@aitne-sh/aitne 0.1.8 → 0.1.9

package/agent-assets/task-flows/scheduled.dm.md

@@ -272,7 +272,7 @@ voice carries the whole message.
 - Tasks list: cap 10, append `...and N more` if over.
 - Overnight: cap 5 per category (mail / dm / calendar).
 - No internal names ("Morning Routine", "Agent Plan",
-  "scheduled.dm", "today.md") in user-facing text.
+  "scheduled.dm", "state/today.md") in user-facing text.
 - Forbidden openers across all variants: "Morning briefing —",
   "Morning briefing delivered", "Here's your day".
 
@@ -305,7 +305,7 @@ occurring outgoing-DM opportunities to slip a question in without it
 feeling cold. Use the **user-interview** skill's "Operation 3 — Latent
 piggyback" recipe:
 
-1. GET `agent/profile-questions.md` ## In Progress. If no entry has
+1. GET `state/profile-questions.md` ## In Progress. If no entry has
    `state=latent`, skip this section entirely.
 1.5 **Slot-filled pre-check.** GET
    `/api/profile-questions/slot-filled?path=<target>&section=<section?>&anchor=<anchor?>`.
@@ -352,7 +352,7 @@ recipe:
 
 ### Step 1 — Fire-time abort (Layer 3)
 
-GET `agent/profile-questions.md` and the row's `<target_path>`. Call:
+GET `state/profile-questions.md` and the row's `<target_path>`. Call:
 
 ```bash
 curl -s "http://localhost:8321/api/profile-questions/slot-filled?path=<target>&section=<section?>&anchor=<anchor?>"
@@ -623,12 +623,12 @@ handled in one read-then-branch sequence:
    ```
 
    `<confirm_decline_marker.path>` is the value from `taskContext`
-   (e.g. `agent/journal.md`). The endpoint accepts the path with or
+   (e.g. `journal/agent.md`). The endpoint accepts the path with or
    without the `.md` suffix.
 
 2. Branch on status + section presence:
    - **status=404 (file missing).** Some marker paths
-     (`agent/journal`) support `PUT` for first-write creation via the
+     (`journal/agent`) support `PUT` for first-write creation via the
      daemon's CREATE_ONLY_PUT allowlist. PUT a minimal file
      containing an H1, the section header, and the new marker line:
      ```bash

package/agent-assets/task-flows/scheduled.task.md

@@ -26,7 +26,7 @@ message the user reads — plan the closing turn accordingly.
 - **Non-empty only when** the task's job is to deliver a short message
   AND you did not call `/api/notify`. Write the message itself, not a
   meta-report about it.
-- **Never name internal mechanisms** in the final text: no `today.md`,
+- **Never name internal mechanisms** in the final text: no `state/today.md`,
   `## Agent Plan`, `## Agent Log`, `did-not-fire`, "DM sent", "logged",
   "closed the row" — those go in Agent Log only. The same rule applies
   in whatever language you respond to the user; no status-word openers
@@ -89,7 +89,7 @@ confirmation.
       off 30 s and retry up to 3 times. If still held, **skip the
       roadmap flip entirely** — the next refresh reconciles — and
       proceed to Step 3 below so the task still executes.
-   2. `GET /api/context/roadmap` and locate the matching
+   2. `GET /api/context/plans/roadmap` and locate the matching
       `### Scheduled: ... (task #<id>)  <!-- id: rm-... -->` entry.
       Flip only its Status line to `running` via `PATCH`
       `section=agent_action_plan` `mode=replace` (include
@@ -137,5 +137,5 @@ confirmation.
 ### Step 5: Follow-up (optional)
 9. Register follow-up wake-ups if the action produced new work (schedule skill).
 10. For additional context if needed:
-    - GET /api/context/roadmap — long-term goals and milestones
-    - GET /api/context/projects/_active — active projects summary
+    - GET /api/context/plans/roadmap — long-term goals and milestones
+    - GET /api/context/plans/projects/_active — active projects summary

package/agent-assets/task-flows/setup.initial.md

@@ -1,13 +1,13 @@
 {context}
 
-## Task: Initial Setup — Create rules/management.md
+## Task: Initial Setup — Create policies/management.md
 
 The dashboard wizard already captured `settings.primary_language` and
 `settings.vault_mode`. Steps 4–6 (Mail / Calendar / Note) configured
 the user's integrations. Your role:
 derive an initial Source-of-Truth table from those integrations,
 confirm it with the user, gather two remaining preferences, and
-generate rules/management.md.
+generate policies/management.md.
 
 Output language: follow `<output_language_policy>`. The conversation
 matches the user's input language.
@@ -19,7 +19,7 @@ assistant messages.
 | Turn | Trigger | What you emit |
 |------|---------|---------------|
 | Turn 1 | No prior assistant message | One natural-language message: greeting + derived Source-of-Truth table + remaining questions. **No code blocks. No curl.** |
-| Turn 2 | The most recent prior assistant message was Turn 1 and the user has now replied | `management-rules` block **FIRST**, then optional `character` block, then silent PUT /api/context/user/profile + any user/*.md PATCHes |
