@codyswann/lisa 1.0.5 → 1.1.0

package/all/copy-overwrite/.claude/commands/project/plan.md

@@ -109,7 +109,16 @@ For each task, use **TaskCreate** with:
 [Or "N/A - no user-facing changes"]
 
 ## Verification
-**Type:** `ui-recording` | `test-coverage` | `api-test` | `manual-check` | `documentation`
+**Type:** `test` | `ui-recording` | `test-coverage` | `api-test` | `manual-check` | `documentation`
+
+| Type | When to Use | Example |
+|------|-------------|---------|
+| `test` | Run specific tests | `bun run test -- src/services/user.spec.ts` |
+| `ui-recording` | UI/UX changes | `bun run playwright:test ...` |
+| `test-coverage` | Coverage threshold | `bun run test:cov -- --collectCoverageFrom='...'` |
+| `api-test` | API endpoints | `./scripts/verify/<task-name>.sh` |
+| `documentation` | Docs, README | `cat path/to/doc.md` |
+| `manual-check` | Config, setup | Command showing config exists |
 
 **Proof Command:**
 ```bash
@@ -118,6 +127,21 @@ For each task, use **TaskCreate** with:
 
 **Expected Output:**
 [What success looks like]
+
+## Learnings
+During implementation, collect any discoveries valuable for future developers:
+- Gotchas or unexpected behavior encountered
+- Edge cases that weren't obvious from requirements
+- Better approaches discovered during implementation
+- Patterns that should be reused or avoided
+- Documentation gaps or misleading information found
+
+**On task completion**, use `TaskUpdate` to save learnings:
+```
+TaskUpdate:
+  taskId: "<this-task-id>"
+  metadata: { learnings: ["Learning 1", "Learning 2", ...] }
+```
 ```
 
 **metadata**:
@@ -127,7 +151,7 @@ For each task, use **TaskCreate** with:
   "type": "bug|task|epic|story",
   "skills": ["/coding-philosophy", ...],
   "verification": {
-    "type": "test-coverage|ui-recording|api-test|manual-check|documentation",
+    "type": "test|ui-recording|test-coverage|api-test|manual-check|documentation",
     "command": "the proof command",
     "expected": "what success looks like"
   }
@@ -138,16 +162,6 @@ For each task, use **TaskCreate** with:
 
 After creating all tasks, use **TaskUpdate** with `addBlockedBy` to establish task order where needed.
 
-**Verification Type Reference:**
-
-| Type | When to Use | Example |
-|------|-------------|---------|
-| `ui-recording` | UI/UX changes | `bun run playwright:test ...` |
-| `test-coverage` | New code with tests | `bun run test:cov -- --collectCoverageFrom='...'` |
-| `api-test` | New API endpoints | `./scripts/verify/<task-name>.sh` |
-| `documentation` | Docs, README | `cat path/to/doc.md` |
-| `manual-check` | Config, setup | Command showing config exists |
-
 ## Step 5: Report
 
 Report: "Planning complete - X tasks created for project <project-name>"
@@ -157,3 +171,9 @@ Use **TaskList** to show the created tasks.
 ---
 
 **IMPORTANT**: Each task description should contain all necessary information from `brief.md` and `research.md` to complete in isolation. Tasks should be independent and as small in scope as possible.
+
+---
+
+## Next Step
+
+After completing this phase, tell the user: "To continue, run `/project:implement $ARGUMENTS`"

package/all/copy-overwrite/.claude/commands/project/reduce-max-lines-per-function.md

@@ -1,6 +1,6 @@
 ---
 description: Reduce max lines per function threshold and fix violations
-allowed-tools: Read, Write, Edit, Bash, Glob, Grep, Task, TaskCreate, TaskUpdate, TaskList, TaskGet
+allowed-tools: Read, Bash, Glob, Grep
 argument-hint: <max-lines-per-function-value>
 model: sonnet
 ---
@@ -11,66 +11,55 @@ Target threshold: $ARGUMENTS lines per function
 
 If no argument provided, prompt the user for a target.
 
