@lavralabs/lavra 0.7.0

package/plugins/lavra/gemini/commands/lfg.toml

@@ -0,0 +1,28 @@
+# Generated by beads-compound v0.6.0
+# DO NOT EDIT - changes will be overwritten on next install
+
+description = "Full autonomous engineering workflow"
+
+prompt = """
+
+<objective>
+Run the full autonomous engineering workflow end-to-end: plan, deepen, work, review, resolve TODOs, browser test, and record a feature video.
+</objective>
+
+<process>
+
+Run these slash commands in order. Do not do anything else.
+
+1. `/beads-plan {{args}}`
+2. `/beads-deepen`
+3. `/beads-work`
+4. `/beads-review`
+5. `/resolve-todo-parallel`
+6. `/test-browser`
+7. `/feature-video`
+
+Start with step 1 now.
+
+</process>
+
+"""

package/plugins/lavra/gemini/commands/release-docs.toml

@@ -0,0 +1,146 @@
+# Generated by beads-compound v0.6.0
+# DO NOT EDIT - changes will be overwritten on next install
+
+description = "Build and update the documentation site with current plugin components"
+
+prompt = """
+
+<objective>
+Regenerate the documentation to ensure it is always up-to-date with the actual plugin components (agents, commands, skills, MCP servers).
+</objective>
+
+<context>
+The documentation needs to be regenerated whenever:
+
+- Agents are added, removed, or modified
+- Commands are added, removed, or modified
+- Skills are added, removed, or modified
+- MCP servers are added, removed, or modified
+</context>
+
+<process>
+
+## Step 1: Inventory Current Components
+
+First, count and list all current components:
+
+```bash
+# Count agents
+find plugins/beads-compound/agents -name "*.md" | wc -l
+
+# Count commands
+ls plugins/beads-compound/commands/*.md | wc -l
+
+# Count skills
+ls -d plugins/beads-compound/skills/*/ 2>/dev/null | wc -l
+```
+
+Read all component files to get their metadata:
+
+### Agents
+For each agent file in `plugins/beads-compound/agents/`:
+- Extract the frontmatter (name, description)
+- Note the category (Review, Research, Workflow, Design, Docs)
+- Get key responsibilities from the content
+
+### Commands
+For each command file in `plugins/beads-compound/commands/*.md`:
+- Extract the frontmatter (name, description, argument-hint)
+- Categorize as Workflow or Utility command
+
+### Skills
+For each skill directory in `plugins/beads-compound/skills/*/`:
+- Read the SKILL.md file for frontmatter (name, description)
+- Note any scripts or supporting files
+
+## Step 2: Update Metadata Files
+
+Ensure counts are consistent across:
+
+1. **`plugins/beads-compound/.claude-plugin/plugin.json`**
+   - Update `description` with correct counts
+   - Update `components` object with counts
+   - Update `agents`, `commands` arrays with current items
+
+2. **`.claude-plugin/marketplace.json`**
+   - Update plugin `description` with correct counts
+
+3. **`README.md`**
+   - Update intro paragraph with counts
+   - Update component lists
+
+## Step 3: Validate
+
+Run validation checks:
+
+```bash
+# Validate JSON files
+cat .claude-plugin/marketplace.json | jq .
+cat plugins/beads-compound/.claude-plugin/plugin.json | jq .
+
+# Verify counts match
+echo "Agents in files: $(find plugins/beads-compound/agents -name '*.md' | wc -l)"
+echo "Commands in files: $(ls plugins/beads-compound/commands/*.md | wc -l)"
+echo "Skills: $(ls -d plugins/beads-compound/skills/*/ | wc -l)"
+```
+
+## Step 4: Report Changes
+
+Provide a summary:
+
+```
+## Documentation Release Summary
+
+### Component Counts
+- Agents: X (previously Y)
+- Commands: X (previously Y)
+- Skills: X (previously Y)
+
+### Files Updated
+- plugin.json - Updated counts and component lists
+- marketplace.json - Updated description
+- README.md - Updated component lists
+- CLAUDE.md or AGENTS.md - Updated counts and tables
+
+### New Components Added
+- [List any new agents/commands/skills]
+
+### Components Removed
+- [List any removed agents/commands/skills]
+```
+
+</process>
+
+<guardrails>
+
+## Dry Run Mode
+
+If `--dry-run` is specified:
+- Perform all inventory and validation steps
+- Report what WOULD be updated
+- Do NOT write any files
+- Show diff previews of proposed changes
+
+## Error Handling
+
+- If component files have invalid frontmatter, report the error and skip
+- If JSON validation fails, report and abort
+- Always maintain a valid state - don't partially update
+
+</guardrails>
+
+<success_criteria>
+- [ ] All component files inventoried with correct metadata
+- [ ] Counts are consistent across plugin.json, marketplace.json, and README.md
+- [ ] JSON files validate successfully
+- [ ] Summary report shows changes from previous state
+</success_criteria>
+
+<handoff>
+After successful release:
+1. Suggest updating CHANGELOG.md with documentation changes
+2. Remind to commit with message: `docs: Update documentation to match plugin components`
+3. Remind to push changes
+</handoff>
+
+"""