+| Turn 2 | The most recent prior assistant message was Turn 1 and the user has now replied | `management-rules` block **FIRST**, then optional `character` block, then silent PUT /api/context/identity/profile + any user/*.md PATCHes |
 | Turn 3+ | User requested revisions after Turn 2 | Revised `management-rules` block only (cap: 2 revision rounds). No curl writes — they already ran in Turn 2. |
 
 ### Step 0 (silent) — Derive Source-of-Truth from context tags
@@ -85,18 +85,18 @@ In this exact order:
 1. Emit the `management-rules` code block **FIRST** — the dashboard
    reveals the preview as soon as the block lands, so emitting it
    first makes visible-progress immediate. Use the template in
-   "rules/management.md Format" below.
+   "policies/management.md Format" below.
 
 2. If the user stated a tone / style preference (not "no preference" /
    "skip"), emit a `character` code block immediately after — see
    "Character code block format" below. Omit the block entirely if
    they skipped.
-   **Do NOT put communication style inside rules/management.md, and do NOT put it inside user/profile.md.**
+   **Do NOT put communication style inside policies/management.md, and do NOT put it inside identity/profile.md.**
    Tone / style / voice / formality / emoji / language preferences
    live in the `character` runtime-config field only.
 
-3. Silently PUT /api/context/user/profile using the
-   "user/profile.md Format" template below. Working hours and quiet
+3. Silently PUT /api/context/identity/profile using the
+   "identity/profile.md Format" template below. Working hours and quiet
    hours pre-populate with defaults (Weekdays 09:00–18:00,
    Quiet hours 22:00–08:00) — do not ask. Fill Platforms from the
    **derived Source-of-Truth table** (Step 0). Leave Identity blank —
@@ -108,18 +108,18 @@ In this exact order:
 
    | Fact type | File |
    |-----------|------|
-   | Named colleagues, family, friends | user/people.md |
-   | Current company, role specifics, ongoing projects | user/work.md |
-   | Specific frameworks, years of experience | user/expertise.md |
-   | Long-term goals, aspirations | user/goals.md |
-   | Hobbies, lifestyle habits, dietary notes | user/personal.md |
+   | Named colleagues, family, friends | identity/people.md |
+   | Current company, role specifics, ongoing projects | identity/work.md |
+   | Specific frameworks, years of experience | identity/expertise.md |
+   | Long-term goals, aspirations | identity/goals.md |
+   | Hobbies, lifestyle habits, dietary notes | identity/personal.md |
 
    See the user-profile skill for the read-before-write PATCH recipe
    and the `section_not_found` → `append_to_file` first-write
-   fallback. (user/profile.md `## Expertise` keeps a one-line summary
-   only — detailed framework history goes to user/expertise.md.)
+   fallback. (identity/profile.md `## Expertise` keeps a one-line summary
+   only — detailed framework history goes to identity/expertise.md.)
 
-**Important**: Do NOT curl-write rules/management.md yourself. The
+**Important**: Do NOT curl-write policies/management.md yourself. The
 dashboard persists it via `POST /setup/save-rules` when the user
 clicks Save & Finish. Do NOT PATCH /api/config/character either —
 the dashboard stages the `character` block and writes it atomically
@@ -132,7 +132,7 @@ re-emit it. Hard cap: **at most 2 revision rounds** total. Do NOT
 re-run the Turn-2 curl writes — they already persisted. The dashboard
 saves the revised rules block on Save & Finish.
 
-### rules/management.md Format
+### policies/management.md Format
 
 Output language: section headers stay English (the daemon parses
 them); descriptive bullets under `## Autonomy Levels`, `## Notification
@@ -140,7 +140,7 @@ Rules`, `## Schedule`, `## Project Management` follow `<settings
 primary_language>`. Also stay English: `## Agent Identity` field
 labels (`- AI name:`, `- WhatsApp label:`), Source-of-Truth table
 headers and Domain labels, and product/brand cells (`Google
-Calendar`, `Obsidian`, `Notion`, `today.md`, `projects/*.md`).
+Calendar`, `Obsidian`, `Notion`, `state/today.md`, `projects/*.md`).
 
 Fill the Source of Truth table from the rows you confirmed in Turn 1.
 Use today's YYYY-MM-DD for `updated` (the date below is an example).
@@ -170,7 +170,7 @@ updated: 2026-04-21
 - today.md updates: Autonomous
 - Notifications: Autonomous (within rules)
 - External service operations: Confirm with user
-- rules/management.md changes: Always confirm
+- policies/management.md changes: Always confirm
 
 ## Notification Rules
 - Quiet hours: 22:00–08:00 (default — adjustable in Settings)
@@ -202,9 +202,9 @@ most one block per turn.
 Speak casually. Tight bullets. No emojis.
 ```
 
