chore: sync private v5.0.0 (a14d3cd)

.cursor-plugin/plugin.json

@@ -1,7 +1,9 @@
 {
   "name": "agent-kit",
   "displayName": "Agent Kit",
-  "author": "agent-kit-startup",
+  "author": {
+    "name": "agent-kit-startup"
+  },
   "description": "HITL framework for AI-assisted IDEs — plan, handoff, staging→prod, memory loop, anti-slop. Stack skills via agent-kit add.",
   "keywords": [
     "agents",
@@ -12,7 +14,14 @@
     "multi-ide",
     "anti-slop"
   ],
-  "license": "MIT",
-  "version": "4.8.9",
-  "repository": "https://github.com/agent-kit-startup/agent-kit"
+  "license": "PolyForm-Noncommercial-1.0.0",
+  "version": "5.0.0",
+  "homepage": "https://github.com/agent-kit-startup/agent-kit",
+  "repository": "https://github.com/agent-kit-startup/agent-kit",
+  "logo": "dashboard/logo.svg",
+  "rules": ".cursor/rules",
+  "skills": ".cursor/skills/core",
+  "agents": ".cursor/agents",
+  "commands": ".cursor/commands",
+  "hooks": ".cursor/hooks.json"
 }

.cursor/agent-kit.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "version": "4.8.9",
+  "version": "5.0.0",
   "protected": [
     ".cursor/HANDOFF.md",
     ".cursor/agents/test-suites.md",

.cursor/commands/agent-kit-onboard.md

@@ -1,3 +1,8 @@
+---
+name: agent-kit-onboard
+description: Prepare and validate repository readiness before /start-project.
+---
+
 # Command: /agent-kit-onboard
 
 ## Goal
@@ -96,10 +101,25 @@ When complete:
 3. Verify each remaining non-essential check is ready or explicitly deferred with both a reason and recovery action. Reject deferral for any check with `status: "blocked"`.
 4. If verification fails, leave `onboarding.status: "in_progress"` and `onboarded` unchanged, then resume the first unresolved essential check derived from `pillars[].checks[]`.
 5. Only after verification passes, merge `onboarding.status: "completed"` and `onboarded: true` into `.cursor/context/config.json` without removing other keys.
-6. End with exactly one call to action:
+6. **Domain-skills scaffold (optional HITL).** Before showing the final finish-setup CTA, run the scaffold gate:
+   - Read `.cursor/context/personalization.json` and `.cursor/agent-kit.config.json` to reuse install-time evidence. Do not invent a second detector.
+   - Build a short proposal from the already-applied L2 skills and L1 packs in personalization, plus any project-owned domain skills implied by the profile but not yet installed.
+   - Ask one question using **Ask questions** with concrete options:
+
+     > "Essentials are ready. Before finish setup, scaffold domain skills from the detected profile?"
+
+     Options: `Scaffold domain skills` / `Defer (record reason)` / `Skip`
+
+   - **Fallback when Ask questions is unavailable:** present the same options as a numbered list, ask the user to reply with the number or the label, and note they can always **type their own answer** if none of the options fit (equivalent of the built-in "Other" choice).
+   - **Scaffold domain skills:** show the proposal list, then write any accepted project-owned skills under `.cursor/skills/domain/<skill-id>/SKILL.md` only when the path does not already exist. Update the **Relevant skills** section of `.cursor/project-context.md` (create the heading if missing) with installed and newly accepted skill ids plus evidence; also ensure those ids appear under `.cursor/agent-kit.json` `skills[]` when that manifest is the project's install index. Record `onboarding.domainSkills` in `.cursor/context/config.json` with `status: "applied"`, the list of accepted items, and `appliedAt`.
+   - **Defer:** ask for a short reason, then record `onboarding.domainSkills` with `status: "deferred"`, `reason`, and `recoveryCommand: "/agent-kit-onboard"`.
+   - **Skip:** record `onboarding.domainSkills` with `status: "skipped"`.
+   - Never overwrite an existing project-owned skill or file without a separate HITL confirmation. This closes the gap reported in public issue https://github.com/agent-kit-startup/agent-kit/issues/36 and the dogfood note `dogfood/cursor_onboard_should_scaffold_domain_skills_2026_08_01.md`.
+   - **Instruction-only surface:** this gate is chat/`/agent-kit-onboard` prose executed by the agent session. There is no separate CLI subcommand that scaffolds domain skills; intentionally document defer/skip when the operator declines. Project-owned skills under `.cursor/skills/domain/` are one-way (not contributeable via `guessRegistryPath` / registry paths `core` and `community` only).
+7. End with exactly one call to action:
    - `Next: /start-project` when the user wants to plan a deliverable.
    - `Next: finish setup` when no deliverable should start now.
 
