@aitne-sh/aitne 0.1.5 → 0.1.7

package/agent-assets/skills/management-task-register/SKILL.md

@@ -102,9 +102,9 @@ label?"*
   flow with the chosen tool as a hint.)
 - **One plausible** → continue.
 
-NEVER hardcode tool names or pattern-match against
-`mcp__claude_ai_<App>__*`. The user may have installed a custom MCP
-with non-standard names — you read the tool description and pick by
+NEVER hardcode tool names or pattern-match against a specific
+namespace prefix. The user may have installed a custom MCP with
+non-standard names — you read the tool description and pick by
 **capability**, not by name.
 
 ### Step 4 — Read-only probe

package/agent-assets/skills/notion/SKILL.native.claude.md

@@ -1,13 +1,13 @@
 ---
 name: notion
-description: Load when the task touches Notion and Notion is in native mode bound to Claude (`nativeBackend === "claude"`). Use Claude's hosted Notion connector directly; the daemon does not proxy Notion. `/api/notion/databases` (label → UUID config dump) is the only daemon route still reachable.
+description: Load when the task touches Notion and Notion is in native mode bound to Claude (`nativeBackend === "claude"`). Use the in-session Notion connector your harness exposes directly; the daemon does not proxy Notion. `/api/notion/databases` (label → UUID config dump) is the only daemon route still reachable.
 allowed-tools:
   - Bash(curl *)
   - Bash(jq *)
   - Read
 ---
 
-# Notion (native — Claude Notion connector)
+# Notion (native — in-session Notion connector)
 
