@aitne-sh/aitne 0.1.9 → 0.1.10

package/agent-assets/skills/context/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: context
-description: Load when reading or writing project notes, weekly/monthly summaries, or agent/journal.md. Owns GET/PATCH for context files except today.md and roadmap.md, which use their dedicated skills.
+description: Load when reading or writing project notes, weekly/monthly summaries, or journal/agent.md. Owns GET/PATCH for context files except today.md and roadmap.md, which use their dedicated skills.
 allowed-tools:
   - Bash(curl *)
   - Read
@@ -28,23 +28,23 @@ vault**, not this primary store.
 |---|---|---|---|
 | `state/today.md` | Today's schedule, tasks, agent log, handoff | See `today` skill | Yes (Morning Routine) |
 | `plans/roadmap.md` | Long-horizon agent action plan + Long-term Plans | See `roadmap` skill | Yes (Roadmap Refresh) |
-| `projects/*.md` | Project state summaries | Any event on material state change | No |
-| `weekly/YYYY-Www.md` | Weekly review snapshots | Friday Weekly Review only (PUT) | No |
-| `monthly/YYYY-MM.md` | Monthly review snapshots | Month-end Monthly Review only (PUT) | No |
-| `rules/*.md` | User-controlled policy files | Explicit user request only | No |
+| `plans/projects/*.md` | Project state summaries | Any event on material state change | No |
+| `journal/weekly/YYYY-Www.md` | Weekly review snapshots | Friday Weekly Review only (PUT) | No |
+| `journal/monthly/YYYY-MM.md` | Monthly review snapshots | Month-end Monthly Review only (PUT) | No |
+| `policies/*.md` | User-controlled policy files | Explicit user request only | No |
 | `policies/management-captures/<slug>.md` | Durable management policies captured from DM | `management-policy` skill — **do not write from here** | No |
 | `policies/management-captures/_index.md` | Readable index of active policies | `management-policy` skill — **do not write from here** | No |
-| `routines/*.md` | Per-cadence check rulebooks | Explicit user request only | No |
+| `policies/routines/*.md` | Per-cadence check rulebooks | Explicit user request only | No |
 | `identity/profile.md` | User identity and preferences | `user-profile` skill — **do not write from here** | No |
-| `user/*.md` | Detailed user dictionary | `user-profile` skill — **do not write from here** | No |
+| `identity/*.md` | Detailed user dictionary | `user-profile` skill — **do not write from here** | No |
 
 Morning Routine scans roadmap daily and processes matching Preparation
 Timeline rows into `state/today.md` — see the `roadmap` skill for the full
 entry taxonomy and the morning routine task-flow for the scanning rules.
 
-## projects/*.md
+## plans/projects/*.md
 
-Update on status changes, milestones reached/delayed, or active set changes. Use `GET /api/context/list/projects` to discover files. The source of truth is always the individual `projects/<slug>.md` notes; `_active.base` is only the Obsidian Bases view config, not a narrative summary note.
+Update on status changes, milestones reached/delayed, or active set changes. Use `GET /api/context/list/plans/projects` to discover files. The source of truth is always the individual `plans/projects/<slug>.md` notes; `_active.base` is only the Obsidian Bases view config, not a narrative summary note.
 
 The canonical frontmatter schema is documented in `plans/projects/_index.md`
 (seeded from `agent-assets/templates/plans/projects/_index.md`). The API
@@ -56,26 +56,16 @@ validates only `type: project`, `owner: shared`, `updated`, and an H1
 
 ## Project DM-intent detection
 
-DM-driven project state writes are dispatched from
-`message.received.dm.md` / `message.received.dm_first.md` Step 4 via
-the `_partials/dm-intent.project.md` task-flow partial — that partial
-carries the decision tree (existing-vs-new match, decline-marker
-pre-check, no-match confirm sub-flow scheduling, reply branches,
-cross-path cancellation, slug grammar, tie-breakers).
+DM-driven project writes are dispatched by
+`_partials/dm-intent.project.md` (the decision tree — match, decline
+markers, confirm sub-flow, slug grammar, tie-breakers — lives there).
+**This skill is the writer:** it executes the `plans/projects/*.md`
+PUT / PATCH / archive per the API Reference below.
 
