agentleFS
frankxaifrankxai/starlight-automation-agent-skills/skills/codex-automation-operator/SKILL.md

codex-automation-operator

Skill0 starsChanged 3 months agoMITView on GitHub

Design and operate recurring Codex automations for scheduled reports, repo health, issue triage, inbox summaries, meeting briefs, deployment monitors, and agentic follow-up work. Use when a user asks to remember recurring work, schedule future Codex tasks, automate routine reviews, or decide whether a task belongs in Codex rather than Make.com, n8n, or MCP.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use Codex automations for recurring work that needs judgment, synthesis, repo context, or connector-backed review.

    line 8

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Codex Automation Operator

Use Codex automations for recurring work that needs judgment, synthesis, repo context, or connector-backed review.

Best Fit

  • daily or weekly repo health summaries
  • issue and PR triage
  • Vercel preview checks
  • inbox and calendar briefings
  • partner follow-up drafts
  • stale task reminders
  • recurring public-safety scans

Use Another Tool When

  • event latency matters more than reasoning: use Make.com or n8n
  • a non-agent system must own execution: use n8n or Make.com
  • the task is only a typed external tool call: use MCP
  • the task needs multiple parallel repo workers: use a Starlight queue

Automation Spec

Return:

  • name
  • cadence
  • scope
  • sources/connectors
  • output shape
  • no-findings behavior
  • archive behavior
  • approval gates
  • escalation condition
  • owner and review cadence

Gates

Codex may draft, summarize, inspect, and report. Human approval is required before sending messages, posting publicly, spending, deleting, inviting, changing access, or production promotion.

Output Shape

Return: automation spec, why Codex is the owner, connectors needed, risk gates, and validation method.

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.