 > **Refusal directive — read first.** Notion is in `native` mode bound
 > to Claude. Do **NOT** call any of:
@@ -19,8 +19,9 @@ allowed-tools:
 >   `/api/notion/pages/<id>/content` (each route-prefix 410 in native
 >   mode)
 >
-> Reach Notion through the `mcp__claude_ai_Notion__*` MCP tools this
-> Claude session already holds.
+> Reach Notion through the in-session Notion connector your harness
+> exposes. Your tool menu lists every available tool at session start
+> — pick the Notion one.
 >
 > The one exception: **`GET /api/notion/databases`** remains reachable
 > in every mode. It is a config dump (label → UUID map) with no Notion
@@ -34,7 +35,7 @@ the `<integration-routing-table>` block in the session preamble.
 Database UUIDs are unstable; user-facing labels (`"projects"`,
 `"meeting-notes"`, `"tasks"`) map to UUIDs through the daemon's
 settings store. Resolve label → UUID BEFORE any Notion call so the
-MCP arguments carry concrete UUIDs.
+connector arguments carry concrete UUIDs.
 
 ```bash
 curl -s http://localhost:8321/api/notion/databases
@@ -43,54 +44,50 @@ curl -s http://localhost:8321/api/notion/databases
 
 This route is **not** part of the absolute deny set and is intentionally
 ungated in native mode — the agent reads the same labels in every mode.
-The `notion-fetch` tool accepts either a Notion page URL or a UUID;
-pass the UUID resolved here.
+Notion page fetch typically accepts either a page URL or a UUID; pass
+the UUID resolved here.
 
-## 2. Notion — Claude's hosted Notion connector (native MCP)
+## 2. Notion — in-session connector
 
-Tool namespace: `mcp__claude_ai_Notion__`
+The exact tool names depend on which Notion connector your harness has
+loaded. Inspect your tool menu at session start and pick the matching
+capability.
 
-### Read-class tools
+### Read-class capabilities
 
-| Capability | Tool | Use |
-|---|---|---|
-| `search` | `mcp__claude_ai_Notion__notion-search` | Workspace search (text + Notion query parameters). |
-| `read` | `mcp__claude_ai_Notion__notion-fetch` | Retrieve a single page / database / block by URL or UUID; returns content + child block tree. |
-| `comments` | `mcp__claude_ai_Notion__notion-get-comments` | Read comments on a page. |
-| `users` | `mcp__claude_ai_Notion__notion-get-users` | Enumerate workspace users. |
-| `teams` | `mcp__claude_ai_Notion__notion-get-teams` | Enumerate teams / teamspaces. |
+| Capability | What to do |
+|---|---|
+| `search` | Workspace search (text + Notion query parameters), optionally filtered to a specific data source. |
+| `read` | Retrieve a single page / database / block by URL or UUID; returns content + child block tree. |
+| `comments` | Read comments on a page. |
+| `users` | Enumerate workspace users. |
+| `teams` | Enumerate teams / teamspaces. |
 
-Canonical search call:
+Canonical search flow:
 
-```
-mcp__claude_ai_Notion__notion-search(
-  query="acme proposal",
-  query_type="internal",
-  data_source_url="https://www.notion.so/<workspace>/<database-uuid>"
-)
-```
+1. Resolve the database label → UUID via `/api/notion/databases` (§1).
+2. Invoke your connector's search function with the user's query, the
+   data-source URL constructed from the resolved UUID, and the
+   `internal` query-type when targeting a known database.
 
-Canonical page read:
+Canonical page read: invoke your connector's fetch / read-page function
+with the page's URL or UUID.
 
-```
-mcp__claude_ai_Notion__notion-fetch(id="<page-url-or-uuid>")
-```
-
-### Destructive tools (require explicit user confirmation)
+### Destructive capabilities (require explicit user confirmation)
 
 Per the registry's
-`notion.backendConnectors.claude.destructiveTools`:
-
-- `notion-create-pages` — adds new pages.
-- `notion-update-page` — mutates properties / content; **also** the
-  archive workaround (Status="Archived") — §3 below.
-- `notion-duplicate-page` — clones a page.
-- `notion-move-pages` — relocates pages between databases / parents.
-- `notion-create-comment` — posts a comment (user-visible).
-- `notion-create-database` — schema admin (creates new DB).
-- `notion-update-data-source` — schema admin (mutates DB columns).
-- `notion-create-view` — schema admin (new view on DB).
-- `notion-update-view` — schema admin (mutates view config).
+`notion.backendConnectors.claude.destructiveTools`, the following
+capability classes are destructive in native:claude mode:
+
+- **Page creation** — adds new pages.
+- **Page update** — mutates properties / content; **also** the archive
+  workaround (Status="Archived") — §3 below.
+- **Page duplicate** — clones a page.
+- **Page move** — relocates pages between databases / parents.
+- **Comment create** — posts a comment (user-visible).
+- **Database create** — schema admin (creates new DB).
+- **Data-source update** — schema admin (mutates DB columns).
+- **View create / update** — schema admin (new view / mutates view config).
 
 Apply the destructive-confirm contract every time:
 
@@ -98,10 +95,9 @@ Apply the destructive-confirm contract every time:
 2. Surface verbatim and wait for explicit user OK.
 3. On OK, issue the call.
 
-Schema-admin tools (`notion-create-database`, `notion-update-data-source`,
-`notion-create-view`, `notion-update-view`) are higher stakes than
-page mutations — explicitly name "this is a schema-admin change" in
-the plan you surface.
+Schema-admin capability classes (database create, data-source update,
+view create / update) are higher stakes than page mutations — explicitly
+name "this is a schema-admin change" in the plan you surface.
 
 The starter `deniedTools` list (typically denies the schema-admin set)
 is enforced before the call lands. The absolute-block layer continues
@@ -109,18 +105,17 @@ to fire regardless of mode.
 
 ## 3. Page archive — workaround only
 
-Claude's hosted Notion connector does **not** expose an archive /
-trash tool. `in_trash` is rejected as a property by
-`notion-update-page`. To "archive" a page:
+Hosted Notion connectors typically do **not** expose an archive / trash
+tool. `in_trash` is rejected as a property by the page-update function.
+To "archive" a page:
 
 1. **Property workaround** (preferred when the page lives in a
-   database with a Status property): `notion-update-page(id=<uuid>,
-   properties={Status: {status: {name: "Archived"}}})`. The page
-   stays addressable but drops out of default views.
-2. **Move to a "Trash" page**: `notion-move-pages(...)` under a
-   top-level "Trash" page (creating it first via
-   `notion-create-pages` if absent). Reversible without admin
-   intervention.
+   database with a Status property): update the page's Status property
+   to "Archived". The page stays addressable but drops out of default
+   views.
+2. **Move to a "Trash" page**: move the page under a top-level "Trash"
+   page (creating it first via page-creation if absent). Reversible
+   without admin intervention.
 
 Surface either option to the user before issuing — they are
 explicitly user-visible workarounds, not silent archive equivalents.
@@ -128,11 +123,12 @@ explicitly user-visible workarounds, not silent archive equivalents.
 ## 4. Structured database filtering
 
 For "what tasks are in status X" or any `WHERE <property> = ...`
-intent, use `notion-search` with the data-source filter and let the
-connector do the matching. Claude's connector does not expose a
-SQL-style query primitive (Codex's `notion_query_data_sources`
-covers that gap when delegated cross-backend; native-Claude has the
-search-with-filter primitive instead).
+intent, use your connector's search function with a data-source filter
+and let the connector do the matching. The hosted Notion connector
+typically does not expose a SQL-style query primitive (Codex's
+`notion_query_data_sources` covers that gap when delegated
+cross-backend; native-Claude has the search-with-filter primitive
+instead).
 
 ## 5. Decision rules
 
@@ -140,42 +136,42 @@ search-with-filter primitive instead).
   "External services are read-only this hour" constraint from
   `routine.hourly_check.native.claude.md`. No creates, property
   updates, content patches, or archives during the hourly pass.
-- **Mass-update — ask first.** A `notion-create-pages` call can take
-  up to 100 pages in one shot, and `notion-move-pages` /
-  `notion-update-page` batches can touch many rows. Summarise and
-  confirm any change that would touch more than ~10 pages.
+- **Mass-update — ask first.** A page-creation call can take up to
+  100 pages in one shot, and move / update batches can touch many
+  rows. Summarise and confirm any change that would touch more than
+  ~10 pages.
 - **Schema admin — Approve-tier.** Database / view / data-source
   mutations alter workspace structure. Surface explicitly and ask;
   do not auto-confirm "this looks right".
-- **Comments are user-visible.** `notion-create-comment` posts to a
-  page comment thread — treat it like a send: confirm before issuing.
+- **Comments are user-visible.** Posting a page comment is treated
+  like a send: confirm before issuing.
 
 ## 6. Persisting observations from native fetches
 
 When `routine.hourly_check.native.claude.md`'s Step 0c fetches recent
 Notion edits, POST each materialised page to `/api/observations`. The
 daemon computes `contentHash` server-side via
-`@personal-agent/shared/observations-hash.ts`; pass `payload` verbatim:
+`@personal-agent/shared/observations-hash.ts`; pass `payload` verbatim.
+
+**Batch when you have more than one page.** Use
+`POST /api/observations/batch` with up to 200 items in one
+`observations[]` array (see the `observations` skill for the envelope).
+The single-item form below is for the rare "one page changed" case.
 