-### user/profile.md Format
+### identity/profile.md Format
 
-When you PUT /api/context/user/profile, write the full file in this
+When you PUT /api/context/identity/profile, write the full file in this
 shape. Use today's YYYY-MM-DD for `updated`. Do not omit
 `## Notification Preferences` — Morning Routine reads it directly.
 
@@ -214,7 +214,7 @@ produced malformed bodies in this flow (server saw literal `@-` and
 returned 500).
 
 ```bash
-curl -s -X PUT http://localhost:8321/api/context/user/profile \
+curl -s -X PUT http://localhost:8321/api/context/identity/profile \
   -H 'Content-Type: application/json' \
   -d '{"content": "---\ntype: user\nowner: shared\nupdated: 2026-04-23\n---\n# User\n\n## Identity\n\n## Work Pattern\n- Working hours: Weekdays 09:00–18:00\n\n## Platforms\n- Schedule: Google Calendar\n- Notes: Obsidian\n- Projects: Notion\n\n## Expertise\n\n## Notification Preferences\n- Quiet hours: 22:00–08:00\n\n## Learned Context\n\n## Raw Signals\n"}'
 ```

package/agent-assets/task-flows/setup.update.md

@@ -12,7 +12,7 @@ Output language: follow `<output_language_policy>` (this is a DM-style turn —
 2. Ask the user which part they'd like to change, presenting these options:
    - **Source of Truth** — Change tools
    - **Notification Rules** — Notification timing and methods
-   - **Character (tone / style / voice)** — Update the `character` runtime-config field, emitted as a ```character``` code block (NOT `rules/management.md`, NOT `user/profile.md`)
+   - **Character (tone / style / voice)** — Update the `character` runtime-config field, emitted as a ```character``` code block (NOT `policies/management.md`, NOT `identity/profile.md`)
    - **Autonomy Levels** — Agent decision scope
    - **Schedule** — Working hours
    - **Project Management** — Preferences for how the agent should handle your projects
@@ -45,7 +45,7 @@ not part of the wizard's editable surface, and stripping them silently
 breaks downstream features:
 
 - **`## Agent Identity`** — populated by the daemon from `agentDisplayName`. Re-emit it as-is or omit it (the server upserts it on save).
-- **`## Active Policies`** — a static wikilink to `rules/policies/_index.md` placed by skeleton seeding. Owned by the management-policy capture flow (the wizard is read-only here). If it is missing from the current rules (legacy installs), do NOT invent it; the next skeleton run will add it.
+- **`## Active Policies`** — a static wikilink to `policies/management-captures/_index.md` placed by skeleton seeding. Owned by the management-policy capture flow (the wizard is read-only here). If it is missing from the current rules (legacy installs), do NOT invent it; the next skeleton run will add it.
 