-## Process
+## Step 1: Gather Requirements
 
-### Step 0: Check Project Context
+1. **Read current config** from eslint thresholds (eslint.thresholds.json or similar)
+2. **Run lint** with the new threshold to find violations:
+   ```bash
+   bun run lint 2>&1 | grep "max-lines-per-function"
+   ```
+3. **Note for each violation**:
+   - File path and line number
+   - Function name
+   - Current line count
 
-Check if there's an active project for task syncing:
+If no violations at $ARGUMENTS, report success and exit.
 
-```bash
-cat .claude-active-project 2>/dev/null
-```
-
-If a project is active, include `metadata: { "project": "<project-name>" }` in all TaskCreate calls.
-
-### Step 1: Locate Configuration
-
-Read the eslint thresholds config (`eslint.thresholds.json` or similar).
+## Step 2: Generate Brief
 
-### Step 2: Update Threshold
+Compile findings into a detailed brief:
 
-Set the `maxLinesPerFunction` threshold to $ARGUMENTS (e.g., `"maxLinesPerFunction": $ARGUMENTS`).
-
-### Step 3: Identify Violations
-
-Run lint to find all functions exceeding the new threshold. Note file path, function name, and current line count.
-
-If no violations, report success and exit.
+```
+Reduce max lines per function threshold to $ARGUMENTS.
 
-### Step 4: Create Task List
+## Functions Exceeding Threshold (ordered by line count)
 
-Create a task for each function needing refactoring, ordered by line count (highest first).
+1. src/services/user.ts:processUser (95 lines, target: $ARGUMENTS)
+   - Line 45, function spans lines 45-140
+2. src/utils/helpers.ts:validateInput (82 lines, target: $ARGUMENTS)
+   - Line 23, function spans lines 23-105
+...
 
-Each task should have:
-- **subject**: "Reduce lines in [function-name]" (imperative form)
-- **description**: File path and line number, function name, current line count, target threshold, refactoring strategies
-- **activeForm**: "Reducing lines in [function-name]" (present continuous)
-- **metadata**: `{ "project": "<active-project>" }` if project context exists
+## Configuration Change
+- File: eslint.thresholds.json
+- Change: maxLinesPerFunction to $ARGUMENTS
 
-Refactoring strategies:
+## Refactoring Strategies
 - **Extract functions**: Break function into smaller named functions
 - **Early returns**: Reduce nesting with guard clauses
 - **Extract conditions**: Move complex boolean logic into named variables
 - **Use lookup tables**: Replace complex switch/if-else chains with object maps
 - **Consolidate logic**: Merge similar code paths
 
-### Step 5: Parallel Execution
+## Acceptance Criteria
+- All functions at or below $ARGUMENTS lines
+- `bun run lint` passes with no max-lines-per-function violations
 
-Launch **up to 5 sub-agents** using the `code-simplifier` subagent to refactor in parallel.
-
-### Step 6: Iterate
-
-Check for remaining pending tasks. Re-run lint to verify.
-
-If violations remain, repeat from Step 3.
-
-Continue until all functions meet or are under $ARGUMENTS lines.
+## Verification
+Command: `bun run lint 2>&1 | grep "max-lines-per-function" | wc -l`
+Expected: 0
+```
 
-### Step 7: Report
+## Step 3: Bootstrap Project
 
-```
-Max lines per function reduction complete:
-- Target threshold: $ARGUMENTS
-- Functions refactored: [count]
-- Functions reduced: [list with line counts]
-```
+Run `/project:bootstrap` with the generated brief as a text prompt.

package/all/copy-overwrite/.claude/commands/project/reduce-max-lines.md

@@ -1,6 +1,6 @@
 ---
 description: Reduce max file lines threshold and fix violations
-allowed-tools: Read, Write, Edit, Bash, Glob, Grep, Task, TaskCreate, TaskUpdate, TaskList, TaskGet
+allowed-tools: Read, Bash, Glob, Grep
 argument-hint: <max-lines-value>
 model: sonnet
 ---
@@ -11,65 +11,52 @@ Target threshold: $ARGUMENTS lines per file
 
 If no argument provided, prompt the user for a target.
 