 ```bash
 curl -s -X POST http://localhost:8321/api/observations \
   -H 'Content-Type: application/json' \
   -d '{
-    "source": "notion",
-    "type": "notion:lifecycle",
+    "source": "notion:<workspaceId>",
     "ref": "<pageId>",
-    "actor": "user",
-    "receivedAt": "<ISO-8601 UTC>",
-    "summary_text": "<title — last edited HH:MM>",
-    "refs": {
-      "pageId": "<id>",
-      "parentDatabase": "<db-uuid-or-null>",
-      "title": "<title>"
-    },
-    "payload": <verbatim MCP page object>
+    "changeType": "created",
+    "actor": "agent",
+    "payload": <verbatim connector page object>
   }'
 ```
 
+`actor` MUST be `"agent"` or `"system"` — the server rejects `"user"`.
+
 `/api/observations` is never gated. HTTP 409 indicates a mode-flip
 race window (§11.3.1); stop and re-read `<integration_modes>`.
 
@@ -196,7 +192,7 @@ Single page edits and routine reads do not need a notify.
 
 ## 8. Cost / audit
 
-Native MCP calls land `agent_actions` rows of type `mcp_call` with
-`provider="claude"`, the tool name, and the parent `event_id` /
+Native connector calls land `agent_actions` rows of type `mcp_call`
+with `provider="claude"`, the tool name, and the parent `event_id` /
 `processKey`. The cost dashboard joins these to the registry by
 `toolNamespace` prefix for the `nativeAttribution` rollup (§14.4).

package/agent-assets/skills/notion/SKILL.native.codex.md

@@ -1,13 +1,13 @@
 ---
 name: notion
-description: Load when the task touches Notion and Notion is in native mode bound to Codex (`nativeBackend === "codex"`). Use Codex's hosted Notion MCP directly; the daemon does not proxy Notion. `/api/notion/databases` (label → UUID config dump) is the only daemon route still reachable.
+description: Load when the task touches Notion and Notion is in native mode bound to Codex (`nativeBackend === "codex"`). Use the in-session Notion connector your Codex harness exposes directly; the daemon does not proxy Notion. `/api/notion/databases` (label → UUID config dump) is the only daemon route still reachable.
 allowed-tools:
   - Bash(curl *)
   - Bash(jq *)
   - Read
 ---
 
-# Notion (native — Codex Notion MCP)
+# Notion (native — in-session Notion connector)
 
 > **Refusal directive — read first.** Notion is in `native` mode bound
 > to Codex. Do **NOT** call any of:
@@ -18,8 +18,9 @@ allowed-tools:
 > - `/api/notion/query`, `/api/notion/search`, `/api/notion/pages`,
 >   `/api/notion/pages/<id>/content` (each route-prefix 410)
 >
-> Reach Notion through the `mcp__codex_apps__notion._*` MCP tools your
-> Codex session already holds.
+> Reach Notion through the in-session Notion connector your harness
+> exposes. Your tool menu lists every available tool at session start
+> — pick the Notion one.
 >
 > Exception: **`GET /api/notion/databases`** remains reachable in every
 > mode (it is a config dump with no Notion API side-effect).
@@ -34,118 +35,115 @@ curl -s http://localhost:8321/api/notion/databases
 # → { "databases": { "<label>": { "id": "<uuid>", "title": "..." }, ... } }
 ```
 