 The same applies to any other section the wizard does not explicitly
 ask the user about — when in doubt, copy it through unchanged.

package/agent-assets/templates/README.md

@@ -1,9 +1,11 @@
 # agent-assets/templates/
 
 Source templates used by the daemon at **fresh install** time to populate
-`~/.personal-agent/context/` with the B-007 vault layout. The daemon copies
-system / pass-through assets from here directly. User-facing scaffolds that
-must follow `primary_language` are seeded by the `setup.initial` agent flow.
+`~/.personal-agent/context/` with the CONTEXT_VAULT_REDESIGN six-class
+layout (`identity/`, `state/`, `plans/`, `journal/`, `knowledge/`,
+`policies/`). The daemon copies system / pass-through assets from here
+directly. User-facing scaffolds that must follow `primary_language` are
+seeded by the `setup.initial` agent flow.
 
 **Language policy (B-007 §3 P6, unified through
 `docs/design/appendices/output-language-policy.md`)** — template source
@@ -11,12 +13,13 @@ lives here in English. The runtime rule is now carried by the
 `<output_language_policy>` block emitted by ContextBuilder, so every
 flow that writes a scaffold or refreshes one of these files follows one
 shared policy reference instead of restating language wording per flow.
-System prose templates (`rules/redaction.md`, `context-index.md`,
-`agent/journal.md`, `.base` files) stay English regardless of locale
-(Policy A). User-facing scaffolds (`today.md`, `roadmap.md`,
-`_index.md`, `routines/*.md`, `rules/journal-format.md`,
-`rules/journal-export.md`, `user/profile.md`) keep the template H2/H3
-headers (skeleton, Policy B) and their body is filled in
+System prose templates (`policies/redaction.md`, `journal/agent.md`,
+`.base` files, and the reconciler-block portion of `_index.md`) stay
+English regardless of locale (Policy A). User-facing scaffolds
+(`state/today.md`, `plans/roadmap.md`, `_index.md`,
+`policies/routines/*.md`, `policies/journal-format.md`,
+`policies/journal-export.md`, `identity/profile.md`) keep the template
+H2/H3 headers (skeleton, Policy B) and their body is filled in
 `primary_language` by the setup conversation before `save-rules`
 finalizes setup.
 
@@ -30,10 +33,10 @@ Two rendering paths:
 Files prefixed `_` (e.g. `_active.base`) are Obsidian sidebar-sort
 conventions — the leading underscore floats them to the top.
 
-**`today.md` and `roadmap.md`** are shape-canary templates. They are
-copied verbatim by `skeleton.ts:ensureSkeletonFiles` when the templates
-tree is reachable; when the tree is unreachable, `skeleton.ts` falls
-back to an inline literal in `FALLBACK_PLACEHOLDERS` that is kept
+**`state/today.md` and `plans/roadmap.md`** are shape-canary templates.
+They are copied verbatim by `skeleton.ts:ensureSkeletonFiles` when the
+templates tree is reachable; when the tree is unreachable, `skeleton.ts`
+falls back to an inline literal in `FALLBACK_PLACEHOLDERS` that is kept
 byte-equal to these template files. A unit test
 (`packages/daemon/src/core/skeleton.test.ts:"shape canary ..."`)
 asserts this equality on every CI run, so a PR that updates one path
@@ -49,7 +52,7 @@ inventory lives at `_manifest.json` (auto-generated) alongside the
 templates. When a template's format changes:
 
 1. **Bump `template_version` in the template file's frontmatter** (e.g.
-   1 → 2 when `rules/management.md` gains a new required section).
+   1 → 2 when `policies/management.md` gains a new required section).
 2. **Regenerate `_manifest.json`** so the `version` entry matches. A
    unit test (`template-versions.test.ts:"shipped manifest consistency"`)
    fails the build if the two disagree.
@@ -75,9 +78,10 @@ templates. When a template's format changes:
 