-**This skill is the writer.** `projects/<slug>.md` PUT / PATCH / archive
-goes through `/api/context/projects/*` per the API Reference below. The
-partial dispatches; this skill executes the writes.
+## Snapshot files — weekly / monthly / policies / routines
 
-Cross-references previously in this section ("Reply branches",
-"Cross-path cancellation", "Decline-marker reversal", "Tie-breakers",
-"Slug grammar") now live alongside their decision-tree steps inside
-the partial.
-
-## Snapshot files — weekly / monthly / rules / routines
-
-Weekly and monthly review snapshots, the user-controlled `rules/*.md`
-policy files, the built-in `routines/<cadence>.md` rulebooks, custom
+Weekly and monthly review snapshots, the user-controlled `policies/*.md`
+policy files, the built-in `policies/routines/<cadence>.md` rulebooks, custom
 routines under `policies/routines/custom/`, and the agent-private
 `journal/agent.md` all have stable per-file conventions (writer event,
 verb, frontmatter, retention) documented in the snapshot-files
@@ -88,11 +78,12 @@ DM handlers and Hourly Checks should generally not write these files
 
 ## Required frontmatter for guarded files
 
-Full-file writes to `user/*.md`, `rules/*.md`, `projects/*.md`,
-`daily/*.md`, `weekly/*.md`, and `monthly/*.md` must open with the
-matching YAML frontmatter (`type`, `owner`, `updated`) followed by at
-least one H1 heading. Per-glob values and the common rejection
-envelope are in the required-frontmatter reference below.
+Full-file writes to `identity/*.md`, `policies/*.md`,
+`plans/projects/*.md`, `journal/daily/*.md`, `journal/weekly/*.md`, and
+`journal/monthly/*.md` must open with the matching YAML frontmatter
+(`type`, `owner`, `updated`) followed by at least one H1 heading.
+Per-glob values and the common rejection envelope are in the
+required-frontmatter reference below.
 
 {{> ref:required-frontmatter }}
 

package/agent-assets/skills/context/curation.json

@@ -10,12 +10,12 @@
       "scope_paths": [
         "state/today.md",
         "plans/roadmap.md",
-        "projects/*.md",
-        "weekly/*.md",
-        "monthly/*.md",
-        "rules/*.md",
-        "user/*.md",
-        "agent/*.md"
+        "plans/projects/*.md",
+        "journal/weekly/*.md",
+        "journal/monthly/*.md",
+        "policies/*.md",
+        "identity/*.md",
+        "journal/agent.md"
       ]
     },
     {
@@ -25,12 +25,12 @@
       "human_label": "Required frontmatter for guarded files",
       "description": "Per file-glob: required + conventional frontmatter keys",
       "scope_paths": [
-        "projects/*.md",
-        "user/*.md",
-        "rules/*.md",
-        "weekly/*.md",
-        "monthly/*.md",
-        "daily/*.md"
+        "plans/projects/*.md",
+        "identity/*.md",
+        "policies/*.md",
+        "journal/weekly/*.md",
+        "journal/monthly/*.md",
+        "journal/daily/*.md"
       ]
     }
   ]

package/agent-assets/skills/context/references/api.md

@@ -32,12 +32,13 @@ URL).
 ### GET /api/context/list/:dir
 
 ```bash
-curl -s http://localhost:8321/api/context/list/projects
+curl -s http://localhost:8321/api/context/list/plans/projects
 ```
 
 Response: `{ "files": [{ "name", "lastModified" }, …] }`. Use this to
-enumerate `projects/`, `weekly/`, `monthly/`, `user/`, `rules/`,
-`routines/`, `inbox/` before deciding a write target.
+enumerate `plans/projects/`, `journal/weekly/`, `journal/monthly/`,
+`identity/`, `policies/`, `policies/routines/`, `state/inbox/` before
+deciding a write target.
 
