Remove zsh-vi-mode plugin from .zshrc

.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/mcp/.mcp.json

@@ -0,0 +1,19 @@
+{
+  "mcpServers": {
+    "context7": {
+      "type": "stdio",
+      "command": "npx",
+      "args": [
+        "-y",
+        "@upstash/context7-mcp"
+      ],
+      "env": {}
+    },
+    "nixos": {
+      "command": "uvx",
+      "args": [
+        "mcp-nixos"
+      ]
+    }
+  }
+}

.claude/settings.json

@@ -0,0 +1,131 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(mkdir:*)",
+      "Bash(uv:*)",
+      "Bash(find:*)",
+      "Bash(mv:*)",
+      "Bash(grep:*)",
+      "Bash(npm:*)",
+      "Bash(ls:*)",
+      "Bash(cp:*)",
+      "Write",
+      "Edit",
+      "Bash(chmod:*)",
+      "Bash(touch:*)"
+    ],
+    "deny": []
+  },
+  "hooks": {
+    "PostToolUse": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "conclaude Hooks PostToolUse"
+          }
+        ]
+      }
+    ],
+    "PreCompact": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "conclaude Hooks PreCompact"
+          }
+        ]
+      }
+    ],
+    "UserPromptSubmit": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "conclaude Hooks UserPromptSubmit"
+          }
+        ]
+      }
+    ],
+    "Stop": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "conclaude Hooks Stop"
+          }
+        ]
+      }
+    ],
+    "PreToolUse": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "conclaude Hooks PreToolUse"
+          }
+        ]
+      }
+    ],
+    "SessionEnd": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "conclaude Hooks SessionEnd"
+          }
+        ]
+      }
+    ],
+    "SubagentStop": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "conclaude Hooks SubagentStop"
+          }
+        ]
+      }
+    ],
+    "SubagentStart": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "conclaude Hooks SubagentStart"
+          }
+        ]
+      }
+    ],
+    "SessionStart": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "conclaude Hooks SessionStart"
+          }
+        ]
+      }
+    ],
+    "Notification": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "conclaude Hooks Notification"
+          }
+        ]
+      }
+    ]
+  }
+}

