openspec to spectr

.claude/commands/spectr/apply.md

@@ -0,0 +1,24 @@
+---
+name: Spectr: Apply
+description: Implement an approved Spectr change and keep tasks in sync.
+category: Spectr
+tags: [spectr, apply]
+---
+<!-- spectr:START -->
+**Guardrails**
+- Favor straightforward, minimal implementations first and add complexity only when it is requested or clearly required.
+- Keep changes tightly scoped to the requested outcome.
+- Refer to `spectr/AGENTS.md` (located inside the `spectr/` directory—run `ls spectr` or `spectr update` if you don't see it) if you need additional Spectr conventions or clarifications.
+
+**Steps**
+Track these steps as TODOs and complete them one by one.
+1. Read `spectr/changes/<id>/proposal.md`, `design.md` (if present), and `tasks.md` to confirm scope and acceptance criteria.
+2. Work through tasks sequentially, keeping edits minimal and focused on the requested change.
+3. Confirm completion before updating statuses—make sure every item in `tasks.md` is finished.
+4. Update the checklist after all work is done so each task is marked `- [x]` and reflects reality.
+5. Reference `spectr list` or `spectr show <item>` when additional context is required.
+
+**Reference**
+- Use `spectr show <id> --json --deltas-only` if you need additional context from the proposal while implementing.
+
+<!-- spectr:END -->

.claude/commands/spectr/archive.md

@@ -0,0 +1,28 @@
+---
+name: Spectr: Archive
+description: Archive a deployed Spectr change and update specs.
+category: Spectr
+tags: [spectr, archive]
+---
+<!-- spectr:START -->
+**Guardrails**
+- Favor straightforward, minimal implementations first and add complexity only when it is requested or clearly required.
+- Keep changes tightly scoped to the requested outcome.
+- Refer to `spectr/AGENTS.md` (located inside the `spectr/` directory—run `ls spectr` or `spectr update` if you don't see it) if you need additional Spectr conventions or clarifications.
+
+**Steps**
+1. Determine the change ID to archive:
+   - If this prompt already includes a specific change ID (for example inside a `<ChangeId>` block populated by slash-command arguments), use that value after trimming whitespace.
+   - If the conversation references a change loosely (for example by title or summary), run `spectr list` to surface likely IDs, share the relevant candidates, and confirm which one the user intends.
+   - Otherwise, review the conversation, run `spectr list`, and ask the user which change to archive; wait for a confirmed change ID before proceeding.
+   - If you still cannot identify a single change ID, stop and tell the user you cannot archive anything yet.
+2. Validate the change ID by running `spectr list` (or `spectr show <id>`) and stop if the change is missing, already archived, or otherwise not ready to archive.
+3. Run `spectr archive <id> --yes` so the CLI moves the change and applies spec updates without prompts.
+4. Review the command output to confirm the target specs were updated and the change landed in `spectr/changes/archive/`.
+5. Validate with `spectr validate --strict` and inspect with `spectr show <id>` if anything looks off.
+
+**Reference**
+- Use `spectr list` to confirm change IDs before archiving.
+- Inspect refreshed specs with `spectr list --specs` and address any validation issues before handing off.
+
+<!-- spectr:END -->