 ### GET /api/context/today/reconciliation
 
@@ -67,21 +68,19 @@ Add `X-Lock-Id: <lock-id>` when writing a locked file (`state/today.md`,
 
 Common rejections:
 
-- `400 {error:"validation_error", message, path}` — file-specific
-  validator failed (e.g. `state/today.md` line-1 date regex, `plans/roadmap.md`
-  transition guard, required frontmatter missing on `user/*.md` /
-  `rules/*.md` / `projects/*.md` / `daily/*.md` / `weekly/*.md` /
-  `monthly/*.md`).
+- `400 {error:"validation_error", message, path}` — a content-body
+  validator failed: `state/today.md` line-1 date regex (the message
+  echoes both the supplied date and the daemon's current agent-day) or
+  the `plans/roadmap.md` transition guard.
+- `422 {error:"validation_error", message, path}` — *frontmatter* shape
+  is missing/wrong on a globbed file (`identity/*.md`, `policies/*.md`,
+  `plans/projects/*.md`, `journal/daily/*.md`, `journal/weekly/*.md`,
+  `journal/monthly/*.md`). Frontmatter validation is a 422; the today.md
+  line-1 case above is a 400.
 - `409 {error:"morning_routine_lock_held"}` — the Morning Routine holds
   the `state/today.md` write lock; `409 {error:"roadmap_write_lock_held"}`
   — another session holds the `plans/roadmap.md` lock. Retry with
   backoff (30s × 3).
-- `400 {error:"validation_error", message, path}` — also covers the
-  `state/today.md` line-1 agent-day mismatch (the message echoes both the
-  supplied date and the daemon's current agent-day). The `422` status is
-  reserved for *frontmatter* validation on globbed files (`user/*.md`,
-  `rules/*.md`, `projects/*.md`, `daily/*.md`, `weekly/*.md`,
-  `monthly/*.md`), not for today.md line-1.
 
 `policies/management.md` is user-controlled policy: modify only when the
 user explicitly asks, and preserve every unrelated section.
@@ -136,7 +135,7 @@ for those.
 
 ### POST /api/context/archive-today
 
-Rotates `state/today.md` → `state/yesterday.md` (synthesized `daily/YYYY-MM-DD.md`
+Rotates `state/today.md` → `state/yesterday.md` (synthesized `journal/daily/YYYY-MM-DD.md`
 is now written by the Morning Routine, not this endpoint). Called by
 the Morning Routine during day rotation; other sessions should NOT
 invoke this directly.
@@ -145,8 +144,9 @@ invoke this directly.
 
 Restores the file from snapshot `id` (the daemon snapshots every PUT /
 PATCH / DELETE). Diagnostic / recovery surface; never part of a normal
-write path. The snapshot listing endpoint is `GET /api/context/health`
-adjacent and is dashboard-only — agents should not rely on it in flows.
+write path. Snapshot listing is dashboard-only via the Knowledge page;
+no agent route exists, so `restore-snapshot/:id` is the only
+agent-relevant snapshot op.
 
 ### POST /api/context/repair/stub
 

package/agent-assets/skills/context/references/required-frontmatter.md

@@ -7,8 +7,9 @@ description: YAML frontmatter required by /api/context/* validators on full-file
 # Required frontmatter — guarded files
 
 Full-file `PUT /api/context/<path>` for the following globs is rejected
-(`400 validation_error`) unless the body opens with the matching YAML
-frontmatter followed by at least one H1 heading.
+(`422 validation_error` — frontmatter shape is a 422, distinct from the
+400 returned for content-body validators) unless the body opens with the
+matching YAML frontmatter followed by at least one H1 heading.
 
 Use today's date (the value from `<current_agent_day date="…" />`) for
 `updated`. The daemon does not auto-fill `updated`; an outdated value
@@ -18,12 +19,12 @@ trips the Evening Review's stale-file detector.
 
 | File glob | `type` | `owner` | Required H1 |
 |---|---|---|---|
-| `projects/*.md` | `project` | `shared` | Yes |
-| `daily/*.md` | `daily` | `agent` | Yes |
-| `weekly/*.md` | `weekly` | `agent` | Yes |
-| `monthly/*.md` | `monthly` | `agent` | Yes |
-| `rules/*.md` | `rule` | `shared` | Yes |
-| `user/*.md` | `user` | `shared` | Yes |
+| `plans/projects/*.md` | `project` | `shared` | Yes |
+| `journal/daily/*.md` | `daily` | `agent` | Yes |
+| `journal/weekly/*.md` | `weekly` | `agent` | Yes |
+| `journal/monthly/*.md` | `monthly` | `agent` | Yes |
+| `policies/*.md` | `rule` | `shared` | Yes |
+| `identity/*.md` | `user` | `shared` | Yes |
 
 Every glob also requires `updated: YYYY-MM-DD`.
 