-After essentials are ready, Mission Control is **optional** and **not** an essential readiness check. Consumer L0 installs the `/dashboard` command text but not `dashboard/**`. If the operator wants the panel, `agent-kit dashboard` serves it from the installed CLI (4.8.2 onward); on older pins point them to an agent-kit checkout that includes `dashboard/start.mjs` (loopback `http://127.0.0.1:3333`). Do not block `/start-project` on Mission Control. Do not ask about skins or external review before essentials (Hard Stop 1).
+After essentials are ready, `/agent-kit-onboard` offers one optional HITL gate: a **domain-skills scaffold** derived from the install-time personalization/doctor evidence. This gate is not a readiness blocker; deferring or skipping it must still allow `/start-project` to proceed. Mission Control is also **optional** and **not** an essential readiness check. Consumer L0 installs the `/dashboard` command text but not `dashboard/**`. If the operator wants the panel, `agent-kit dashboard` serves it from the installed CLI (4.8.2 onward); on older pins point them to an agent-kit checkout that includes `dashboard/start.mjs` (loopback `http://127.0.0.1:3333`). Do not block `/start-project` on Mission Control or on the domain-skills scaffold. Do not ask about skins or external review before essentials (Hard Stop 1).
 
 Agent Personas remain available through later personalization or settings. External review is offered only when a plan reaches exhaustion.

.cursor/commands/archive-plan.md

@@ -1,3 +1,8 @@
+---
+name: archive-plan
+description: Archive a parked plan: drop it from the HANDOFF parked list and move the file into .cursor/plans/archive/.
+---
+
 # Command: /archive-plan
 
 ## Goal

.cursor/commands/backlog-add.md

@@ -1,3 +1,8 @@
+---
+name: backlog-add
+description: Enqueue a new plan with to-dos under the HANDOFF Backlog without activating it.
+---
+
 # Command: /backlog-add
 
 ## Goal
@@ -47,6 +52,7 @@ Before enqueueing a new plan, **scan** these sources (read/skim; do not deep-div
 | **Archived context** | Prior packs for same theme | `.cursor/context/archive/**` (if present; glob by topic) |
 | **Decisions** | ADRs that constrain the goal | `.cursor/memory/decisions/`, `_index.md` Decisions table |
 | **Memory** | Errors, audits, consolidations, review logs, plan-monitors, findings audits | `.cursor/memory/errors/`, `.cursor/memory/plan-monitor-*.md`, theme-matched `plan-review-*.md`, `_index.md` (Audits + Decisions) |
+| **Unprocessed dogfood** | Factory/consumer inbox notes awaiting triage (not sessionStart-only) | `dogfood/README.md` or `.cursor/dogfood/README.md` under `##` or `### Unprocessed Files`; skim titles/summaries only. Missing/empty inbox → no findings. Labels: ignore (owned by open plan), error/include (kit gap), note (inbox evidence only). Never auto-analyze or memory WRITE (ADR `decisions/2026-08-11_dogfood-unprocessed-broad-intake-bucket.md`) |
 | **Local docs** | SoT / inventories / getting-started that the goal touches | `docs/**`, especially files named in the payload or related SoT |
 | **Working tree** | Uncommitted local work that would collide | `git status`, `git diff` (staged + unstaged); do not commit |
 | **Recent commits** | What already shipped for this theme | `git log` (short, recent), related PR titles if available |
@@ -66,8 +72,8 @@ The actual scanning and triage is delegated to a **Task(explore) subagent** usin
 1. **Fill the template** — set these parameters:
    - **Repo:** `[absolute repo path]`
    - **Command:** `/backlog-add`
-   - **Task description:** "Scan the 9 Broad Intake buckets (prepared repository, active session, plans, archived context, decisions, memory, local docs, working tree, recent commits, product version) and return a structured triage report with findings per bucket, each labeled ignore/error/include/note."
-   - **read_scope:** `[".cursor/agent-kit.config.json", ".cursor/context/readiness.json", ".cursor/HANDOFF.md", ".cursor/context/current/", ".cursor/plans/*.plan.md", ".cursor/context/archive/**", ".cursor/memory/decisions/", ".cursor/memory/errors/", ".cursor/memory/plan-monitor-*.md", ".cursor/memory/plan-review-*.md", ".cursor/memory/_index.md", "docs/**", "package.json", "CHANGELOG.md"]`
+   - **Task description:** "Scan the Broad Intake buckets listed in this command (prepared repository, active session, plans, archived context, decisions, memory, Unprocessed dogfood, local docs, working tree, recent commits, product version) and return a structured triage report with findings per bucket, each labeled ignore/error/include/note. For Unprocessed dogfood: skim `dogfood/README.md` or `.cursor/dogfood/README.md` `##` or `### Unprocessed Files` only; never auto-analyze."
+   - **read_scope:** `[".cursor/agent-kit.config.json", ".cursor/context/readiness.json", ".cursor/HANDOFF.md", ".cursor/context/current/", ".cursor/plans/*.plan.md", ".cursor/context/archive/**", ".cursor/memory/decisions/", ".cursor/memory/errors/", ".cursor/memory/plan-monitor-*.md", ".cursor/memory/plan-review-*.md", ".cursor/memory/_index.md", "dogfood/README.md", ".cursor/dogfood/README.md", "docs/**", "package.json", "CHANGELOG.md"]`
    - **worker_contract:** "structured triage report: list of findings per bucket with triage labels (ignore/error/include/note)"
    - **max_ticks:** 2
 

