codex-agent-creator

codex-agent-creator is a skill for Codex from jscraik/Agent-Skills. It costs 70 tokens per session (1,708 once invoked), scanned A, original, Apache-2.0.

A workflow for creating, checking, installing, and troubleshooting Codex subagent roles stored in TOML configuration. A subagent role gives a delegated agent a defined responsibility, scope, and routing setup.

In plain words
What is it for?
Use it to create reviewer or specialist roles, configure subagents, validate role files, plan bounded delegation, or merge duplicate roles.
Why use it?
It helps keep delegated agents discoverable, bounded, and non-duplicated. It also provides a way to merge overlapping roles and verify that the configuration works.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions subagents; mentions AGENTS.md; mentions Codex.

Good fit Use it to create reviewer or specialist roles, configure subagents, validate role files, plan bounded delegation, or merge duplicate roles.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jscraik/agent-skills/codex-agent-creator"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/codex-agent-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,708 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 $0.00070 $0.01708
Opus 5 $0.00035 $0.00854
Sonnet 5 $0.00014 $0.00342
Haiku 4.5 $0.00007 $0.00171

Measured 8d ago against content hash f84f3ffe920d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

codex-agent-creator 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-agent-creator/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Codex Agent Creator

Purpose

Create, review, install, fold, or validate Codex custom subagent role files, routing manifests, task envelopes, and discoverability wiring. Prefer one valid role, explicit scope, runtime-state evidence, validation proof, and rollback over broad edits or duplicate agents.

Philosophy

Build the smallest role surface that can be validated from current Codex evidence.

When to Use

  • The user asks for a Codex custom subagent, reviewer/delegation role, role TOML, or role validation.
  • The work targets standalone role TOML, [agents.<name>], .codex/agents/*.toml, or duplicate role folding.
  • The user wants a bounded swarm or delegation plan that depends on Codex roles.
  • The user wants role routing, agent task envelopes, artifact-first reviewer output, blocked-agent classification, or agent boundary validation.

When Not to Use

  • The artifact should be a skill, hook, CI gate, MCP tool, AGENTS.md rule, or approval workflow.
  • The target is a projection, generated handle, cache, or mirror and a canonical source exists.
  • The user has not authorized global, user-scope, project-config, external, destructive, or ambiguous writes.

Inputs

  • Edit canonical sources only; do not hand-edit .agents/**, .skillsets/**, Plugins/cache/**, mirrors, or handles.
  • For agent-skills, read AGENTS.md and UBIQUITOUS_LANGUAGE.md before edits.
  • Ground Codex config keys from official docs, codex-repo, or local ~/dev/codex source before writing. Current source anchors include codex-rs/config/src/config_toml.rs, codex-rs/core/src/config/agent_roles.rs, and codex-rs/core/src/tools/handlers/multi_agents_spec.rs.
  • Confirm install scope before writing config; validation-only work writes no install config.
  • Prefer live runtime-state snapshots over chat memory when judging branch, head, dirty state, active agents, expected artifacts, or validation freshness.
  • Narrow each role request to one primary surface before editing: standalone role file, declaring [agents.<name>] table, routing manifest, task envelope, or artifact receipt contract. Keep scope tight by default; add a second surface only when it is required for discoverability or validation.

Read the full file on GitHub · 139 lines

Files

What ships with it

7 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 · 139 lines · 70 tokens per session scan A f84f3ffe920d

Subscribe to this mod's changes

codex-agent-creator is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,708 once invoked, about $0.0003 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.