name: 17th-vanguard description: | Use this skill when the user wants to explore or search across the codebase. Delegates search to GLM-4.7 via background subagent for non-blocking execution. Appropriate for: finding implementations, locating code patterns, exploring unfamiliar areas. Not appropriate for: reading a known file, simple single-command lookups.

Vanguard

Delegate codebase searches to GLM-4.7 via background subagent. You remain free to do other work and receive automatic notification when complete.

When to Use

• Finding code patterns across the codebase
• Locating implementations of specific features
• Searching for function/class/variable definitions
• Exploring unfamiliar codebases
• Any search that might require multiple grep/rg commands

When NOT to Use

• You already know the file path (use Read directly)
• Simple single-file search (use Grep directly)
• Quick lookups that take < 5 seconds

Workflow

1. User requests a search (e.g., "find where authentication is implemented")
2. Launch background subagent with GLM delegation
3. Continue with other tasks or conversation
4. Receive notification when search completes
5. Subagent verifies GLM results before reporting
6. Report verified results to user

Implementation

Use the Task tool with these parameters:

Task(
    description="GLM quick search: {brief description}",
    subagent_type="general-purpose",
    run_in_background=true,
    max_turns=30,  # GLM call + verification reads + summarization
    prompt="""
Call the delegate_to_glm MCP tool with:

task: "{search_instructions}"
working_dir: "{project_root}"

Search instructions should include:
- Use rg (ripgrep) for fast searching
- Specific patterns or keywords to find
- File types or directories to focus on
- Output format: file:line with brief context

IMPORTANT: After GLM returns results, you MUST verify them:
1. For each reported file:line, use Read tool to check the actual content
2. Confirm the code/pattern GLM described actually exists at that location
3. If GLM reported something incorrectly, exclude it from your report
4. Only include verified findings in your final summary

Report format:
- Verified files with line numbers
- Actual code snippet or description (from your verification)
- Any discrepancies found in GLM's results
"""
)

Example Prompts

Find feature implementation

Task(
    description="GLM search: authentication",
    subagent_type="general-purpose",
    run_in_background=true,
    max_turns=30,
    prompt="""
Call delegate_to_glm MCP tool:

task: "Find where user authentication is implemented in this Go project.
Use rg to search for:
- rg -n 'func.*Auth|func.*Login|func.*Verify' --type go
- rg -n 'middleware.*auth' --type go -i

Return file:line for each match."

working_dir: {project_root}

After GLM returns, verify the top 3-5 results:
- Read each file at the reported line
- Confirm the authentication logic exists there
- Report only verified findings with actual code context
"""
)

Find Clean Architecture violations

Task(
    description="GLM search: architecture violations",
    subagent_type="general-purpose",
    run_in_background=true,
    max_turns=30,
    prompt="""
Call delegate_to_glm MCP tool:

task: "Check for Clean Architecture violations.
Use rg to find domain layer importing infrastructure:
- rg -n 'import.*infrastructure|protocol|data' internal/feature/*/domain/ --type go

Report any violations as file:line, or 'No violations found'."

working_dir: {project_root}

If GLM reports violations, verify each one:
- Read the import block of each reported file
- Confirm it actually imports from infrastructure/protocol/data
- Distinguish real violations from false positives (e.g., comments, string literals)
"""
)

Find TODO/FIXME comments

Task(
    description="GLM search: TODOs",
    subagent_type="general-purpose",
    run_in_background=true,
    max_turns=30,
    prompt="""
Call delegate_to_glm MCP tool:

task: "Find all TODO and FIXME comments in the codebase.
Use: rg -n 'TODO|FIXME' --type go --type proto

Return file:line for each match."

working_dir: {project_root}

Verify a sample of results (at least 3-5):
- Read the actual lines to confirm they are real TODO/FIXME comments
- Summarize by category or urgency based on verified content
"""
)

Tips

• Always use rg (ripgrep) instead of grep for speed
• Specify --type to limit search scope
• Use -n flag to include line numbers
• For large results, ask GLM to summarize top findings
• Set max_iterations higher (15-20) for complex searches

Configuration

Notes

• Results come via automatic notification (no polling needed)
• GLM uses bash, read_file, write_file internally
• For sync (blocking) searches, use delegate_to_glm directly without subagent
• Verification is critical: GLM may hallucinate or misinterpret results; always verify before reporting to user