package/plugins/lavra/gemini/commands/report-bug.toml

@@ -0,0 +1,157 @@
+# Generated by lavra v0.6.0
+# DO NOT EDIT - changes will be overwritten on next install
+
+description = "Report a bug in the lavra plugin"
+
+prompt = """
+
+<objective>
+Report bugs encountered while using the lavra plugin by gathering structured information and creating a GitHub issue for the maintainer.
+</objective>
+
+<process>
+
+## Step 1: Gather Bug Information
+
+Use the AskUserQuestion tool to collect the following information:
+
+**Question 1: Bug Category**
+- What type of issue are you experiencing?
+- Options: Agent not working, Command not working, Skill not working, MCP server issue, Installation problem, Other
+
+**Question 2: Specific Component**
+- Which specific component is affected?
+- Ask for the name of the agent, command, skill, or MCP server
+
+**Question 3: What Happened (Actual Behavior)**
+- Ask: "What happened when you used this component?"
+- Get a clear description of the actual behavior
+
+**Question 4: What Should Have Happened (Expected Behavior)**
+- Ask: "What did you expect to happen instead?"
+- Get a clear description of expected behavior
+
+**Question 5: Steps to Reproduce**
+- Ask: "What steps did you take before the bug occurred?"
+- Get reproduction steps
+
+**Question 6: Error Messages**
+- Ask: "Did you see any error messages? If so, please share them."
+- Capture any error output
+
+## Step 2: Collect Environment Information
+
+Automatically gather:
+```bash
+# Get plugin version
+cat ~/.claude/plugins/installed_plugins.json 2>/dev/null | grep -A5 "lavra" | head -10 || echo "Plugin info not found"
+
+# Get Claude Code version
+claude --version 2>/dev/null || echo "Claude CLI version unknown"
+
+# Get OS info
+uname -a
+```
+
+## Step 3: Format the Bug Report
+
+Create a well-structured bug report with:
+
+```markdown
+## Bug Description
+
+**Component:** [Type] - [Name]
+**Summary:** [Brief description from argument or collected info]
+
+## Environment
+
+- **Plugin Version:** [from installed_plugins.json]
+- **Claude Code Version:** [from claude --version]
+- **OS:** [from uname]
+
+## What Happened
+
+[Actual behavior description]
+
+## Expected Behavior
+
+[Expected behavior description]
+
+## Steps to Reproduce
+
+1. [Step 1]
+2. [Step 2]
+3. [Step 3]
+
+## Error Messages
+
+```
+[Any error output]
+```
+
+## Additional Context
+
+[Any other relevant information]
+
+---
+*Reported via `/report-bug` command*
+```
+
+## Step 4: Create GitHub Issue
+
+Use the GitHub CLI to create the issue:
+
+```bash
+gh issue create \
+  --repo rbm/lavra \
+  --title "[lavra] Bug: [Brief description]" \
+  --body "[Formatted bug report from Step 3]" \
+  --label "bug"
+```
+
+**Note:** If labels don't exist, create without labels:
+```bash
+gh issue create \
+  --repo rbm/lavra \
+  --title "[lavra] Bug: [Brief description]" \
+  --body "[Formatted bug report]"
+```
+
+## Step 5: Confirm Submission
+
+After the issue is created:
+1. Display the issue URL to the user
+2. Thank them for reporting the bug
+3. Let them know the maintainer will be notified
+
+</process>
+
+<success_criteria>
+- [ ] All six bug information questions answered
+- [ ] Environment information collected automatically
+- [ ] Bug report formatted with all sections
+- [ ] GitHub issue created successfully
+- [ ] Issue URL displayed to user
+</success_criteria>
+
+<guardrails>
+
+## Error Handling
+
+- If `gh` CLI is not authenticated: Prompt user to run `gh auth login` first
+- If issue creation fails: Display the formatted report so user can manually create the issue
+- If required information is missing: Re-prompt for that specific field
+
+## Privacy Notice
+
+This command does NOT collect:
+- Personal information
+- API keys or credentials
+- Private code from your projects
+- File paths beyond basic OS info
+
+Only technical information about the bug is included in the report.
+
+</guardrails>
+
+"""

