codex-automation-architect

codex-automation-architect is a skill for Codex from jscraik/Agent-Skills. It costs 35 tokens per session (1,200 once invoked), scanned A, original, Apache-2.0.

A design and review workflow for Codex automations, scheduled tasks, recurring runs, and heartbeat follow-ups. It defines the task scope, timing, execution environment, validation, and rollback expectations.

In plain words
What is it for?
Use it to design, audit, consolidate, or review scheduled Codex workflows and background project tasks.
Why use it?
It helps prevent recurring jobs from running with unclear ownership, unsafe scope, or duplicate schedules. It also makes the risks and preflight checks visible before rollout.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Good fit Use it to design, audit, consolidate, or review scheduled Codex workflows and background project tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jscraik/agent-skills/codex-automation-architect
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add jscraik/Agent-Skills --skill codex-automation-architect
Clone the repo
git clone --depth 1 https://github.com/jscraik/Agent-Skills

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for codex-automation-architect

README.md
[![agentmods](https://agentmods.dev/badge/skills/jscraik/agent-skills/codex-automation-architect/github.svg)](https://agentmods.dev/skills/jscraik/agent-skills/codex-automation-architect)
Your own site
<a href="https://agentmods.dev/skills/jscraik/agent-skills/codex-automation-architect"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/codex-automation-architect/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for codex-automation-architect

Your own site · 80×15
<a href="https://agentmods.dev/skills/jscraik/agent-skills/codex-automation-architect"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/codex-automation-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,200 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.01200
Opus 5 $0.00017 $0.00600
Sonnet 5 $0.00007 $0.00240
Haiku 4.5 $0.00003 $0.00120

Measured 8d ago against content hash 9021c11ad1bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

codex-automation-architect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Skills/agent-ops/codex-automation-architect/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Automation Architect

Philosophy

  • Keep the skill focused on the decision and workflow the user actually requested.
  • Preserve important context through progressive disclosure instead of trimming it away.
  • Prefer repo-local contracts, wrappers, and validation before generic advice.

When To Use

  • The user wants a recurring Codex automation designed, audited, or consolidated.
  • A background workflow needs scope, schedule, sandbox, and validation decisions.
  • Existing automations need risk review or deduplication.

Avoid

  • One-off manual tasks that do not need recurring automation.
  • Generic CI setup that belongs to CI-specific skills.
  • Automations that lack a safe project path or owner.

Inputs

  • automation goal
  • target project path
  • schedule or trigger
  • sandbox posture
  • validation and rollback expectations
  • existing automation ids or $CODEX_HOME/automations/*/automation.toml evidence
  • Codex app dynamic tool availability (automation_update and automation_list, possibly deferred behind tool_search)

Outputs

  • automation design
  • risk and scope review
  • preflight plan
  • validation evidence
  • rollout or consolidation notes
  • Schema-bound outputs include schema_version.

Workflow

  • Start with 2-3 focused surfaces before expanding scope.
  • Confirm the automation goal and whether it should be recurring at all.
  • Resolve existing automations first by id, name, prompt, and local TOML evidence; prefer update or consolidation over duplicate creation.
  • Map kind (cron or heartbeat), destination, project path, execution environment, permissions, schedule, and expected outputs.
  • Prefer heartbeats for current-thread follow-ups, especially short delays; prefer cron for detached workspace jobs.
  • Use suggested create/update when proposing worktree automations with a non-null local environment setup config so the user can review before save.
  • Define preflight, stop conditions, observability, and rollback.
  • Validate the final plan or config with repo checks and the Codex app automation tool response.

Read the full file on GitHub · 118 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 118 lines · 35 tokens per session scan A 9021c11ad1bb

Subscribe to this mod's changes

codex-automation-architect is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,200 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.