-## Process
+## Step 1: Gather Requirements
 
-### Step 0: Check Project Context
+1. **Read current config** from eslint thresholds (eslint.thresholds.json or similar)
+2. **Run lint** with the new threshold to find violations:
+   ```bash
+   bun run lint 2>&1 | grep "max-lines"
+   ```
+3. **Note for each violation**:
+   - File path
+   - Current line count
 
-Check if there's an active project for task syncing:
+If no violations at $ARGUMENTS, report success and exit.
 
-```bash
-cat .claude-active-project 2>/dev/null
-```
-
-If a project is active, include `metadata: { "project": "<project-name>" }` in all TaskCreate calls.
-
-### Step 1: Locate Configuration
-
-Read the eslint thresholds config (`eslint.thresholds.json` or similar).
+## Step 2: Generate Brief
 
-### Step 2: Update Threshold
+Compile findings into a detailed brief:
 
-Set the `maxLines` threshold to $ARGUMENTS (e.g., `"maxLines": $ARGUMENTS`).
-
-### Step 3: Identify Violations
-
-Run lint to find all files exceeding the new threshold. Note file path and current line count.
-
-If no violations, report success and exit.
+```
+Reduce max file lines threshold to $ARGUMENTS.
 
-### Step 4: Create Task List
+## Files Exceeding Threshold (ordered by line count)
 
-Create a task for each file needing refactoring, ordered by line count (highest first).
+1. src/services/user.ts (450 lines, target: $ARGUMENTS)
+2. src/utils/helpers.ts (380 lines, target: $ARGUMENTS)
+3. src/components/Dashboard.tsx (320 lines, target: $ARGUMENTS)
+...
 
-Each task should have:
-- **subject**: "Reduce lines in [file]" (imperative form)
-- **description**: File path, current line count, target threshold, refactoring strategies
-- **activeForm**: "Reducing lines in [file]" (present continuous)
-- **metadata**: `{ "project": "<active-project>" }` if project context exists
+## Configuration Change
+- File: eslint.thresholds.json
+- Change: maxLines to $ARGUMENTS
 
-Refactoring strategies:
+## Refactoring Strategies
 - **Extract modules**: Break file into smaller focused modules
 - **Remove duplication**: Consolidate repeated logic
 - **Delete dead code**: Remove unused functions/code paths
 - **Simplify logic**: Use early returns, reduce nesting
 
-### Step 5: Parallel Execution
+## Acceptance Criteria
+- All files at or below $ARGUMENTS lines
+- `bun run lint` passes with no max-lines violations
 
-Launch **up to 5 sub-agents** using the `code-simplifier` subagent to refactor in parallel.
-
-### Step 6: Iterate
-
-Check for remaining pending tasks. Re-run lint to verify.
-
-If violations remain, repeat from Step 3.
-
-Continue until all files meet or are under $ARGUMENTS lines.
+## Verification
+Command: `bun run lint 2>&1 | grep "max-lines" | wc -l`
+Expected: 0
+```
 
-### Step 7: Report
+## Step 3: Bootstrap Project
 
-```
-Max lines reduction complete:
-- Target threshold: $ARGUMENTS
-- Files refactored: [count]
-- Files reduced: [list with line counts]
-```
+Run `/project:bootstrap` with the generated brief as a text prompt.

package/all/copy-overwrite/.claude/commands/project/research.md

@@ -103,6 +103,15 @@ last_updated: [YYYY-MM-DD]
 ## Code References
 - `path/to/file.py:123` - Description
 
+## Reusable Code
+### Existing Functions/Modules
+- `path/to/utils.ts:45` - `functionName()` - description of what it does and how it can be reused
+- `path/to/service.ts:120` - `ClassName` - description of reusable functionality
+
+### Existing Patterns to Follow
+- Similar feature implemented in `path/to/feature/` - follow same structure
+- Existing implementation of X in `path/to/file.ts` - can be extended/adapted
+
 ## Architecture Documentation
 [Patterns, conventions, design implementations]
 
