From ca51546be03c8adb6882271045ffe744adac69f2 Mon Sep 17 00:00:00 2001
From: Owen <owenrees.dev@gmail.com>
Date: Tue, 11 Aug 2026 20:48:00 +0200
Subject: [PATCH] allow graft mcp to be used within opencode

---
 .gitignore    |  3 ++
 .ignore       |  5 +++
 AGENTS.md     | 97 ++++++++++++++++++++++++++++++++++++++-------------
 opencode.json | 10 ++++++
 4 files changed, 91 insertions(+), 24 deletions(-)
 create mode 100644 .ignore
 create mode 100644 opencode.json

diff --git a/.gitignore b/.gitignore
index ad84ffb..354fd11 100644
--- a/.gitignore
+++ b/.gitignore
@@ -35,3 +35,6 @@ chesstrainer-*.tar
 npm-debug.log
 /assets/node_modules/
 
+
+# graft's local graph cache — regenerable, not committed (run `graft build`).
+graft/
diff --git a/.ignore b/.ignore
new file mode 100644
index 0000000..615e581
--- /dev/null
+++ b/.ignore
@@ -0,0 +1,5 @@
+# graft's cards are gitignored but should stay greppable: ripgrep reads
+# .ignore before .gitignore, so this re-admits the tree to search only.
+!graft/
+graft/.cache/
+graft/.graph/
diff --git a/AGENTS.md b/AGENTS.md
index 73a6e08..c5e7277 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -1,5 +1,49 @@
 This is a web application written using the Phoenix web framework.
 
+<!-- graft:start -->
+
+## Graft — repo context graph
+
+This repo is indexed in `graft/`: small linked markdown nodes that explain each
+system and carry exact file:line spans, kept in sync with the code through git.
+
+For ANY task here — understanding how something works, finding where code lives,
+or scoping a change — get context from the graph before grepping or opening
+source files. Re-ask freely (it's cheap) and reuse literal identifiers you
+already have (symbol, error string, file name) as the query. New to this repo?
+Run `graft map` first — a token-budgeted orientation (dir clusters, hubs,
+hotspots), no LLM, no key.
+
+- Run `graft ask "<your question>" --source` → ranked nodes with the relevant
+  code spans inlined (each hit's ≤8-line crux by default; `--full` for whole
+  definitions when the crux isn't enough). Match the tool to the task shape:
+  for understanding or editing, the top node IS the answer — cite its
+  `covers:` file:line spans and edit straight from `--source`. For
+  exhaustive tasks ("every occurrence / every caller of this pattern"), ranked
+  results are top-N, not complete — run `graft grep "<literal>"` instead
+  (exhaustive over indexed files, grouped by enclosing symbol), falling back
+  to raw `grep -rn` only for unindexed files.
+- `graft skeleton <file>` → every definition's signature + span, ~10× cheaper
+  than reading the file; use it to skim an API surface.
+- `graft callers <symbol>` gives precomputed, exact edges — who calls this.
+  Add `--direction out` for what it calls, or `--depth N` to walk
+  transitively for the full blast radius. For structural questions, skip
+  ranking and use this directly.
+- Or browse: `graft/INDEX.md` lists every node; follow the links.
+- Monorepos and folders of multiple repos rank fairly across sub-projects —
+  hits carry `[scope/]` labels naming which one they're from. Narrow with
+  `graft ask "<task>" --in <scope>/` once you know where you're working.
+
+If a returned span is truncated ("+N more lines"), open the file at that exact
+range before finalizing. Only open source files when a node genuinely lacks a
+needed detail, and then at the exact file:line the node points to — never
+re-read whole files.
+
+After big code changes, refresh the graph with `graft build` (deterministic,
+no API key, $0).
+
+<!-- graft:end -->
+
 ## Project guidelines
 