 ### Files excluded from versioning
 
-- `today.md`, `roadmap.md`, `projects/_active.base` — no frontmatter to
-  carry the marker. These files are shape canaries / Obsidian view
-  configs that evolve through schema validation, not template diff.
+- `state/today.md`, `plans/roadmap.md`, `plans/projects/_active.base` —
+  no frontmatter to carry the marker. These files are shape canaries /
+  Obsidian view configs that evolve through schema validation, not
+  template diff.
 - `README.md` (this file) — documentation, not a template.
 
 Bump `manifestVersion` in `_manifest.json` only when the manifest
@@ -85,8 +89,11 @@ schema itself changes (e.g. a new per-entry field). Individual
 template-version bumps leave `manifestVersion` alone.
 
 See `docs/design/06-memory.md` and `docs/design/12-configuration.md` for the
-fresh-install flow and vault layout. The `rules/management.md` template
+fresh-install flow and vault layout. The `policies/management.md` template
 follows the structured `schema_version: 3` registry specified in
 `docs/design/21-management-registry-and-entities.md` (A. SoT bindings,
-B. Managed tasks, C. Active-Policies stub) — the v2 "Default Schedules"
-section has been retired (§21 §8.10); do not reintroduce it.
+B. Managed tasks, C. Active-Policies stub). `Default Schedules` is not a
+static template section: the daemon's default-schedules reconciler appends
+a read-only `## Default Schedules` mirror of `recurring_schedules` at
+runtime (§21 §8.10), so it is intentionally absent from this seed — do
+not add it here.

package/agent-assets/templates/_index.md

@@ -1,39 +1,55 @@
 ---
 type: index
 owner: shared
-updated: 2026-04-22
-template_version: 1
+updated: 2026-05-25
+template_version: 2
 ---
 # Aitne Vault
 
-This directory is shared by the agent and me. The agent writes most of it;
-I can edit any file and my edits are preserved (see `rules/management.md`
-for conflict handling).
+This directory is shared by the agent and me. Six top-level folders sit
+under this root; each carries a single authority/lifecycle contract so I
+(and the agent) can always tell which kind of file lives where. The
+agent writes most of it; I can edit any file and my edits are preserved
+(see `policies/management.md` for conflict handling).
 
 ## Where things live
 
-- **About me** → `user/` (profile, people, work, expertise, personal, goals)
-- **Today / Roadmap** → root-level `today.md` and `roadmap.md`
-- **Yesterday snapshot** → yesterday.md appears after the first morning
-  rotation and is replaced by the next one
-- **Projects** → `projects/`; project notes use the projects/<slug>.md
-  naming pattern. See `projects/_index.md` or open `projects/_active.base`
-  in Obsidian
-- **Daily archives** → `daily/` files named by date (synthesized journal)
-- **Weekly / Monthly reviews** → `weekly/`, `monthly/`
-- **Agent self-reflection** → `agent/journal.md` (internal; never pushed
-  as a notification)
-- **Rules & policies** → `rules/` (how the agent should behave — edited by
-  either of us)
-- **Routines** → `routines/` (per-cadence check-list rulebooks)
-- **Dump bucket** → `inbox/` (paste anything here; I'll triage on next
-  morning routine)
+- **About me** → `identity/` (profile, people, work, expertise, personal, goals)
+- **Today / Yesterday** → `state/today.md`, `state/yesterday.md`
+- **Roadmap & projects** → `plans/roadmap.md`, `plans/projects/<slug>.md`
+  (open `plans/projects/_active.base` in Obsidian for the active list)
+- **Inbox dumps** → `state/inbox/` (paste anything here; I'll triage on
+  the next morning routine)
+- **Agent scratch** → `state/scratch/` (48h-TTL working area; not
+  durable)
+- **Activity views** → `state/activity/` (90-day reconciler outputs)
+- **Profile-question queue** → `state/profile-questions.md`
+- **Daily / Weekly / Monthly journals** → `journal/daily/`,
+  `journal/weekly/`, `journal/monthly/` (date-named, append-only)
+- **Per-repo journals** → `journal/repos/<slug>/<date>.md`
+- **Agent self-reflection** → `journal/agent.md` (decision log,
+  append-only, never DM'd)
+- **Wiki workspaces** → `knowledge/wiki/<workspace>/` (internal vaults
+  live here; external Obsidian vaults stay external)
+- **Per-repo overviews** → `knowledge/repos/<slug>/overview.md`
+- **Dossiers** → `knowledge/dossiers/` (accumulated agent research)
+- **Management-registry entities** → `knowledge/entities/<domain>/<type>/<slug>.md`
+- **Rules & policies** → `policies/` (`management.md`, `mcp.md`,
+  `redaction.md`, `journal-format.md`, `journal-export.md`,
+  `integrations.md`)
+- **Routines** → `policies/routines/` (per-cadence rulebooks)
+- **User skills** → `policies/skills/<slug>/SKILL.md`
+- **Policy captures** → `policies/management-captures/`
 