@@ -119,6 +128,15 @@ last_updated: [YYYY-MM-DD]
 ### E2E Test Patterns
 [Similar structure]
 
+## Impacted Tests
+### Tests Requiring Modification
+- `tests/example.spec.ts` - tests X functionality, will need updates for Y
+- `e2e/feature.spec.ts` - may need new assertions for Z
+
+### Test Gaps
+- No existing tests for X functionality - will need new test file
+- Missing edge case coverage for Y scenario
+
 ## Documentation Patterns
 ### JSDoc Conventions
 ### Database Comments (Backend)
@@ -130,6 +148,7 @@ last_updated: [YYYY-MM-DD]
 **Question**: [Full question]
 **Context**: [Why this arose]
 **Impact**: [What it affects]
+**Recommendation**: [Researcher's best recommendation based on findings]
 **Answer**: _[Human fills before /project:plan]_
 ```
 
@@ -144,3 +163,9 @@ Run `/git:commit`
 - Focus on finding concrete file paths and line numbers
 - Each sub-agent prompt should be specific and focused on read-only documentation
 - **REMEMBER**: Document what IS, not what SHOULD BE
+
+---
+
+## Next Step
+
+After completing this phase, tell the user: "To continue, run `/project:plan $ARGUMENTS`"

package/all/copy-overwrite/.claude/commands/project/review.md

@@ -10,35 +10,45 @@ The current branch is a feature branch with full implementation of the project i
 
 ## Setup
 
-Create workflow tracking tasks with `metadata: { "project": "<project-name>", "phase": "review" }`:
+Set active project marker: `echo "$ARGUMENTS" | sed 's|.*/||' > .claude-active-project`
 
-1. Perform Claude Review
-2. Implement Claude Review Fixes
-3. Perform CodeRabbit Review
-4. Implement CodeRabbit Review Fixes
-5. Perform Claude Optimizations
+Extract `<project-name>` from the last segment of `$ARGUMENTS`.
 
-## Step 1: Perform Claude Review
+## Create and Execute Tasks
 
-If `$ARGUMENTS/claude-review.md` already exists, skip to Step 2.
+Create workflow tracking tasks with `metadata.project` set to the project name:
 
-Otherwise, run `/project:local-code-review $ARGUMENTS`
+```
+TaskCreate:
+  subject: "Perform Claude review"
+  description: "If $ARGUMENTS/claude-review.md already exists, skip this task. Otherwise, run /project:local-code-review $ARGUMENTS"
+  metadata: { project: "<project-name>" }
 
-## Step 2: Implement Claude Review Fixes
+TaskCreate:
+  subject: "Implement Claude review fixes"
+  description: "Read $ARGUMENTS/claude-review.md and fix any suggestions that score above 45."
+  metadata: { project: "<project-name>" }
 
-1. Read `$ARGUMENTS/claude-review.md`
-2. Fix any suggestions that score above 45
+TaskCreate:
+  subject: "Perform CodeRabbit review"
+  description: "If $ARGUMENTS/coderabbit-review.md already exists, skip this task. Otherwise, run `coderabbit review --plain || true` and write results to $ARGUMENTS/coderabbit-review.md"
+  metadata: { project: "<project-name>" }
 
-## Step 3: Perform CodeRabbit Review
+TaskCreate:
+  subject: "Implement CodeRabbit review fixes"
+  description: "Evaluate suggestions in $ARGUMENTS/coderabbit-review.md and implement fixes for valid findings."
+  metadata: { project: "<project-name>" }
 
-If `$ARGUMENTS/coderabbit-review.md` already exists, skip to Step 4.
+TaskCreate:
+  subject: "Perform Claude optimizations"
+  description: "Use the code simplifier agent to clean up code added to the current branch."
+  metadata: { project: "<project-name>" }
+```
 
-Otherwise, use Task tool with prompt: "Run `coderabbit review --plain || true` and write results to $ARGUMENTS/coderabbit-review.md"
+**Execute each task via a subagent** to preserve main context. Launch up to 6 in parallel where tasks don't have dependencies. Do not stop until all are completed.
 
-## Step 4: Implement CodeRabbit Review Fixes
-
-Evaluate suggestions in `$ARGUMENTS/coderabbit-review.md` and implement fixes for valid findings.
+---
 
-## Step 5: Perform Claude Optimizations
+## Next Step
 