 - Use `mix precommit` alias when you are done with all changes and fix any pending issues
@@ -16,7 +60,7 @@ This is a web application written using the Phoenix web framework.
 - Out of the box, `core_components.ex` imports an `<.icon name="hero-x-mark" class="w-5 h-5"/>` component for hero icons. **Always** use the `<.icon>` component for icons, **never** use `Heroicons` modules or similar
 - **Always** use the imported `<.input>` component for form inputs from `core_components.ex` when available. `<.input>` is imported and using it will save steps and prevent errors
 - If you override the default input classes (`<.input class="myclass px-2 py-1 rounded-lg">)`) class with your own values, no default classes are inherited, so your
-custom classes must fully style the input
+  custom classes must fully style the input
 
 ### JS and CSS guidelines
 
@@ -43,10 +87,10 @@ custom classes must fully style the input
 - Ensure **clean typography, spacing, and layout balance** for a refined, premium look
 - Focus on **delightful details** like hover effects, loading states, and smooth page transitions
 
-
 <!-- usage-rules-start -->
 
 <!-- phoenix:elixir-start -->
+
 ## Elixir guidelines
 
 - Elixir lists **do not support index based access via the access syntax**
@@ -64,7 +108,7 @@ custom classes must fully style the input
       Enum.at(mylist, i)
 
 - Elixir variables are immutable, but can be rebound, so for block expressions like `if`, `case`, `cond`, etc
-  you *must* bind the result of the expression to a variable if you want to use it and you CANNOT rebind the result inside the expression, ie:
+  you _must_ bind the result of the expression to a variable if you want to use it and you CANNOT rebind the result inside the expression, ie:
 
       # INVALID: we are rebinding inside the `if` and the result never gets assigned
       if connected?(socket) do
@@ -97,13 +141,14 @@ custom classes must fully style the input
 - **Avoid** `Process.sleep/1` and `Process.alive?/1` in tests
   - Instead of sleeping to wait for a process to finish, **always** use `Process.monitor/1` and assert on the DOWN message:
 
-      ref = Process.monitor(pid)
-      assert_receive {:DOWN, ^ref, :process, ^pid, :normal}
+    ref = Process.monitor(pid)
+    assert_receive {:DOWN, ^ref, :process, ^pid, :normal}
 
-   - Instead of sleeping to synchronize before the next call, **always** use `_ = :sys.get_state/1` to ensure the process has handled prior messages
-<!-- phoenix:elixir-end -->
+  - Instead of sleeping to synchronize before the next call, **always** use `_ = :sys.get_state/1` to ensure the process has handled prior messages
+  <!-- phoenix:elixir-end -->
 
 <!-- phoenix:phoenix-start -->
+
 ## Phoenix guidelines
 
 - Remember Phoenix router `scope` blocks include an optional alias which is prefixed for all routes within the scope. **Always** be mindful of this when creating routes within a scope to avoid duplicate module prefixes.
@@ -122,6 +167,7 @@ custom classes must fully style the input
 <!-- phoenix:phoenix-end -->
 
 <!-- phoenix:ecto-start -->
+
 ## Ecto Guidelines
 
 - **Always** preload Ecto associations in queries when they'll be accessed in templates, ie a message that needs to reference the `message.user.email`
@@ -134,6 +180,7 @@ custom classes must fully style the input
 <!-- phoenix:ecto-end -->
 
 <!-- phoenix:html-start -->
+
 ## Phoenix HTML guidelines
 
 - Phoenix templates **always** use `~H` or .html.heex files (known as HEEx), **never** use `~E`
@@ -163,7 +210,7 @@ custom classes must fully style the input
           ...
       <% end %>
 
-- HEEx require special tag annotation if you want to insert literal curly's like `{` or `}`. If you want to show a textual code snippet on the page in a `<pre>` or `<code>` block you *must* annotate the parent tag with `phx-no-curly-interpolation`:
+- HEEx require special tag annotation if you want to insert literal curly's like `{` or `}`. If you want to show a textual code snippet on the page in a `<pre>` or `<code>` block you _must_ annotate the parent tag with `phx-no-curly-interpolation`:
 
       <code phx-no-curly-interpolation>
         let obj = {key: "val"}
@@ -196,26 +243,28 @@ custom classes must fully style the input
 
