agent-system-output-hygiene-ops
Skill2 starsChanged 9 months agoMITView on GitHub
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-change validation is required.
In this repository27 other files it gives its agents.
- Agent BrowserSkill
- agent-governanceSkill
- agent-system-learning-loopSkill
- agent-system-live-quality-opsSkill
- agent-system-memory-proactivity-opsSkill
- agent-system-stability-opsSkill
- auto-updaterSkill
- deep-researchSkill
- domaindetailsSkill
- hnSkill
- humanizerSkill
- memory-hygieneSkill
- model-usageSkill
- nano-pdfSkill
- news-aggregator-skillSkill
- orchestrator-loopSkill
- prompt-guardSkill
- security-reviewSkill
- self-improvementSkill
- structured-brainstormingSkill
- subagent-executionSkill
- summarizeSkill
- systematic-debuggingSkill
- tavilySkill
- tdd-workflowSkill
- topic-monitorSkill
- verification-gateSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Run this skill when cron summaries must stay concise and safe for user-facing channels.
- Very specific: line 17
If leaks exist, patch top leaking jobs using references/prompt-remediation.md.
- Very specific: line 27
Run scripts/hygiene_audit.sh and identify highest-frequency leaking job IDs.
- Distinctive: line 32
prefer deterministic local fallback over noisy web-search errors
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AgentSystem 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-finalWorkflow
- 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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.