@@ -55,7 +56,7 @@ have their own validators (date-line regex, transition guard, append-
 only mode, policy schema). The frontmatter rules in this reference do
 not apply to them — see each owning skill for the specifics.
 
-## Common 400 envelope
+## Common 422 envelope
 
 ```json
 {

package/agent-assets/skills/context/references/snapshot-files.md

@@ -7,17 +7,18 @@ description: Weekly / monthly review snapshots, rules / routines files — who w
 # Snapshot files — weekly / monthly / rules / routines
 
 These files live in the primary management vault under
-`weekly/`, `monthly/`, `rules/`, and `routines/`. They are not part
+`journal/weekly/`, `journal/monthly/`, `policies/`, and
+`policies/routines/`. They are not part
 of the day-to-day context churn (`state/today.md`, `plans/roadmap.md`,
-`projects/*.md`); they accumulate slowly and are written by routines
+`plans/projects/*.md`); they accumulate slowly and are written by routines
 or by explicit user request.
 
-## weekly/*.md, monthly/*.md
+## journal/weekly/*.md, journal/monthly/*.md
 
 | File | Path | Cadence | Writer | Verb |
 |---|---|---|---|---|
-| Weekly review | `weekly/YYYY-Www.md` | Friday Weekly Review only | `routine.weekly_review` | `PUT` (full body) |
-| Monthly review | `monthly/YYYY-MM.md` | Month-end Monthly Review only | `routine.monthly_review` | `PUT` (full body) |
+| Weekly review | `journal/weekly/YYYY-Www.md` | Friday Weekly Review only | `routine.weekly_review` | `PUT` (full body) |
+| Monthly review | `journal/monthly/YYYY-MM.md` | Month-end Monthly Review only | `routine.monthly_review` | `PUT` (full body) |
 
 Notes:
 
@@ -25,13 +26,13 @@ Notes:
   retry counts, self-critique) go to `journal/agent.md`, not here.
 - Weekly file name uses ISO week (`YYYY-Www` — `2026-W19`, not
   `2026-W5`); pad the week to two digits.
-- Never write `weekly/*.md` or `monthly/*.md` on any other day. The
+- Never write `journal/weekly/*.md` or `journal/monthly/*.md` on any other day. The
   Morning Routine, Hourly Check, Evening Review, and DM handlers do
   not produce these files; if you are not the matching review
   routine, do not PUT this path.
 - `PATCH` is technically accepted but unusual. The normal write is a
   single full-body `PUT` at the end of the review session.
-- **Weekly leverage contract.** `weekly/YYYY-Www.md` carries three
+- **Weekly leverage contract.** `journal/weekly/YYYY-Www.md` carries three
   load-bearing H2 sections — `## Carry Over to Next Week`,
   `## Next Week Focus`, `## Lessons for Next Week` — that the
   morning_routine lifts mechanically via the `<previous_week>` context
@@ -40,7 +41,7 @@ Notes:
   3 bullets respectively; empty sections render as `(none recorded)`
   downstream. Full design: `docs/design/appendices/weekly-next-week-leverage.md`.
 
-## agent/journal.md
+## journal/agent.md
 
 | Field | Value |
 |---|---|
@@ -56,12 +57,12 @@ Weekly Review, and Monthly Review each append their own block.
 **Nothing from this file should appear in notifications.** The journal
 is the agent's private metrics surface, not user-readable content.
 
-## rules/*.md, routines/*.md
+## policies/*.md, policies/routines/*.md
 
 User-controlled policy and routine files. Only modify when the user
 explicitly asks to change the policy or routine itself.
 
-### `rules/*.md`
+### `policies/*.md`
 
 - Preserve unrelated sections verbatim. PATCH the one section the
   user is changing; do not full-body PUT.
@@ -75,7 +76,7 @@ similarity-detection, and pause/resume fan-out for durable policies.
 **Do not hand-edit from this skill.** A direct PATCH here bypasses the
 similarity check and the dossier / routine fan-out.
 
-### `routines/<cadence>.md` (built-in cadences)
+### `policies/routines/<cadence>.md` (built-in cadences)
 
 - Cadences: `morning`, `evening`, `weekly`, `monthly`, `hourly`.