 ## How the agent reads/writes this
 
-All writes go through the context API (locked + snapshotted). Read: direct.
-`Edit`/`Write` tools are not available to the agent — the API is the only
-chokepoint.
+All writes go through the context API (locked + snapshotted). Read:
+direct. `Edit`/`Write` tools are not available to the agent — the API
+is the only chokepoint.
 
-This file is human-readable navigation. The agent's canonical file catalog
-is `context-index.md`, maintained from the filesystem.
+The block below is maintained by the daemon reconciler. Edits inside
+the `<!-- reconciler-section -->` markers are overwritten on the next
+run. Anything outside the markers is yours and is preserved.
+
+<!-- reconciler-section -->
+<!-- /reconciler-section -->

package/agent-assets/templates/_manifest.json

@@ -1,103 +1,38 @@
 {
-  "manifestVersion": 1,
-  "generatedAt": "2026-05-18",
-  "notes": "Auto-generated inventory of versioned templates. Each entry's 'version' must equal the `template_version:` field in the corresponding template file's frontmatter. Bump both in the same PR. A unit test asserts this consistency.",
+  "manifestVersion": 2,
+  "generatedAt": "2026-05-25",
+  "notes": "Auto-generated inventory of versioned templates. Each entry's 'version' must equal the `template_version:` field in the corresponding template file's frontmatter. Bump both in the same PR. A unit test asserts this consistency. Layout rebased onto the CONTEXT_VAULT_REDESIGN six-class structure (identity/, state/, plans/, journal/, knowledge/, policies/).",
   "templates": {
-    "_index.md": {
-      "version": 1
-    },
-    "agent/journal.md": {
-      "version": 1
-    },
-    "agent/profile-questions.md": {
-      "version": 1
-    },
-    "context-index.md": {
-      "version": 1
-    },
-    "dossiers/_index.md": {
-      "version": 1
-    },
-    "dossiers/evening.md": {
-      "version": 1
-    },
-    "dossiers/hourly.md": {
-      "version": 1
-    },
-    "dossiers/monthly.md": {
-      "version": 1
-    },
-    "dossiers/morning.md": {
-      "version": 1
-    },
-    "dossiers/roadmap.md": {
-      "version": 1
-    },
-    "dossiers/weekly.md": {
-      "version": 1
-    },
-    "projects/_index.md": {
-      "version": 1
-    },
-    "routines/_index.md": {
-      "version": 1
-    },
-    "routines/evening.md": {
-      "version": 1
-    },
-    "routines/hourly.md": {
-      "version": 1
-    },
-    "routines/monthly.md": {
-      "version": 1
-    },
-    "routines/morning.md": {
-      "version": 1
-    },
-    "routines/weekly.md": {
-      "version": 1
-    },
-    "rules/_index.md": {
-      "version": 2
-    },
-    "rules/journal-export.md": {
-      "version": 1
-    },
-    "rules/journal-format.md": {
-      "version": 3
-    },
-    "rules/management.md": {
-      "version": 2
-    },
-    "rules/mcp.md": {
-      "version": 1
-    },
-    "rules/policies/_index.md": {
-      "version": 2
-    },
-    "rules/redaction.md": {
-      "version": 1
-    },
-    "user/_index.md": {
-      "version": 1
-    },
-    "user/expertise.md": {
-      "version": 2
-    },
-    "user/goals.md": {
-      "version": 2
-    },
-    "user/people.md": {
-      "version": 2
-    },
