agentleFS
mahsumaktasmahsumaktas/agent-evolution-kit/skills/agent-stability-ops/SKILL.md

agent-system-stability-ops

Skill2 starsChanged 9 months agoMITView on GitHub

Audit and harden AgentSystem scheduler reliability, cron contract compliance, and agent consistency. Use when bots skip jobs, show timeout spikes, leak raw logs, or run with wrong agent identity/session.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 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.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run fast reliability checks before changing cron/model/memory behavior.

    line 8
  2. Distinctive:

    Run scheduler contract audit:

    line 17
  3. Very specific:

    Check scheduler contract first.

    line 29
  4. Very specific:

    If isolated + payload.kind != agentTurn exists, fix or remove those jobs before any other tuning.

    line 30
  5. Very specific:

    If runAgent != job.agentId, treat as high severity and verify session routing + explicit agentId for every enabled job.

    line 33
  6. Distinctive:

    Do not declare stable until the last 6-12h window has zero contract violations and zero agent mismatches.

    line 42

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

AgentSystem Stability Ops

Run fast reliability checks before changing cron/model/memory behavior.

Quick Start

  1. Run reliability audit:
python3 scripts/reliability_audit.py --hours 24
  1. Run scheduler contract audit:
bash ~/.agent-evolution/scripts/agent-system-cron-audit.sh --json
  1. Regenerate health report:
bash ~/scripts/cron-health-monitor.sh

Workflow

  1. Check scheduler contract first. If isolated + payload.kind != agentTurn exists, fix or remove those jobs before any other tuning.
  2. Check agent consistency. If runAgent != job.agentId, treat as high severity and verify session routing + explicit agentId for every enabled job.
  3. Check failure quality. Separate transport/provider failures from logic failures. Timeout-heavy clusters usually require timeout/model/prompt changes, not blind retries.
  4. Enforce output hygiene. Any summary containing raw tool logs (Exec, stack trace, raw JSON) is a regression.
  5. Re-run audits after changes. Do not declare stable until the last 6-12h window has zero contract violations and zero agent mismatches.

Resources

  • scripts/reliability_audit.py: Computes reliability metrics from jobs.json + run logs.
  • references/runbook.md: Safe remediation order and command cookbook.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.