.cursor/commands/backlog-cancel.md

@@ -1,3 +1,8 @@
+---
+name: backlog-cancel
+description: Soft-cancel a backlog plan: mark open to-dos cancelled and drop it from the Backlog, keeping the file.
+---
+
 # Command: /backlog-cancel
 
 ## Goal

.cursor/commands/backlog-delete.md

@@ -1,3 +1,8 @@
+---
+name: backlog-delete
+description: Remove a plan from the HANDOFF Backlog and move the file to .cursor/plans/archive/.
+---
+
 # Command: /backlog-delete
 
 ## Goal

.cursor/commands/backlog-edit.md

@@ -1,3 +1,8 @@
+---
+name: backlog-edit
+description: Edit an existing plan body or frontmatter to-dos without activating it.
+---
+
 # Command: /backlog-edit
 
 ## Goal

.cursor/commands/context-status.md

@@ -1,3 +1,8 @@
+---
+name: context-status
+description: Show the current context state: active task, handoff, archived tasks.
+---
+
 # Command: /context-status
 
 ## Goal

.cursor/commands/continue-plan.md

@@ -1,3 +1,8 @@
+---
+name: continue-plan
+description: Resume a plan from the last handoff and execute only the next unit.
+---
+
 # Command: /continue-plan
 
 ## Goal
@@ -14,10 +19,11 @@ Resume a plan from the last handoff. Confirm the next unit, then execute **only
 1. **Read `.cursor/HANDOFF.md` first.** No handoff → say so and suggest `/start-project`. Do not invent progress.
 2. **Pre-flight (API/usage limit):** if `- **Mode:**`, `- **Gaps:**`, or `- **Instruction for the next agent:**` still records an API/usage limit hard stop from a prior tick, **do not** mark a to-do `in_progress`, dispatch a Task, or edit product files until the operator confirms recovery (switch from Auto to a named model such as Claude Opus, Sonnet 4.6, or Composer 2.5 Fast; and/or wait for quota reset). Surface recovery via **Ask questions** when available. **Fallback after Auto→Grok:** Grok 4.5 and Auto often lack Ask questions (see `.cursor/memory/decisions/2026-07-20_ask-questions-model-availability.md`); use the numbered-list chat fallback (reply by number or label; typed answer = "Other"). Pre-flight is HANDOFF check plus operator model choice only; the kit has no remaining-quota API. Align with `context-guardian` Quota-blocked sessions and `/run-plan` Read-state pre-flight.
 3. **Audits pre-flight** (config `externalPlanReview.preflight`: `off` | `warn` | `block`; missing = `off`): before the next-unit confirmation Ask, check owed / untriaged audits for the chosen plan slug (Field Report owed, untriaged `plan-monitor-*.md`, open cadence WARNING). `off`: skip. `warn`: surface once, then continue. `block`: arm via `.cursor/scripts/plan-external-review.sh` (prefer `--autonomous` when `mode: autonomous`, else `--paste-only`) or stop until the operator defers; never steal `/git-prod`. Distinct from the advisory pre-unit monitor skim below (ADR `2026-07-27_audits-autonomous-plan-review-contract.md`).
-4. **Apply Agent Persona chrome.** Read `.cursor/context/config.json` for `agentPersona.modes.continue-plan` (fallback to legacy `workspaceSkin`, then "autopilot"). Use the corresponding persona's `chatHints` from `registry/personas/core/` for tone and confirmations.
