agent-system-output-hygiene-ops
Audit and remediate AgentSystem cron output hygiene by detecting raw tool logs, stack traces, and noisy summaries. Use when jobs leak 403/429/internal details, summaries are not user-safe, or post-cha
SKILL.mdskills/agent-output-hygiene-ops/SKILL.md
GitHubAgentSystem Output Hygiene Ops
Run this skill when cron summaries must stay concise and safe for user-facing channels.
Quick Start
- Run hygiene audit:
bash scripts/hygiene_audit.sh --run-suite
If leaks exist, patch top leaking jobs using
references/prompt-remediation.md.Smoke-test patched jobs:
agent-system cron run <job-id> --expect-final --timeout 480000
agent-system cron runs --id <job-id> --limit 2 --expect-final
Workflow
- Run
scripts/hygiene_audit.shand identify highest-frequency leaking job IDs. - Prioritize jobs leaking raw tool output (
Exec,stack trace,raw JSON,403/429payloads). - Apply strict output contract to prompt:
- ban raw logs and internal diagnostics
- force compact final format or
NO_REPLY - prefer deterministic local fallback over noisy web-search errors
- Re-run patched jobs and confirm the latest run is clean.
- Re-run health suite and record report paths.
Resources
scripts/hygiene_audit.sh: summarizes leak-heavy jobs from latest health report.references/prompt-remediation.md: safe prompt patch template and command pattern.