 - Keep the existing frontmatter. Keep a `## Checks` section.

package/agent-assets/skills/context/seeds/file-responsibilities.seed.json

@@ -3,11 +3,11 @@
   "files": [
     { "path": "state/today.md", "purpose": "today's schedule, tasks, agent log, handoff", "sections": [{ "heading": "## Schedule", "contains": "today's events" }, { "heading": "## Tasks", "contains": "open tasks" }, { "heading": "## Agent Notes", "contains": "agent observations" }] },
     { "path": "plans/roadmap.md", "purpose": "long-horizon agent action plan + Long-term Plans", "sections": [{ "heading": "## Annual Goals", "contains": "year-scope outcomes" }, { "heading": "## Quarterly Milestones", "contains": "quarter-scope deliverables" }, { "heading": "## Focus Areas", "contains": "current themes of work" }] },
-    { "path": "projects/*.md", "purpose": "per-project state summaries (slug-named)", "sections": [{ "heading": "## Overview", "contains": "what the project is about" }, { "heading": "## Lifecycle Phases", "contains": "phase ladder for the project" }] },
-    { "path": "weekly/*.md", "purpose": "weekly review snapshots (YYYY-Www); Carry Over / Next Week Focus / Lessons are lifted into next week's morning_routine via <previous_week>", "sections": [{ "heading": "## Highlights", "contains": "wins of the week" }, { "heading": "## Open Loops", "contains": "tasks/commitments still pending" }, { "heading": "## Carry Over to Next Week", "contains": "open loops to carry over (max 5) with one-line reason" }, { "heading": "## Next Week Focus", "contains": "top priorities for next week (max 3)" }, { "heading": "## Lessons for Next Week", "contains": "behavioral observation → action (max 3)" }] },
-    { "path": "monthly/*.md", "purpose": "monthly review snapshots (YYYY-MM)", "sections": [{ "heading": "## Theme", "contains": "the month's overall theme" }] },
-    { "path": "rules/*.md", "purpose": "user-controlled policy files", "sections": [{ "heading": "## Why", "contains": "rationale for the rule" }, { "heading": "## How", "contains": "concrete rule shape" }] },
-    { "path": "user/*.md", "purpose": "user identity and preferences dictionary", "sections": [{ "heading": "## Identity", "contains": "name role tz" }] },
+    { "path": "plans/projects/*.md", "purpose": "per-project state summaries (slug-named)", "sections": [{ "heading": "## Overview", "contains": "what the project is about" }, { "heading": "## Lifecycle Phases", "contains": "phase ladder for the project" }] },
+    { "path": "journal/weekly/*.md", "purpose": "weekly review snapshots (YYYY-Www); Carry Over / Next Week Focus / Lessons are lifted into next week's morning_routine via <previous_week>", "sections": [{ "heading": "## Highlights", "contains": "wins of the week" }, { "heading": "## Open Loops", "contains": "tasks/commitments still pending" }, { "heading": "## Carry Over to Next Week", "contains": "open loops to carry over (max 5) with one-line reason" }, { "heading": "## Next Week Focus", "contains": "top priorities for next week (max 3)" }, { "heading": "## Lessons for Next Week", "contains": "behavioral observation → action (max 3)" }] },
+    { "path": "journal/monthly/*.md", "purpose": "monthly review snapshots (YYYY-MM)", "sections": [{ "heading": "## Theme", "contains": "the month's overall theme" }] },
+    { "path": "policies/*.md", "purpose": "user-controlled policy files", "sections": [{ "heading": "## Why", "contains": "rationale for the rule" }, { "heading": "## How", "contains": "concrete rule shape" }] },
+    { "path": "identity/*.md", "purpose": "user identity and preferences dictionary", "sections": [{ "heading": "## Identity", "contains": "name role tz" }] },
     { "path": "journal/agent.md", "purpose": "agent-owned weekly + monthly self-critique", "sections": [{ "heading": "## Weekly", "contains": "what worked, what slipped, improvements" }] }