package/plugins/lavra/gemini/commands/reproduce-bug.toml

@@ -0,0 +1,99 @@
+# Generated by beads-compound v0.6.0
+# DO NOT EDIT - changes will be overwritten on next install
+
+description = "Reproduce and investigate a bug using logs, console inspection, and browser screenshots"
+
+prompt = """
+
+<objective>
+Reproduce and investigate a bug by reading the GitHub issue, analyzing logs, visually reproducing it in a browser, and documenting findings with screenshots and code references.
+</objective>
+
+<execution_context>
+Look at github issue #{{args}} and read the issue description and comments.
+</execution_context>
+
+<process>
+
+## Phase 1: Log Investigation
+
+Run the following agents in parallel to investigate the bug:
+
+1. Task rails-console-explorer(issue_description)
+2. Task appsignal-log-investigator(issue_description)
+
+Think about the places it could go wrong looking at the codebase. Look for logging output we can look for.
+
+Run the agents again to find any logs that could help us reproduce the bug.
+
+Keep running these agents until you have a good idea of what is going on.
+
+## Phase 2: Visual Reproduction with Playwright
+
+If the bug is UI-related or involves user flows, use Playwright to visually reproduce it:
+
+### Step 1: Verify Server is Running
+
+```bash
+agent-browser open "http://localhost:3000"
+agent-browser snapshot -i
+```
+
+If server not running, inform user to start `bin/dev`.
+
+### Step 2: Navigate to Affected Area
+
+Based on the issue description, navigate to the relevant page:
+
+```bash
+agent-browser open "http://localhost:3000/[affected_route]"
+agent-browser snapshot -i
+```
+
+### Step 3: Capture Screenshots
+
+Take screenshots at each step of reproducing the bug:
+
+```bash
+agent-browser screenshot "bug-[issue]-step-1.png"
+```
+
+### Step 4: Follow User Flow
+
+Reproduce the exact steps from the issue:
+
+1. **Read the issue's reproduction steps**
+2. **Execute each step using agent-browser:**
+   - `agent-browser click @e1` for clicking elements
+   - `agent-browser fill @e1 "text"` for filling forms
+   - `agent-browser snapshot -i` to see the current state
+   - `agent-browser screenshot` to capture evidence
+
+## Phase 3: Document Findings
+
+- [ ] Document all research findings with specific file paths (e.g., `app/services/example_service.rb:42`)
+- [ ] Include screenshots showing the bug reproduction
+- [ ] List console errors if any
+- [ ] Document the exact reproduction steps
+
+## Phase 4: Report Back
+
+Add a comment to the issue with:
+
+1. **Findings** - What you discovered about the cause
+2. **Reproduction Steps** - Exact steps to reproduce (verified)
+3. **Screenshots** - Visual evidence of the bug (upload captured screenshots)
+4. **Relevant Code** - File paths and line numbers
+5. **Suggested Fix** - If you have one
+
+</process>
+
+<success_criteria>
+- [ ] GitHub issue read and understood
+- [ ] Log investigation completed (rails console + appsignal)
+- [ ] Bug visually reproduced (if UI-related) with screenshots
+- [ ] Findings documented with specific file paths and line numbers
+- [ ] Comment added to the GitHub issue with findings
+</success_criteria>
+
+"""