.claude/commands/spectr/proposal.md

@@ -0,0 +1,28 @@
+---
+name: Spectr: Proposal
+description: Scaffold a new Spectr change and validate strictly.
+category: Spectr
+tags: [spectr, change]
+---
+<!-- spectr:START -->
+**Guardrails**
+- Favor straightforward, minimal implementations first and add complexity only when it is requested or clearly required.
+- Keep changes tightly scoped to the requested outcome.
+- Refer to `spectr/AGENTS.md` (located inside the `spectr/` directory—run `ls spectr` or `spectr update` if you don't see it) if you need additional Spectr conventions or clarifications.
+- Identify any vague or ambiguous details and ask the necessary follow-up questions before editing files.
+
+**Steps**
+1. Review `spectr/project.md`, run `spectr list` and `spectr list --specs`, and inspect related code or docs (e.g., via `rg`/`ls`) to ground the proposal in current behaviour; note any gaps that require clarification.
+2. Choose a unique verb-led `change-id` and scaffold `proposal.md`, `tasks.md`, and `design.md` (when needed) under `spectr/changes/<id>/`.
+3. Map the change into concrete capabilities or requirements, breaking multi-scope efforts into distinct spec deltas with clear relationships and sequencing.
+4. Capture architectural reasoning in `design.md` when the solution spans multiple systems, introduces new patterns, or demands trade-off discussion before committing to specs.
+5. Draft spec deltas in `spectr/changes/<id>/specs/<capability>/spec.md` (one folder per capability) using `## ADDED|MODIFIED|REMOVED Requirements` with at least one `#### Scenario:` per requirement and cross-reference related capabilities when relevant.
+6. Draft `tasks.md` as an ordered list of small, verifiable work items that deliver user-visible progress, include validation (tests, tooling), and highlight dependencies or parallelizable work.
+7. Validate with `spectr validate <id> --strict` and resolve every issue before sharing the proposal.
+
+**Reference**
+- Use `spectr show <id> --json --deltas-only` or `spectr show <spec> --type spec` to inspect details when validation fails.
+- Search existing requirements with `rg -n "Requirement:|Scenario:" spectr/specs` before writing new ones.
+- Explore the codebase with `rg <keyword>`, `ls`, or direct file reads so proposals align with current implementation realities.
+
+<!-- spectr:END -->

.claude/settings.json

@@ -17,101 +17,101 @@
     "deny": []
   },
   "hooks": {
-    "PreCompact": [
+    "SessionStart": [
       {
         "matcher": "",
         "hooks": [
           {
             "type": "command",
-            "command": "conclaude PreCompact"
+            "command": "conclaude SessionStart"
           }
         ]
       }
     ],
-    "SessionStart": [
+    "PostToolUse": [
       {
         "matcher": "",
         "hooks": [
           {
             "type": "command",
-            "command": "conclaude SessionStart"
+            "command": "conclaude PostToolUse"
           }
         ]
       }
     ],
-    "SubagentStop": [
+    "UserPromptSubmit": [
       {
         "matcher": "",
         "hooks": [
           {
             "type": "command",
-            "command": "conclaude SubagentStop"
+            "command": "conclaude UserPromptSubmit"
           }
         ]
       }
     ],
-    "PreToolUse": [
+    "Notification": [
       {
         "matcher": "",
         "hooks": [
           {
             "type": "command",
-            "command": "conclaude PreToolUse"
+            "command": "conclaude Notification"
           }
         ]
       }
     ],
-    "SessionEnd": [
+    "PreCompact": [
       {
         "matcher": "",
         "hooks": [
           {
             "type": "command",
-            "command": "conclaude SessionEnd"
+            "command": "conclaude PreCompact"
           }
         ]
       }
     ],
-    "Notification": [
+    "SubagentStop": [
       {
         "matcher": "",
         "hooks": [
           {
             "type": "command",
-            "command": "conclaude Notification"
+            "command": "conclaude SubagentStop"
           }
         ]
       }
     ],
-    "Stop": [
+    "PreToolUse": [
       {
         "matcher": "",
         "hooks": [
           {
             "type": "command",
-            "command": "conclaude Stop"
+            "command": "conclaude PreToolUse"
           }
         ]
       }
     ],
-    "PostToolUse": [
+    "Stop": [
       {
         "matcher": "",
         "hooks": [
           {
             "type": "command",
-            "command": "conclaude PostToolUse"
+            "command": "conclaude Stop"
           }
         ]
       }
     ],
-    "UserPromptSubmit": [
+    "SessionEnd": [
       {
         "matcher": "",
         "hooks": [
           {
             "type": "command",
-            "command": "conclaude UserPromptSubmit"
+            "command": "conclaude SessionEnd"
           }
         ]
       }

.conclaude.yaml

@@ -5,11 +5,7 @@
 
 # Stop hook configuration - runs when Claude is about to stop
 stop:
-  # Commands to run during Stop hook
-  # Each line is executed as a separate bash command
-  run: ""
-
-  # Alternative structured command format with optional custom error messages
+  # Structured command format with optional custom error messages
   # Each command can have its own error message, and control output display
   commands: []
   # Examples:

.config/hypr/hyprland.conf

@@ -29,8 +29,8 @@ env = DEFAULT_BROWSER,zen
 env = GBM_BACKEND,nvidia-drm
 env = __GLX_VENDOR_LIBRARY_NAME,nvidia
 # env = SDL_VIDEODRIVER,wayland
-# env = GDK_BACKEND,wayland,x11,*
-# env = GTK_THEME,Adwaita:dark
+env = GDK_BACKEND,wayland,x11,*
+env = GTK_THEME,Adwaita:dark
 env = CLUTTER_BACKEND,wayland
 env = XCURSOR_SIZE,24
 
@@ -103,7 +103,7 @@ windowrulev2 = center, class:Xdg-desktop-portal-gtk, focus:0, tile:1
 windowrulev2 = tile, class:^(Spotify)$
 windowrulev2 = workspace 9, class:^(Spotify)$
 windowrulev2 = workspace 10, class:^(Chromium-browser), focus:0$
-windowrulev2 = stayfocused, class:^gcr-prompter-
+windowrule = stayfocused, class:(gcr-prompter-)(.*), focus:1
 
 # Key bindings https://wiki.hyprland.org/Configuring/Binds/
 bind = $mainMod, B,exec, $browser
@@ -118,6 +118,7 @@ bind = $mainMod, F, fullscreen,0
 bind = $mainMod, P, pseudo, # dwindle
 bind = $mainMod, T, togglesplit, # dwindle
 bind = $mainMod SHIFT, C, exec, $color_picker
+bind = , mouse:274, exec, ;
 
 # Move focus with mainMod + arrow keys
 bind = $mainMod, H, movefocus, l

.config/kitty/kitty.conf

@@ -11,3 +11,19 @@ cursor_trail_decay 0.03 0.1
 editor nvim 
 allow_hyperlinks yes
 linux_display_server auto
+
+map ctrl+shift+e launch --type=overlay --stdin-source=@screen_scrollback nvim -
+
+tab_separator "   "
+tab_bar_style separator
+tab_title_max_length 0
+tab_powerline_style slanted
+tab_title_template " {f'{title[:4]}' if title.rindex(title[-1]) + 1 > 30 else (title.center(6) if (title.rindex(title[-1]) + 1) % 2 == 0 else title.center(5))}"
+
+active_tab_font_style   bold
+inactive_tab_font_style bold
+
+active_tab_foreground   #6c6c6c
+active_tab_background   #000000
+inactive_tab_foreground #303030
+inactive_tab_background #000000

.config/wezterm/wezterm.lua

@@ -0,0 +1,43 @@
+local wezterm = require 'wezterm'
+local io = require 'io'
+local os = require 'os'
+local act = wezterm.action
+
+wezterm.on('trigger-vim-with-scrollback', function(window, pane)
+	-- Retrieve the text from the pane
+	local text = pane:get_lines_as_text(pane:get_dimensions().scrollback_rows)
+
+	-- Create a temporary file to pass to vim
+	local name = os.tmpname()
+	local f = io.open(name, 'w+')
+	f:write(text)
+	f:flush()
+	f:close()
+
+	-- Open a new window running vim and tell it to open the file
+	window:perform_action(
+		act.SpawnCOmmandInPane {
+			args = { 'nvim', name },
+		},
+		pane
+	)
+
+	-- Wait "enough" time for vim to read the file before we remove it.
+	-- The window creation and process spawn are asynchronous wrt. running
+	-- this script and are not awaitable, so we just pick a number.
+	--
+	-- Note: We don't strictly need to remove this file, but it is nice
+	-- to avoid cluttering up the temporary directory.
+	wezterm.sleep_ms(1000)
+	os.remove(name)
+end)
+
+return {
+	keys = {
+		{
+			key = 'E',
+			mods = 'SHIFT|CTRL',
+			action = act.EmitEvent 'trigger-vim-with-scrollback',
+		},
+	},
+}