-    "user/personal.md": {
-      "version": 2
-    },
-    "user/profile.md": {
-      "version": 2
-    },
-    "user/work.md": {
-      "version": 2
-    }
+    "_index.md": { "version": 2 },
+    "identity/_index.md": { "version": 1 },
+    "identity/expertise.md": { "version": 2 },
+    "identity/goals.md": { "version": 2 },
+    "identity/people.md": { "version": 2 },
+    "identity/personal.md": { "version": 2 },
+    "identity/profile.md": { "version": 2 },
+    "identity/work.md": { "version": 2 },
+    "journal/agent.md": { "version": 1 },
+    "knowledge/dossiers/_index.md": { "version": 1 },
+    "knowledge/dossiers/evening.md": { "version": 1 },
+    "knowledge/dossiers/hourly.md": { "version": 1 },
+    "knowledge/dossiers/monthly.md": { "version": 1 },
+    "knowledge/dossiers/morning.md": { "version": 1 },
+    "knowledge/dossiers/roadmap.md": { "version": 1 },
+    "knowledge/dossiers/weekly.md": { "version": 1 },
+    "plans/projects/_index.md": { "version": 1 },
+    "policies/_index.md": { "version": 2 },
+    "policies/journal-export.md": { "version": 1 },
+    "policies/journal-format.md": { "version": 3 },
+    "policies/management-captures/_index.md": { "version": 2 },
+    "policies/management.md": { "version": 2 },
+    "policies/mcp.md": { "version": 1 },
+    "policies/redaction.md": { "version": 1 },
+    "policies/routines/_index.md": { "version": 1 },
+    "policies/routines/evening.md": { "version": 1 },
+    "policies/routines/hourly.md": { "version": 1 },
+    "policies/routines/monthly.md": { "version": 1 },
+    "policies/routines/morning.md": { "version": 1 },
+    "policies/routines/weekly.md": { "version": 1 },
+    "state/profile-questions.md": { "version": 1 }
   }
 }

package/agent-assets/templates/{user → identity}/_index.md

@@ -13,4 +13,4 @@ template_version: 1
 | `work.md` | Workplace, team, tech stack |
 | `expertise.md` | Domains, tools, skills |
 | `personal.md` | Hobbies, health, habits |
-| `goals.md` | Developmental goals (distinct from `../roadmap.md` project milestones) |
+| `goals.md` | Developmental goals (distinct from `../plans/roadmap.md` project milestones) |

package/agent-assets/templates/{user → identity}/profile.md

@@ -9,8 +9,8 @@ template_version: 2
 # User
 
 > Primary profile injected into every session. Keep this file concise.
-> Detailed profile lives under `user/`.
-> Fetch index: `curl -s http://localhost:8321/api/context/user/_index`
+> Detailed profile lives under `identity/`.
+> Fetch index: `curl -s http://localhost:8321/api/context/identity/_index`
 
 ## Identity
 (To be filled during setup)

package/agent-assets/templates/{dossiers → knowledge/dossiers}/_index.md

@@ -19,4 +19,4 @@ Injected into prompts through the root-level context-index.md catalog.
 | `evening.md` | `routine.evening_review` |
 | `weekly.md` | `routine.weekly_review` |
 | `monthly.md` | `routine.monthly_review` |
-| `roadmap.md` | `routine.roadmap_refresh` |
+| `plans/roadmap.md` | `routine.roadmap_refresh` |

package/agent-assets/templates/{projects → plans/projects}/_active.base

@@ -1,6 +1,6 @@
 filters:
   and:
-    - file.inFolder("projects")
+    - file.inFolder("plans/projects")
     - state != "archived"
 views:
   - type: table

