About validator-status
validator-status is a skill for inspecting the latest Agent Validator session and reporting its status, gate results, and details from failed checks or reviews.
Key features
- 01Session status and run summary
- 02Gate result overview
- 03Failure details from logs
- 04Review violation fields
Use cases
- 01Reviewing the latest validation session
- 02Finding the cause of failed gates
- 03Tracking review violations by file and status
Install
Copy the command and run it in a terminal.
npx skills add https:/ / github.com/ codagent-ai/ agent-validator --skill validator-statusAfter installing, type/validator-statusin Claude Code to confirm it loaded.
Details
From the project README/validator-status
Show a detailed summary of the most recent validator session.
Step 1: Run the status script
agent-validate status 2>&1
The script parses the .debug.log for session-level data (run count, gate results, pass/fail status) and lists all log files with their paths and sizes.
Step 2: Read failed gate details
For each gate marked FAIL in the Gate Results table, read the corresponding log files to extract failure details:
- Check failures (e.g.,
check:src:code-health): Read the matchingcheck_*.logfile. Check log formats vary by tool (linters, test runners, code health analyzers) — read the file and extract the relevant error/warning output. - Review failures (e.g.,
review:.:code-quality): Read the matchingreview_*.jsonfile(s). These contain structured violation data withfile,line,issue,priority, andstatusfields.
Use the file paths from the "Log Files" section of the script output. Match gate IDs to file names: check:.:lint corresponds to check_._lint.*.log, review:.:code-quality corresponds to review_._code-quality_*.{log,json}.
Step 3: Present the results
Combine the script's session summary with the detailed failure information into a comprehensive report:
- Session overview (status, iterations, duration, fixed/skipped/failed counts)
- Gate results table
- For any failed gates: the specific errors, violations, or test failures from the log files
- For reviews with violations: list each violation with file, line, issue, priority, and current status (fixed/skipped/outstanding)