   ]
 }

package/agent-assets/skills/context/seeds/frontmatter-requirements.seed.json

@@ -2,7 +2,7 @@
   "kind": "frontmatter_schema",
   "file_types": [
     {
-      "glob": "projects/*.md",
+      "glob": "plans/projects/*.md",
       "required": [
         { "key": "type", "type": "enum", "example": "project" },
         { "key": "owner", "type": "string", "example": "shared" },
@@ -19,7 +19,7 @@
       ]
     },
     {
-      "glob": "user/*.md",
+      "glob": "identity/*.md",
       "required": [
         { "key": "type", "type": "enum", "example": "user" },
         { "key": "owner", "type": "string", "example": "shared" },
@@ -28,7 +28,7 @@
       "conventional": []
     },
     {
-      "glob": "rules/*.md",
+      "glob": "policies/*.md",
       "required": [
         { "key": "type", "type": "enum", "example": "rule" },
         { "key": "owner", "type": "string", "example": "shared" },

package/agent-assets/skills/docs-search/SKILL.md

@@ -27,38 +27,24 @@ the FTS query in three steps:
 
 1. **Extract the topic.** Strip interrogatives, particles, and meta
    phrases. Keep only the noun phrase or technical term.
-
-   | Input | Topic |
-   |---|---|
-   | "what is delegated mode?" | `delegated mode` |
-   | "什么是 delegated 模式？" | `delegated模式` |
-   | "tell me about ProcessKey" | `ProcessKey` |
-   | "ProcessKey 是什么？" | `ProcessKey` |
-   | "how does the morning routine work?" | `morning routine` |
-   | "早晨例行公事是怎么运作的？" | `早晨例行公事` |
-
 2. **Split at script boundaries.** If the topic mixes Latin and CJK
    without spaces, insert a space at every Latin↔CJK boundary. FTS5
    quotes each whitespace-separated token as a phrase before
    AND-joining; an unsplit `delegated模式` becomes one unmatchable
    trigram phrase.
-
-   | Input | Split |
-   |---|---|
-   | `delegated模式` | `delegated 模式` |
-   | `ProcessKey列表` | `ProcessKey 列表` |
-
 3. **Latin wins.** If the split topic contains both Latin and CJK
-   tokens, drop the CJK tokens. The corpus is English; CJK is the
-   operator's gloss, not the indexed term. Pure-CJK topics are passed
-   through unchanged (and may legitimately miss until bilingual aliases
-   land — see "When you cannot find an answer" below).
+   tokens, drop the CJK tokens — the corpus is English; CJK is the
+   operator's gloss, not the indexed term. Pure-CJK topics pass through
+   unchanged (and may legitimately miss until bilingual aliases land —
+   see "When you cannot find an answer" below).
 
-   | Input | Final query |
-   |---|---|
-   | `delegated 模式` | `delegated` |
-   | `ProcessKey 列表` | `ProcessKey` |
-   | `早晨例行公事` | `早晨例行公事` (passes through; may miss) |
+| Input | Final query |
+|---|---|
+| "what is delegated mode?" | `delegated` |
+| "什么是 delegated 模式？" | `delegated` |
+| "ProcessKey 是什么？" | `ProcessKey` |
+| "how does the morning routine work?" | `morning routine` |
+| "早晨例行公事是怎么运作的？" | `早晨例行公事` (passes through; may miss) |
 
 ## Endpoints
 
@@ -87,18 +73,20 @@ must not exceed 3. Quality rule, not a daemon-enforced cap.
 2. **Call 2 (optional).** If 0 hits and a Latin synonym is obvious,
    retry `term-search` with the synonym. Otherwise fall back to
    `search` with the same topic.
-3. **Call 3 (rare).** Broaden — strip qualifiers, or add `&category=`
-   / `&tag=` to narrow.
+3. **Call 3 (rare).** Broaden — strip qualifiers, or narrow with
+   `&category=` (both endpoints) or, on `search` only, `&tag=`.
 
 If three calls do not surface an answer, stop and tell the operator the
 docs do not cover their question.
 
 ## Search query syntax
 
-Treat `q` as an FTS5 query. Quote multi-word phrases (`"day plan"`)
-when you want them adjacent. Wildcards (`day*`) match prefixes. Boolean