-Resolve label → UUID before any Notion call. Codex's namespace
-terminates with `._`; the bare suffix below is what you write after
-the namespace (`_search` = `mcp__codex_apps__notion._search`).
+Resolve label → UUID before any Notion call so the connector arguments
+carry concrete UUIDs.
 
-## 2. Notion — Codex's hosted Notion MCP (native)
+## 2. Notion — in-session connector
 
-Tool namespace: `mcp__codex_apps__notion._`
+The exact tool names depend on which Notion connector your harness has
+loaded. Inspect your tool menu at session start and pick the matching
+capability. Codex-side hosted Notion connectors typically include a
+structured query primitive that Claude's connector lacks; the table
+below treats it as a capability rather than naming the tool.
 
-### Read-class tools
+### Read-class capabilities
 
-| Capability | Tool | Use |
-|---|---|---|
-| `search` | `_search` | Workspace search. |
-| `read` | `_fetch` | Single page / database / block by URL or UUID; returns block tree. |
-| `comments` | `_notion_get_comments` | Read page comments. |
-| `users` | `_notion_get_users` | Enumerate workspace users. |
-| `teams` | `_notion_get_teams` | Enumerate teams. |
-| `query_data_sources` | `_notion_query_data_sources` | **SQL-style** structured filter (`WHERE <property> = ?`) — Codex-only capability, not exposed by Claude. Use it for "what tasks are in status X" intents. |
-| `query_meeting_notes` | `_notion_query_meeting_notes` | Structured filter over the user's meeting-notes data source (niche). |
+| Capability | What to do |
+|---|---|
+| `search` | Workspace search (text + Notion query parameters), optionally filtered to a specific data source. |
+| `read` | Retrieve a single page / database / block by URL or UUID; returns block tree. |
+| `comments` | Read page comments. |
+| `users` | Enumerate workspace users. |
+| `teams` | Enumerate teams / teamspaces. |
+| `query_data_sources` | **SQL-style** structured filter (`WHERE <property> = ?`) — Codex-side connectors typically expose this; use it for "what tasks are in status X" intents when available. Falls back to `search` + client-side filtering when absent. |
+| `query_meeting_notes` | Structured filter over a meeting-notes data source (niche, only some connectors expose it). |
 
-Canonical search call:
+Canonical search flow: invoke your connector's search function with
+the user's text query and the data-source UUID resolved in §1.
 
-```
-mcp__codex_apps__notion._search(
-  query="acme proposal",
-  data_source_id="<db-uuid-resolved-from-labels>"
-)
-```
-
-Canonical structured filter (Codex-only):
-
-```
-mcp__codex_apps__notion._notion_query_data_sources(
-  data_source_id="<db-uuid>",
-  filter="Status = 'Active' AND Priority = 'P1'",
-  limit=20
-)
-```
+Canonical structured filter (when the connector exposes it): invoke
+the structured-query function with the data-source UUID, a filter
+expression like `"Status = 'Active' AND Priority = 'P1'"`, and a
+sensible `limit`.
 
-Canonical page read:
+Canonical page read: invoke your connector's fetch / read-page function
+with the page's URL or UUID.
 
