+
+<!-- Max 10 compact lines. Use docs/WORKLOG.md for session history. -->
+
+- TODO YYYY-MM-DD — summary — verification
+
+## Notes for Next AI Session
+
+- Read first: docs/STATUS.md, then docs/CODE_MAP.md only if navigation is needed.
+- Avoid: treating this file as source truth when it is stale or contradicted by code/tests.
+- Known traps: keep concrete debug/implementation prompts on their specific workflow; do not turn them into global roadmap suggestions.
+
+## Future Candidate: Task Context Files
+
+v1.2 candidate: task-scoped `docs/context/<slug>.md` files for granular bug/feature context. Keep this out of v1.1.8 scope unless a project already uses that folder.

package/templates/docs/UKIT_USAGE_GUIDE.md

@@ -14,6 +14,7 @@ UKit should handle:
 - hidden skill selection
 - source-code indexing
 - compact context selection
+- living project status for open-ended continuation prompts
 - targeted verification
 - optional internal delegation when it is actually useful
 
@@ -127,6 +128,21 @@ Expected UKit behavior:
 2. use DuraOne references only when the repo actually matches that domain/shape
 3. keep the user away from manual skill selection
 
+### F) Continue / what next
+
+User says:
+
+```text
+Project đang ở đâu, làm gì tiếp?
+```
+
+Expected UKit behavior:
+1. auto-load the hidden next-step lane
+2. read `docs/STATUS.md` first and show whether it is fresh, possibly stale, stale, or missing
+3. suggest only a few actionable next candidates
+4. if status is stale, verify with source/index before treating any candidate as authoritative
+5. if the prompt names a concrete bug/feature/review target, keep the concrete workflow primary instead of producing a global roadmap
+
 ---
 
 ## What users should NOT need to do

package/templates/ukit/README.md

@@ -1,6 +1,6 @@
 # UKit Shared Runtime
 
-This folder stores shared UKit runtime state for v1.1.7 features.
+This folder stores shared UKit runtime state for v1.1.8 features.
 
 - `storage/config.json` — runtime feature flags and defaults
 - `storage/cache/` — prompt-cache, compact history, compact pressure state, output summaries, and preserved raw tool outputs under `storage/cache/tee/`

package/templates/ukit/storage/config.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.1.7",
+  "version": "1.1.8",
   "agent": "claude-code",
   "compact": {
     "enabled": true,