-operators (`AND`, `OR`, `NOT`) work — but plain space-separated terms
-are usually enough. The bm25 weights already boost
+`q` is **not** a raw FTS5 query. The daemon tokenizes it on whitespace,
+wraps each token in quotes as a literal phrase, and AND-joins them, so
+every term is required. Wildcards (`day*`), booleans (`AND`/`OR`/`NOT`),
+and your own quotes are searched as literal text, not as operators —
+multi-word queries are already implicit-AND across all tokens. Just send
+space-separated terms. The bm25 weights already boost
 title/keywords/aliases over body, so a one-word query against a doc's
 `title` or `keywords` is typically the right first move.
 

package/agent-assets/skills/external-services/SKILL.delegated.claude.md

@@ -128,7 +128,7 @@ curl -s -X POST http://localhost:8321/api/integrations/google_calendar/exec \
 `needsConfirmation` plan, or skip the dance for self-only events you
 already greenlit.)
 
-`outputSchema` is **required** (4 KB cap). Defaults: `maxToolCalls=7`,
+`outputSchema` is **required** (4 KB cap). Defaults: `maxToolCalls=8`,
 `maxBudgetUsd=0.05`, `timeoutMs=60000`. Bump up to 15 / 0.50 / 300000
 for genuinely larger intents.
 
@@ -176,32 +176,7 @@ freshness matters, and never on a destructive-confirm second call.
   know about, call `POST /api/notify` with a one-line summary. The
   daemon does NOT auto-notify — it's an explicit choice.
 
-### Error envelope
-
-`/exec` extends the direct-mode envelope with delegated-mode fields.
-Discriminator: `body.mode === "delegated"`.
-
-| HTTP | `error` | retry? | What to do |
-|---|---|---|---|
-| 400 | `validation_error` / `schema_too_large` | no | Fix the request body. |
-| 409 | `mode_mismatch` | no | Calendar isn't delegated, OR your DM backend matches `delegatedBackend`. Re-read `integrations.md` and stop. |
-| 409 | `precondition` | no | Mode/backend flipped during the queue wait. Re-check state and re-plan. |
-| 429 | `task_quota_exhausted` | no | Daily cap reached; wait or surface. |
-| 502 | `parse_error` / `schema_violation` | no (daemon already retried once) | Consider a simpler schema. |
-| 502 | `tool_unavailable` | no | No connector tool fits the intent. Surface the gap. |
-| 502 | `tool_failed` | maybe | Connector tool returned an error. Surface `body.message` verbatim; retry only if clearly transient. |
-| 502 | `auth_error` | no | Connector signed out. Tell the user to re-authenticate it. |
-| 502 | `policy_violation` | no | Subprocess attempted a tool outside the per-task allowlist (anti-injection). |
-| 502 | `loop_aborted` | no | `maxToolCalls` exceeded. Bump the cap or simplify. |
-| 502 | `budget_exhausted` | no | `maxBudgetUsd` exceeded. Caller can raise the cap. |
-| 502 | `post_write_format_failure` | no | Write succeeded; formatting failed. Side effect is real — surface with the partial trace. |
-| 503 | `delegated_proxy_busy` | yes | Daemon queue saturated. Backoff a few seconds, try once. |
-| 503 | `task_mode_disabled` | no | Operator turned the kill switch off. Stop. |
-| 504 | `timeout` | yes (1×) | Wall-clock fired. Retry once if intent was simple. |
-| 500 | `subprocess_crashed` | no | Unhandled exception inside the subprocess. Surface and stop. |
-
-Always preserve `body.message` verbatim when reporting to the user — it
-carries the connector's own language.
+{{> ref:exec-errors }}
 <!-- /service:calendar -->
 
 ---
@@ -286,72 +261,10 @@ existing rows (dedup). → Full guide: load the `agent-create` or `schedule` ski
 
 ---
 
-## One-Shot Scheduling
+## Scheduling & Skills CRUD
 
-Schedule a future DM or agent task. Use `<current_time>` to resolve relative times into absolute ISO 8601 with offset.
-
-### DM vs Agent Task
-
-| Criterion | `/api/schedule/dm` (free) | `/api/schedule` (~$0.03) |
-|---|---|---|
-| Message text knowable now? | Yes | No — needs lookup/decision at execution |