   **Always** do this:
 
-      <div id={@id}>
-        {@my_assign}
-        <%= if @some_block_condition do %>
-          {@another_assign}
-        <% end %>
-      </div>
+        <div id={@id}>
+          {@my_assign}
+          <%= if @some_block_condition do %>
+            {@another_assign}
+          <% end %>
+        </div>
 
   and **Never** do this – the program will terminate with a syntax error:
 
-      <%!-- THIS IS INVALID NEVER EVER DO THIS --%>
-      <div id="<%= @invalid_interpolation %>">
-        {if @invalid_block_construct do}
-        {end}
-      </div>
-<!-- phoenix:html-end -->
+        <%!-- THIS IS INVALID NEVER EVER DO THIS --%>
+        <div id="<%= @invalid_interpolation %>">
+          {if @invalid_block_construct do}
+          {end}
+        </div>
+
+  <!-- phoenix:html-end -->
 
 <!-- phoenix:liveview-start -->
+
 ## Phoenix LiveView guidelines
 
-- **Never** use the deprecated `live_redirect` and `live_patch` functions, instead **always** use the `<.link navigate={href}>` and  `<.link patch={href}>` in templates, and `push_navigate` and `push_patch` functions LiveViews
+- **Never** use the deprecated `live_redirect` and `live_patch` functions, instead **always** use the `<.link navigate={href}>` and `<.link patch={href}>` in templates, and `push_navigate` and `push_patch` functions LiveViews
 - **Avoid LiveComponent's** unless you have a strong, specific need for them
 - LiveViews should be named like `AppWeb.WeatherLive`, with a `Live` suffix. When you go to add LiveView routes to the router, the default `:browser` scope is **already aliased** with the `AppWeb` module, so you can just do `live "/weather", WeatherLive`
 
@@ -235,7 +284,7 @@ custom classes must fully style the input
         </div>
       </div>
 
-- LiveView streams are *not* enumerable, so you cannot use `Enum.filter/2` or `Enum.reject/2` on them. Instead, if you want to filter, prune, or refresh a list of items on the UI, you **must refetch the data and re-stream the entire stream collection, passing reset: true**:
+- LiveView streams are _not_ enumerable, so you cannot use `Enum.filter/2` or `Enum.reject/2` on them. Instead, if you want to filter, prune, or refresh a list of items on the UI, you **must refetch the data and re-stream the entire stream collection, passing reset: true**:
 
       def handle_event("filter", %{"filter" => filter}, socket) do
         # re-fetch the messages based on the filter
@@ -248,7 +297,7 @@ custom classes must fully style the input
          |> stream(:messages, messages, reset: true)}
       end
 
-- LiveView streams *do not support counting or empty states*. If you need to display a count, you must track it using a separate assign. For empty states, you can use Tailwind classes:
+- LiveView streams _do not support counting or empty states_. If you need to display a count, you must track it using a separate assign. For empty states, you can use Tailwind classes:
 
       <div id="tasks" phx-update="stream">
         <div class="hidden only:block">No tasks yet</div>
@@ -446,4 +495,4 @@ And **never** do this:
 - **Never** use `<.form let={f} ...>` in the template, instead **always use `<.form for={@form} ...>`**, then drive all form references from the form assign as in `@form[:field]`. The UI should **always** be driven by a `to_form/2` assigned in the LiveView module that is derived from a changeset
 <!-- phoenix:liveview-end -->
 
-<!-- usage-rules-end -->
\ No newline at end of file
+<!-- usage-rules-end -->
diff --git a/opencode.json b/opencode.json
new file mode 100644
index 0000000..17f3f8d
--- /dev/null
+++ b/opencode.json
@@ -0,0 +1,10 @@
+{
+  "$schema": "https://opencode.ai/config.json",
+  "mcp": {
+    "graft": {
+      "type": "local",
+      "command": ["npx", "-y", "@nanonets/graft", "mcp"],
+      "enabled": true
+    }
+  }
+}