-Use the code simplifier agent to clean up code added to the current branch.
+After completing this phase, tell the user: "To continue, run `/project:verify $ARGUMENTS`"

package/all/copy-overwrite/.claude/commands/project/setup.md

@@ -1,19 +1,55 @@
 ---
-description: Initialize a comprehensive NestJS backend project with full requirements analysis, planning, and structure setup
-argument-hint: <project-brief-file-or-jira-issue-number>
+description: Initialize a project with full requirements analysis, planning, and structure setup
+argument-hint: <file-path|jira-issue|text-description>
 allowed-tools: Read, Write, Bash(git*), Glob, Grep, Task, TaskCreate, TaskUpdate, TaskList
 ---
 
-1. Decide if $ARGUMENTS is a Jira issue number or a path to a file
-2. If $ARGUMENTS is a Jira issue number
-   1. Use the atlassian MCP server to Read the issue FULLY. If the MCP server is not working, STOP WORKING AND LET THE HUMAN KNOW
-   2. Otherwise: $ARGUMENTS is a brief for a project. Read it FULLY (no limit/offset)
-3. Create a project directory in projects/ that is appropriately named for the project and prefixed with today's date like `YYYY-MM-DD-<project-name>`
-4. If $ARGUMENTS is a Jira issue number
-   1. Create a file called `brief.md` in the newly created project directory and populate it with the jira issue number, title and description
-   2. Otherwise: Move $ARGUMENTS into the newly created project directory and rename it `brief.md`
-5. Create an empty file in the new project directory called `findings.md`
-6. If $ARGUMENTS is a Jira issue number
-   1. run /git:commit and add the jira issue number to the newly created branch (e.g. feature/SE-111-<branch-name>)
-   2. OTHERWISE: run /git:commit
-7. If $ARGUMENTS is a Jira issue number Use the atlassian MCP server to update the issue with status "In Progress"
+## Step 1: Determine Input Type
+
+Examine $ARGUMENTS to determine which type:
+- **Jira issue**: Matches pattern like `SE-123`, `PROJ-456` (letters-dash-numbers)
+- **File path**: Path exists as a file (check with Glob or Read)
+- **Text prompt**: Everything else - a description of work to be done
+
+## Step 2: Get Brief Content
+
+Based on input type:
+
+**If Jira issue:**
+1. Use the atlassian MCP server to Read the issue FULLY
+2. If MCP server not working, STOP and let human know
+
+**If file path:**
+1. Read the file FULLY (no limit/offset)
+
+**If text prompt:**
+1. The prompt IS the brief content - use $ARGUMENTS directly
+
+## Step 3: Create Project Structure
+
+1. Create project directory in `projects/` named `YYYY-MM-DD-<project-name>` where `<project-name>` is derived from:
+   - Jira: the issue key and title (e.g., `2026-01-26-se-123-add-auth`)
+   - File: the filename without extension
+   - Text prompt: a kebab-case summary of the prompt (e.g., `2026-01-26-add-user-authentication`)
+
+2. Create `brief.md` in the project directory:
+   - Jira: populate with issue number, title, and description
+   - File: move/copy the file and rename to `brief.md`
+   - Text prompt: create `brief.md` with the prompt text as content
+
+3. Create empty `findings.md` in the project directory
+
+4. Create `.claude-active-project` marker file:
+   ```bash
+   echo "YYYY-MM-DD-<project-name>" > .claude-active-project
+   ```
+
+## Step 4: Git and Finalize
+
+1. If Jira issue:
+   - run /git:commit with branch name including issue number (e.g., `feature/SE-111-<branch-name>`)
+   - Use atlassian MCP server to update issue status to "In Progress"
+2. Otherwise:
+   - run /git:commit
+
+3. Output: "Project created: `YYYY-MM-DD-<project-name>`"

package/all/copy-overwrite/.claude/commands/project/verify.md

@@ -8,68 +8,40 @@ The current branch is a feature branch with full implementation of the project i
 
 ## Setup
 
-Create workflow tracking tasks with `metadata: { "project": "<project-name>", "phase": "verify" }`:
+Set active project marker: `echo "$ARGUMENTS" | sed 's|.*/||' > .claude-active-project`
 
-1. Review Requirements
-2. Verify Implementation
-3. Run Task Verification Commands
-4. Document Drift
+Extract `<project-name>` from the last segment of `$ARGUMENTS`.
 
-## Step 1: Review Requirements
+## Create and Execute Tasks
 
-Read all requirements for $ARGUMENTS.
+Create workflow tracking tasks with `metadata.project` set to the project name:
 
-## Step 2: Verify Implementation
+```
+TaskCreate:
+  subject: "Review requirements"
+  description: "Read all requirements for $ARGUMENTS (brief.md, research.md, task files)."
+  metadata: { project: "<project-name>" }
 
-Verify the implementation completely and fully satisfies all requirements from Step 1.
+TaskCreate:
+  subject: "Verify implementation"
+  description: "Verify the implementation completely and fully satisfies all requirements from the brief and research."
+  metadata: { project: "<project-name>" }
 
-## Step 3: Run Task Verification Commands
+TaskCreate:
+  subject: "Run task verification commands"
+  description: "Read all task files in $ARGUMENTS/tasks/. For each task with verification metadata (JSON: metadata.verification, or Markdown: ## Verification section), create a verification task with subject 'Verify: <original-subject>' and metadata including originalTaskId and verification details. Then execute each verification task: run the command, compare output to expected. If pass, mark completed. If fail, keep in_progress and document failure in $ARGUMENTS/drift.md. Report summary: total tasks, passed, failed, blocked."
+  metadata: { project: "<project-name>" }
 
-### 3a: Create Verification Tasks
+TaskCreate:
+  subject: "Document drift"
+  description: "If there is any divergence from requirements or verification failures, ensure all drift is documented in $ARGUMENTS/drift.md."
+  metadata: { project: "<project-name>" }
+```
 
-First, read all task files in `$ARGUMENTS/tasks/` and create a new task for each one that has verification metadata:
+**Execute each task via a subagent** to preserve main context. Launch up to 6 in parallel where tasks don't have dependencies. Do not stop until all are completed.
 
-For each task file:
-1. **Read the task file** (JSON or markdown)
-2. **Check for verification metadata**:
-   - JSON tasks: Look for `metadata.verification`
-   - Markdown tasks: Look for `## Verification` section with `### Proof Command`
-3. **If verification exists**, create a new task:
-   ```
-   subject: "Verify: <original-task-subject>"
-   description: "Run verification for task <id>: <verification.command>"
-   activeForm: "Verifying <original-task-subject>"
-   metadata: {
-     "project": "<project-name>",
-     "phase": "verify",
-     "originalTaskId": "<id>",
-     "verification": <copy the verification object>
-   }
-   ```
-
-### 3b: Execute Verification Tasks
-
-Work through each verification task:
-
-1. **Run verification command** using Bash tool:
-   - JSON: Execute `metadata.verification.command`
-   - Markdown: Execute the command in `### Proof Command` code block
-2. **Compare output to expected**:
-   - JSON: Compare to `metadata.verification.expected`
-   - Markdown: Compare to `### Expected Output` section
-3. **Record results and mark task**:
-   - If verification passes → Mark task completed
-   - If verification fails → Keep task in_progress, document failure in drift.md
-   - If command cannot run → Keep task in_progress, document blocker in drift.md
-
-### Verification Summary
-
-After running all verification tasks, report:
-- Total tasks with verification: X
-- Passed: Y
-- Failed: Z
-- Blocked: W
+---
 
-## Step 4: Document Drift
+## Next Step
 
-If there is any divergence from the requirements or verification failures, document the drift to `$ARGUMENTS/drift.md`.
+After completing this phase, tell the user: "To continue, run `/project:debrief $ARGUMENTS`"