-| Needs API data at execution? | No | Yes |
-| Multi-step action? | No | Yes |
-| Conditional on state that may change? | No | Yes |
-
-**Default to DM** — every agent wake-up costs money and context.
-
-### Context-loss warning
-
-> The wake-up agent has NO memory of why it was scheduled — the `description` field is its only context.
-
-Include: **What** (verb + object), **Why** (trigger/reason), **Who/What** (names, IDs, URLs), **Expected output** (what success looks like).
-
-Bad: `"Meeting prep"` — which meeting? when? what to prepare? The wake-up agent will skip ambiguous descriptions.
-
-### POST /api/schedule/dm — Pre-composed DM
-```bash
-curl -s -X POST http://localhost:8321/api/schedule/dm \
-  -H 'Content-Type: application/json' \
-  -d '{"time": "2026-04-06T16:00:00-04:00", "message": "Reminder: Design review in 30 min.", "platform": "slack"}'
-```
-
-### POST /api/schedule — Agent task
-```bash
-curl -s -X POST http://localhost:8321/api/schedule \
-  -H 'Content-Type: application/json' \
-  -d '{"time": "2026-04-06T16:00:00-04:00", "taskType": "wake", "prompt": "Check PR #42 status and notify user.", "description": "PR #42 status check", "tier": "medium", "taskContext": {"scheduledBy": "dm_conversation"}}'
-```
-Fields: `time` (required), `taskType` (`wake`), `prompt` (required — the agent instruction, ≤8000 chars), `description` (optional label, ≤200 chars), `tier` (`lite`/`medium`/`high`) **or** `model` (registered id like `claude-opus-4-8`, legacy alias `sonnet`/`opus`, or composite `<backendId>/<modelId>`) — mutually exclusive, `taskContext` (optional metadata). See the `schedule` skill body for the full surface and `/api/schedule/options` for the live model list.
-
-### Manage pending items
-```bash
-curl -s "http://localhost:8321/api/schedule?status=pending"                         # list
-curl -s -X PATCH http://localhost:8321/api/schedule/42 \
-  -H 'Content-Type: application/json' -d '{"time": "2026-04-06T17:00:00-04:00"}'   # edit
-curl -s -X DELETE http://localhost:8321/api/schedule/42                              # cancel
-```
-Editable: `time`, `description`, `message` (dm only), `tier` (or `model`, mutually exclusive — pass `null` to clear), `taskContext`. Only `pending` items.
-
-### Time discipline
-- Absolute ISO 8601 with offset required — no relative times.
-- Do not schedule during quiet hours (default 22:00–08:00, configurable) unless critical.
-- Maximum 5 wake-ups per execution.
-
----
-
-## Skills Management
-
-User-authored skills: `~/.personal-agent/skills/{slug}/SKILL.md`. Built-in skills are read-only (403). Slug: lowercase kebab-case `[a-z0-9][a-z0-9-]*`, 1–64 chars.
-
-```bash
-curl -s http://localhost:8321/api/skills                                            # list all
-curl -s http://localhost:8321/api/skills/todo-digest                                # read one
-curl -s -X POST http://localhost:8321/api/skills \
-  -H 'Content-Type: application/json' \
-  -d '{"name": "todo-digest", "description": "Summarize today.md", "content": "# TODO Digest\n...", "allowedTools": ["Bash(curl *)", "Read"]}'
-curl -s -X PUT http://localhost:8321/api/skills/todo-digest \
-  -H 'Content-Type: application/json' -d '{"description": "New description"}'      # update
-curl -s -X DELETE http://localhost:8321/api/skills/todo-digest                      # delete
-```
-Always `GET /api/skills` before creating (check name collisions). **Omit frontmatter** from `content` — the API injects it.
+One-shot DMs / agent wake-ups (`/api/schedule`, `/api/schedule/dm`) and
+user-authored Skills CRUD (`/api/skills`) work identically to direct
+mode — they are never proxied. Load the `schedule` skill for scheduling
+and the `agent-create` skill for recurring work; this variant does not
+mirror those surfaces.