-```
-mcp__codex_apps__notion._fetch(id="<page-url-or-uuid>")
-```
-
-### Destructive tools (require explicit user confirmation)
+### Destructive capabilities (require explicit user confirmation)
 
-Per the registry's `notion.backendConnectors.codex.destructiveTools`:
+Per the registry's `notion.backendConnectors.codex.destructiveTools`,
+the following capability classes are destructive in native:codex mode:
 
-- `_notion_create_pages`
-- `_notion_update_page` — properties, content, archive workaround.
-- `_notion_duplicate_page`
-- `_notion_move_pages`
-- `_notion_create_comment`
-- `_notion_create_database` — schema admin.
-- `_notion_update_data_source` — schema admin.
-- `_notion_create_view` — schema admin.
-- `_notion_update_view` — schema admin.
+- **Page creation** — adds new pages (batch-aware on most connectors).
+- **Page update** — mutates properties / content; **also** the archive
+  workaround (Status="Archived") — §3 below.
+- **Page duplicate** — clones a page.
+- **Page move** — relocates pages between databases / parents.
+- **Comment create** — posts a comment (user-visible).
+- **Database create** — schema admin (creates new DB).
+- **Data-source update** — schema admin (mutates DB columns).
+- **View create / update** — schema admin (new view / mutates view
+  config).
 
 Apply the destructive-confirm contract: summarise, wait for explicit
-OK, then issue. Schema-admin tools warrant an explicit "schema admin"
-label on the plan you surface. The starter `deniedTools` list is
-enforced before the call lands.
+OK, then issue. Schema-admin capability classes warrant an explicit
+"schema admin" label on the plan you surface. The starter `deniedTools`
+list is enforced before the call lands.
 
 ## 3. Page archive — workaround only
 
-Same gap as Claude's connector — no dedicated archive tool. Use the
-property-update workaround (Status="Archived") via
-`_notion_update_page`, or move the page under a top-level Trash page
-via `_notion_move_pages`. Surface the choice to the user.
+Same gap as Claude's connector — hosted Notion connectors typically
+expose no dedicated archive / trash tool. To "archive":
+
+1. **Property workaround** (preferred): update the page's Status
+   property to "Archived" via the page-update capability. The page
+   stays addressable but drops out of default views.
+2. **Move to a "Trash" page**: relocate the page under a top-level
+   "Trash" page via the page-move capability (create it first via
+   page-creation if absent).
+
+Surface the choice to the user before issuing.
 
 ## 4. Decision rules
 
 - **Hourly check is read-only** — inherits the constraint from
   `routine.hourly_check.native.codex.md`.
-- **Mass-update — ask first.** `_notion_create_pages` can take up to
-  100 pages; `_notion_move_pages` and `_notion_update_page` batches
-  can touch many rows. Summarise and confirm anything >~10 pages.
+- **Mass-update — ask first.** Batch page-creation can take up to 100
+  pages; page-move and page-update batches can touch many rows.
+  Summarise and confirm anything >~10 pages.
 - **Schema admin — Approve-tier.** Database / view / data-source
   mutations alter workspace structure. Explicit user confirmation
   required.
-- **Comments are user-visible.** `_notion_create_comment` posts to a
-  page comment thread — treat like a send.
+- **Comments are user-visible.** Posting a page comment is treated
+  like a send: confirm before issuing.
 - **Prefer structured filter over text search** when the user's
-  intent is property-shaped. `_notion_query_data_sources` is the
-  Codex-only capability that closes the gap Claude's connector has;
-  use it.
+  intent is property-shaped and the connector exposes a structured
+  query primitive. If the connector only exposes text search, fall
+  back to search + client-side property filtering.
 
 ## 5. Persisting observations from native fetches
 
+**Batch when you have more than one page.** Use
+`POST /api/observations/batch` with up to 200 items in one
+`observations[]` array (see the `observations` skill for the envelope).
+The single-item form below is for the rare "one page changed" case.
+
 ```bash
 curl -s -X POST http://localhost:8321/api/observations \
   -H 'Content-Type: application/json' \
   -d '{
-    "source": "notion",
-    "type": "notion:lifecycle",
+    "source": "notion:<workspaceId>",
     "ref": "<pageId>",
-    "actor": "user",
-    "receivedAt": "<ISO-8601 UTC>",
-    "summary_text": "<title — last edited HH:MM>",
-    "refs": {
-      "pageId": "<id>",
-      "parentDatabase": "<db-uuid-or-null>",
-      "title": "<title>"
-    },
-    "payload": <verbatim MCP page object>
+    "changeType": "created",
+    "actor": "agent",
+    "payload": <verbatim connector page object>
   }'
 ```
 
 The daemon computes `contentHash` server-side. Pass `payload`
-verbatim. HTTP 409 → mode-flip race window (§11.3.1); stop and re-read
-`<integration_modes>`.
+verbatim. `actor` MUST be `"agent"` or `"system"` — the server
+rejects `"user"`. HTTP 409 → mode-flip race window (§11.3.1); stop and
+re-read `<integration_modes>`.
 
 ## 6. Owner notification (opt-in)