.conclaude.yaml

@@ -0,0 +1,159 @@
+# yaml-language-server: $schema=https://github.com/connerohnesorge/conclaude/releases/latest/download/conclaude-schema.json
+# Conclaude Configuration Template
+#
+# This is a minimal example configuration file.
+# For full documentation of all options, run: conclaude config --docs
+# Or see the generated documentation from `cargo doc --open`
+
+# Stop hook - runs when Claude is about to stop
+stop:
+  commands: []
+  # Example:
+  # - run: "npm test"
+  #   showStdout: true
+  #   showStderr: true
+  #   showCommand: true  # Show "Executing command X/Y: npm test" (default: true)
+  #   message: "Tests failed"
+  #   maxOutputLines: 100
+  #   timeout: 300
+
+  infinite: false
+  infiniteMessage: "continue working on the task"
+
+# Subagent stop hook - runs when subagents finish
+subagentStop:
+  commands: {}
+  # Example:
+  # coder:
+  #   - run: "npm run lint"
+  #     showStdout: true
+  #     showCommand: true  # Show "Executing command X/Y: npm run lint" (default: true)
+  #     message: "Linting failed"
+  # test*:
+  #   - run: "npm test"
+  #     showStderr: true
+  #     showCommand: false  # Hide the "Executing command..." line
+
+# Pre-tool-use hook - file protection and tool validation
+preToolUse:
+  # Prevent files at repository root
+  preventRootAdditions: true
+  # Custom message for root additions block (supports {file_path} and {tool} placeholders)
+  # Example: "Files must go in src/. Cannot create {file_path} using {tool}."
+  preventRootAdditionsMessage: null
+
+  # Protected files (glob patterns)
+  uneditableFiles:
+    - ".conclaude.yml"
+    - ".conclaude.yaml"
+  # Examples:
+  # - "*.lock"
+  # - pattern: ".env*"
+  #   message: "Environment files contain secrets"
+  #
+  # Agent-specific protection examples (blocks specific subagents):
+  # - pattern: "spectr/changes/**/tasks.jsonc"
+  #   message: "Task files managed by orchestrator"
+  #   agent: "coder"  # Only blocks coder subagent
+  #
+  # - pattern: "src/**/*.test.ts"
+  #   message: "Test files managed by tester agent"
+  #   agent: "code*"  # Blocks coder, coder-v2, etc.
+  #
+  # - pattern: "docs/**"
+  #   agent: "*"  # Blocks all agents (same as omitting agent field)
+
+  # Prevent editing git-ignored files
+  preventUpdateGitIgnored: false
+
+  # Tool usage rules
+  toolUsageValidation: []
+  # Example:
+  # - tool: "Write"
+  #   pattern: "**/*.js"
+  #   action: "allow"
+  # - tool: "Bash"
+  #   commandPattern: "git push --force*"
+  #   action: "block"
+  #   message: "Force push not allowed"
+  #
+  # Agent-scoped rules (only apply to specific agents):
+  # - tool: "Bash"
+  #   pattern: ""
+  #   commandPattern: "rm -rf *"
+  #   action: "block"
+  #   agent: "coder"
+  #   message: "Coder agent cannot run destructive rm commands"
+  # - tool: "Write"
+  #   pattern: "**/*.test.ts"
+  #   action: "block"
+  #   agent: "coder"
+  #   message: "Coder agent should not modify test files"
+  # - tool: "*"
+  #   pattern: "src/**"
+  #   action: "block"
+  #   agent: "test*"
+  #   message: "Test agents cannot modify source files"
+  #
+  # Agent pattern examples:
+  #   - agent: "coder"    # Exact match - only "coder" subagent
+  #   - agent: "test*"    # Glob pattern - matches "tester", "test-runner"
+  #   - agent: "*"        # Wildcard - matches all agents (default if omitted)
+
+  # Directories where additions are prevented
+  preventAdditions: []
+  # Example: ["dist", "build"]
+
+# System notifications
+notifications:
+  enabled: false
+  hooks: []  # ["*"] for all, or ["Stop", "PreToolUse"]
+  showErrors: false
+  showSuccess: false
+  showSystemEvents: true
+
+# Permission request hook - auto-approve/deny tools
+# Uncomment to enable:
+#
+# permissionRequest:
+#   default: deny  # "allow" or "deny"
+#   allow:
+#     - "Read"
+#     - "Glob"
+#     - "Grep"
+#     - "Edit"
+#     - "Write"
+#   deny:
+#     - "BashOutput"
+#     - "KillShell"
+
+# User prompt submit hook - context injection based on prompt patterns
+# Automatically prepends context when prompts match patterns
+# Uncomment to enable:
+#
+# userPromptSubmit:
+#   contextRules:
+#     # Pattern-based context injection
+#     - pattern: "sidebar"
+#       prompt: |
+#         Make sure to read @.claude/contexts/sidebar.md before proceeding.
+#
+#     # Multiple patterns with regex alternation
+#     - pattern: "auth|login|authentication"
+#       prompt: |
+#         Review the authentication patterns in @.claude/contexts/auth.md
+#
+#     # Case-insensitive matching (using regex flag)
+#     - pattern: "(?i)database|sql|query"
+#       prompt: |
+#         Follow the database conventions in @.claude/contexts/database.md
+#
+#     # Disable a rule temporarily
+#     - pattern: "test"
+#       prompt: "Run tests before proceeding"
+#       enabled: false
+#
+#     # Explicit case-insensitive flag
+#     - pattern: "api"
+#       prompt: "Check API documentation first"
+#       caseInsensitive: true