package/agent-assets/templates/policies/_index.md

@@ -0,0 +1,21 @@
+---
+type: index
+owner: shared
+updated: 2026-04-24
+template_version: 2
+---
+# Policies
+
+Natural-language policy files the agent reads to decide HOW to act. Each
+is user-editable; changes take effect at the next task-flow assembly.
+
+| File | Purpose |
+|---|---|
+| `policies/management.md` | Source-of-truth bindings (where each category lives) |
+| `policies/management-captures/_index.md` | Active management policies captured from conversation |
+| `policies/mcp.md` | MCP usage rules (B-003) |
+| `policies/journal-format.md` | Format spec for the daily synthesized journal |
+| `policies/journal-export.md` | User-defined redaction / inclusion rules for B-005 |
+| `policies/redaction.md` | Built-in secret patterns (English, informational) |
+| `policies/routines/` | Per-cadence routine definitions read by the scheduler |
+| `policies/integrations.md` | Integration mode snapshot (renderer keeps this in sync) |

package/agent-assets/templates/{rules → policies}/journal-export.md

@@ -9,7 +9,7 @@ template_version: 1
 
 Edit this file to control what's included when the agent mirrors your
 synthesized `daily/*.md` entries to an external backend (B-005). These
-rules run *on top of* the built-in `rules/redaction.md` patterns.
+rules run *on top of* the built-in `policies/redaction.md` patterns.
 
 ## Inclusion defaults
 

package/agent-assets/templates/{rules → policies}/journal-format.md

@@ -22,7 +22,7 @@ because the human user doesn't journal by hand — but the perspective,
 voice, and content all belong to the user.
 
 Agent-side bookkeeping (action counts, internal anomalies, audit
-trail) lives in `agent/journal.md` — not here. If you find yourself
+trail) lives in `journal/agent.md` — not here. If you find yourself
 about to log "the agent ran N tools today" or "the hourly check
 fired M times", that belongs in the agent-side log instead. Filter
 it out.
@@ -108,7 +108,7 @@ day, etc.
 **Sections deliberately NOT in the daily journal:**
 
 - ❌ Agent action counts (`agent_actions` breakdown by type). Lives
-  in `agent/journal.md` instead — the audit-trail footprint.
+  in `journal/agent.md` instead — the audit-trail footprint.
 - ❌ Internal stage status, retry counts, anomalies. Same as above.
 - ❌ "The agent did X for the user" framing. The user's diary uses
   user voice; agent meta-narration belongs in the agent-side log.
@@ -129,7 +129,7 @@ day, etc.
 
 - When `settings.vault_mode` is `obsidian`, Stage B renders project /
   people references throughout the body as `[[wikilinks]]` targeting
-  `projects/<slug>.md` or `user/people.md#<person>` (basename resolves
+  `projects/<slug>.md` or `identity/people.md#<person>` (basename resolves
   automatically). The `## Summary` paragraph is the primary surface,
   but data sections may also receive wikilinks where a project / person
   name appears (e.g. a meeting title containing a person's name).
@@ -140,10 +140,10 @@ day, etc.
 
 ## Redaction
 
-- Apply `rules/redaction.md` patterns to the entire body Stage B
+- Apply `policies/redaction.md` patterns to the entire body Stage B
   authors (Summary + data sections both — Stage B owns the body, so
   redaction applies wherever sensitive content might surface).
-- Apply `rules/journal-export.md` user rules to the entire body.
+- Apply `policies/journal-export.md` user rules to the entire body.
 - If yesterday.md frontmatter had `no_journal_export: true`, write
   `[Skipped by user request]` as the body of `## Summary` and omit
   the data sections (they would echo information the export rule is

package/agent-assets/templates/{rules/policies → policies/management-captures}/_index.md

@@ -8,8 +8,8 @@ template_version: 2
 
 Auto-maintained by the daemon's policy-index reconciler. Direct edits
 are overwritten on the next reconcile pass — to add or modify a policy,
-edit its `rules/policies/<slug>.md` file (or use the `management-policy`
-skill).
+edit its `policies/management-captures/<slug>.md` file (or use the
+`management-policy` skill).
 
 ## Active