-5. **Confirm the next unit with Ask questions** before editing. Use concrete option labels (see What to Do step 5). Do not accept a typed "yes" as the gate.
-6. **One unit per chat** (phase or one heavy to-do) unless the user explicitly ran `/run-plan`.
-7. **Do not start a competing plan.** New goal requires `/start-project`, which parks the active plan and proceeds to create a new one.
+4. **Unprocessed dogfood preflight (advisory):** before the next-unit confirmation Ask, skim `##` or `### Unprocessed Files` in factory `dogfood/README.md` or consumer `.cursor/dogfood/README.md`. Non-empty: mention count and top titles once with standard triage labels (`ignore` / `error` / `include` / `note`). Empty or missing inbox: silent OK. Do **not** force analysis, memory WRITE, or Field Reports; do **not** block resume solely because the inbox is non-empty. Runs regardless of `externalPlanReview.preflight`. sessionStart inbox tip stays complementary (ADR `2026-08-11_dogfood-unprocessed-broad-intake-bucket.md`).
+5. **Apply Agent Persona chrome.** Read `.cursor/context/config.json` for `agentPersona.modes.continue-plan` (fallback to legacy `workspaceSkin`, then "autopilot"). Use the corresponding persona's `chatHints` from `registry/personas/core/` for tone and confirmations.
+6. **Confirm the next unit with Ask questions** before editing. Use concrete option labels (see What to Do step 5). Do not accept a typed "yes" as the gate.
+7. **One unit per chat** (phase or one heavy to-do) unless the user explicitly ran `/run-plan`.
+8. **Do not start a competing plan.** New goal requires `/start-project`, which parks the active plan and proceeds to create a new one.
 
 ## What to Do
 

.cursor/commands/cursor-update-awareness.md

@@ -1,3 +1,8 @@
+---
+name: cursor-update-awareness
+description: Run an opt-in advisory check for Cursor product updates against the native audit inventory.
+---
+
 # Command: /cursor-update-awareness
 
 ## Goal
@@ -23,11 +28,12 @@ Run an **opt-in advisory** check for Cursor product updates (changelog + `docs/c
 ## Check-only (CLI)
 
 ```bash
-agent-kit cursor-awareness --check [--json] [--respect-prefs] [--stamp] [--offline]
+agent-kit cursor-awareness --check [--cwd <path>] [--json] [--respect-prefs] [--stamp] [--offline]
 ```
 
 - Fetches `https://cursor.com/changelog` (override via `cursorUpdateCheck.changelogUrl`) unless `--offline`.
-- Diffs against `docs/cursor-native-audit.md` (open Action items, refresh staleness) and validates `docs/cursor-3-features.md` presence.
+- Resolves `docs/cursor-native-audit.md` by walking up from `--cwd` (default `process.cwd()`); errors with a `--cwd` hint when no ancestor has the inventory.
+- Diffs against that inventory (open Action items, refresh staleness) and validates `docs/cursor-3-features.md` under the same root.
 - Prefs in `.cursor/context/config.json` under `cursorUpdateCheck` (`enabled` default `false`, `intervalDays`, `lastSeenCursorVersion`). Distinct from kit `updateCheck`.
 - `applyRecommended` and `fieldReportRecommended` are always `false`.