package/plugins/lavra/gemini/commands/resolve-pr-parallel.toml

@@ -0,0 +1,56 @@
+# Generated by beads-compound v0.6.0
+# DO NOT EDIT - changes will be overwritten on next install
+
+description = "Resolve all PR comments using parallel processing"
+
+prompt = """
+
+<objective>
+Resolve all unresolved PR comments by spawning parallel pr-comment-resolver agents for each comment, then committing and pushing the changes.
+</objective>
+
+<process>
+
+## 1. Analyze
+
+Get all unresolved comments for PR
+
+```bash
+gh pr status
+bin/get-pr-comments PR_NUMBER
+```
+
+## 2. Plan
+
+Create a task list (using TaskCreate) of all unresolved items grouped by type.
+
+## 3. Implement (PARALLEL)
+
+Spawn a pr-comment-resolver agent for each unresolved item in parallel.
+
+So if there are 3 comments, it will spawn 3 pr-comment-resolver agents in parallel. Like this:
+
+1. Task pr-comment-resolver(comment1)
+2. Task pr-comment-resolver(comment2)
+3. Task pr-comment-resolver(comment3)
+
+Always run all in parallel subagents/Tasks for each Todo item.
+
+## 4. Commit & Resolve
+
+- Commit changes
+- Run bin/resolve-pr-thread THREAD_ID_1
+- Push to remote
+
+Last, check bin/get-pr-comments PR_NUMBER again to see if all comments are resolved. They should be, if not, repeat the process from 1.
+
+</process>
+
+<success_criteria>
+- [ ] All unresolved PR comments identified
+- [ ] Each comment resolved by a parallel pr-comment-resolver agent
+- [ ] Changes committed and pushed to remote
+- [ ] Re-check confirms all comments are resolved
+</success_criteria>
+
+"""

package/plugins/lavra/gemini/commands/resolve-todo-parallel.toml

@@ -0,0 +1,54 @@
+# Generated by beads-compound v0.6.0
+# DO NOT EDIT - changes will be overwritten on next install
+
+description = "Resolve all pending CLI todos using parallel processing"
+
+prompt = """
+
+<objective>
+Resolve all TODO comments using parallel processing, analyzing dependencies to determine execution order and spawning parallel agents for independent items.
+</objective>
+
+<guardrails>
+If any todo recommends deleting, removing, or gitignoring files in `.lavra/memory/`, skip it and mark it as `wont_fix`. These are beads-compound pipeline artifacts that are intentional and permanent.
+</guardrails>
+
+<process>
+
+## 1. Analyze
+
+Get all unresolved TODOs from the todos/ directory.
+
+## 2. Plan
+
+Create a task list (using TaskCreate) of all unresolved items grouped by type. Make sure to look at dependencies that might occur and prioritize the ones needed by others. For example, if you need to change a name, you must wait to do the others. Output a mermaid flow diagram showing how we can do this. Can we do everything in parallel? Do we need to do one first that leads to others in parallel? Put the to-dos in the mermaid diagram flow-wise so the agent knows how to proceed in order.
+
+## 3. Implement (PARALLEL)
+
+Spawn a pr-comment-resolver agent for each unresolved item in parallel.
+
+So if there are 3 comments, it will spawn 3 pr-comment-resolver agents in parallel. Like this:
+
+1. Task pr-comment-resolver(comment1)
+2. Task pr-comment-resolver(comment2)
+3. Task pr-comment-resolver(comment3)
+
+Always run all in parallel subagents/Tasks for each Todo item.
+
+## 4. Commit & Resolve
+
+- Commit changes
+- Remove the TODO from the file, and mark it as resolved.
+- Push to remote
+
+</process>
+
+<success_criteria>
+- [ ] All TODOs identified and dependency-analyzed
+- [ ] Mermaid flow diagram produced showing execution order
+- [ ] Each TODO resolved by a parallel agent (respecting dependencies)
+- [ ] Changes committed and pushed to remote
+- [ ] TODO entries removed/marked as resolved
+</success_criteria>
+
+"""