🔍 Agentic Workflow Audit Report - 2025-12-30

[github-actions[bot]]

Audit Summary

Period: Last 24 hours (Dec 29-30, 2025)
Runs Analyzed: 44
Success Rate: 88.6%
Issues Found: 2 failures, 6 missing tool reports

Key Findings

✅ Overall Health

• 39 successful runs (88.6% success rate)
• 2 failed runs
• 2 cancelled runs
• 1 in-progress run

📊 Most Active Workflows

Workflow	Runs	Success Rate
Issue Monster	9	100%
Tidy	5	60%
Smoke Tests (combined)	12	100%
Security Fix PR	2	100%

⚠️ Missing Tools

Three distinct missing tool reports were detected across 6 occurrences:

Tool	Count	Workflows Affected	Impact
safeinputs-gh	3	Smoke Codex, Smoke Claude, Tidy	Medium - Prevents gh command execution in tests
Go toolchain and make	1	Tidy	Medium - Blocks code formatting and linting
Build toolchain	2	Tidy	Medium - Cannot run make commands

Details: safeinputs-gh Tool

The safeinputs-gh tool is required to run GitHub CLI commands like gh issues list --limit 3 but is not available in the smoke test environments. This affects:

• §20582611462 - Smoke Codex
• §20582611478 - Smoke Claude
• §20585976863 - Tidy

Details: Build Toolchain (Tidy Workflow)

The Tidy workflow requires Go toolchain, make, golangci-lint, and npm to perform code formatting and linting. Two runs reported these tools as missing:

• §20580210061
• §20582370492

This explains the 60% success rate for the Tidy workflow.

❌ Failed Runs

Run ID	Workflow	Agent	Status
§20585692661	Spec-Kit Execute	GitHub Copilot CLI	Failed
§20587781581	Daily Project Performance Summary	Codex	Failed

📈 Performance Metrics

Note: Token usage and cost data were not captured in the current run logs. Historical data from cache-memory shows typical costs:

• Average cost per run: $0.18-$0.28 (historical)
• Daily total: $2.50-$11.64 (historical range)

🔒 Firewall Analysis

Total Requests: 639 network requests were logged
Status: No allowed/denied categorization available in current logs

Recommendations

1. Add safeinputs-gh tool to smoke test environments - This would eliminate 3 of the 6 missing tool reports and improve test coverage.

2. Configure build toolchain for Tidy workflow - Ensure Go, make, golangci-lint, and npm are available in the Tidy workflow environment to achieve 100% success rate.

3. Investigate failed runs:

   • Spec-Kit Execute failure needs investigation
   • Daily Project Performance Summary failure needs root cause analysis

4. Improve token/cost tracking - Current run logs don't capture token usage and cost data. Consider enhancing the logging mechanism.

Historical Context

Previous audits from cache-memory show:

• October 12-13, 2025: Success rates ranged from 92-100%
• Average cost per run: $0.18-$0.28
• Typical daily token usage: 3-17M tokens

Next Steps

• Add safeinputs-gh tool to smoke test configurations
• Configure build toolchain in Tidy workflow
• Investigate root cause of Spec-Kit Execute failure
• Investigate root cause of Daily Performance Summary failure
• Enhance token/cost tracking in workflow logs

References:

• §20582611462
• §20585692661
• §20587781581

AI generated by Agentic Workflow Audit Agent