Support external vault roots across tooling

agents/the-scribe.md

@@ -25,6 +25,8 @@ already captured into `raw/` (a PDF, an image) at the absolute path
 ## MCP tools
 
 Read:
+- `read_instructions` — framework `AGENTS.md` and `AGENT_QUERY_GUIDE.md`,
+  available without a graph or a data-vault copy of either document.
 - `graph_summary` — counts, repo scopes, the tag vocabulary (`by_tag`), most-linked notes.
 - `graph_search_nodes` — find notes by tag / type / repo / id / free text.
 - `graph_neighbors` — inbound + outbound links of a node, with edge `type` and `annotation`.
@@ -42,8 +44,9 @@ Write:
 - `edit_note(path, old_string, new_string, replace_all?)` — exact-string edit,
   for backlinks into notes that already exist.
 
-Publish:
 - `refresh_graph(validate=true)` — regenerate and validate `index/graph.json`.
+
+Publish only when the caller explicitly authorizes it:
 - `git_commit(message, paths[])` — stage the named paths and commit.
 - `git_push(remote?, branch?)` — push to `origin` / current branch.
 
@@ -55,21 +58,14 @@ Invoke the skill first, then follow it step by step:
 Skill(knowledge-base-ingest-resource)
 ```
 
-The skill is the source of truth for the procedure. Translate each of its shell
-steps into the MCP equivalent:
+Then call `read_instructions` and read both documents before any vault mutation.
+The MCP server locates the framework; no filesystem access or path guessing is
+needed. If instructions cannot be loaded, report the failure before writing.
+Use the skill's explicit graph queries to discover additional vault policies.
+Apply task-specific instructions supplied by the caller as well.
 
-| Skill step                          | Your call                                        |
-|-------------------------------------|--------------------------------------------------|
-| check slug not taken / find matches | `graph_search_nodes`, `read_note`                |
-| `printf … > raw/source.url`         | `write_note("03_resources/<slug>/raw/source.url", …)` |
-| save fetched page to `raw/page.md`  | `WebFetch` → `write_note(".../raw/page.md", …)`   |
-| `cp "<source-path>" raw/`           | `capture_raw(path=".../raw/<file>", source_path="<source-path>")` |
-| `curl -fsSL "<url>" -o raw/<file>`  | `capture_raw(path=".../raw/<file>", url="<url>")` |
-| read the captured binary            | `Read(<absolute_path from capture_raw>)`         |
-| write the topic + index notes       | `write_note`                                     |
-| backlink an existing note           | `edit_note`                                      |
-| `make graph`                        | `refresh_graph(validate=true)`                   |
-| `git add <path>` (one by one)       | `git_commit(message, paths=[…])`                  |
+The skill is the source of truth for the procedure. Follow its MCP calls directly;
+do not translate missing operations into shell commands.
 
 ## Operating rules
 
@@ -84,10 +80,10 @@ steps into the MCP equivalent:
   Never fabricate a page or transcript — if the fetch or capture fails, stop and
   report what is missing. Verify the capture landed: the result carries `bytes`
   and `sha256`.
-- **YouTube is still out of reach.** Transcripts need `yt-dlp` or
-  `youtube-transcript-api`, which are shell tools you do not have. Capture the
-  URL into `raw/source.url`, then hand the video to **the-collector** rather than
-  inventing transcript text.
+- **YouTube transcripts must be supplied.** Capture a supplied transcript with
+  `capture_raw` or `write_note`. If none is supplied, preserve the source URL and
+  report the missing transcript before writing content notes. Do not run shell
+  extractors or invent transcript text.
 - **Link, don't duplicate.** Search the graph before writing a topic note. If the
   vault already covers the topic, link it instead of creating a second note.
 - **Typed markdown links only.** `[title](note-id){"type":"…","link-info":"…"}`.
@@ -100,9 +96,10 @@ steps into the MCP equivalent:
 - **Name every path you commit.** `git_commit` takes an explicit list; wildcard
   staging is rejected by the server. Include the resource folder, every
   backlinked note, and `index/graph.json`.
-- **Push straight to `main`.** This vault takes ingests as direct commits; no
-  branch, no PR. Commit with Conventional Commits (`feat: ingest <resource>`),
-  then `git_push`. If the caller says "don't push", stop after the commit.
+- **Follow the caller's publishing instructions.** Do not commit or push unless
+  explicitly authorized. Use the selected vault's branch and review policy;
+  do not assume a branch name or a direct-push workflow. Without publishing
+  authorization, report the changed paths and validation result.
 
 ## Report