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.
npx agentmods add skills/viisopen/get-codex-theme/create-codex-themenpx skills add ViisOpen/get-codex-theme --skill create-codex-themegit clone --depth 1 https://github.com/ViisOpen/get-codex-themeWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00083 | $0.03423 |
| Opus 5 | $0.00042 | $0.01711 |
| Sonnet 5 | $0.00017 | $0.00685 |
| Haiku 4.5 | $0.00008 | $0.00342 |
Grade A, and why
create-codex-theme 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Codex Theme
Create and locally verify a release candidate without modifying the signed Codex application. Keep filesystem creation, user-authorized live QA, official native settings, and unofficial visual-background delivery clearly separated.
Human guidance and agent execution
Keep these two surfaces separate:
- A human-facing wizard may explain choices, preview paths, and ask only for creative intent, unavoidable rights facts, and bounded local-state authorization.
- A Codex agent must translate the user's natural-language intent into one
deterministic creation invocation, followed by explicit coverage and
validation commands. It must use
--non-interactivefor creation, must not wait for terminal prompts, and must fail closed when a required input is unknown.
When a Get Codex Theme website prompt includes a creative brief, an asset record, an autonomy contract, and explicit local-QA authorization, treat that prompt as the complete guided Create contract. Do not ask again for id, name, mode, authoring path, preset, component groups, output directory, background strategy, description, tagline, design story, tags, author display name, pack license, image approval, local install permission, or visual acceptance. Derive those values and evaluate the available automated evidence as directed by the prompt. This authorization never includes launching, quitting, restarting, or capturing private Codex surfaces.
Before executing, write a short contract with these headings:
- Goal: the pack to create and whether the result is a draft or release candidate.
- Context: known id, name, mode, source image, output directory, authoring path, selected component groups, preset, and asset rights.
- Constraints: no overwrite, no inferred redistribution rights, bounded component tokens only, no live changes before static validation, and no launch, restart, or capture without explicit permission.
- Done when: creation succeeds, coverage and strict validation pass, the exact pack is installed only after authorization, real-Codex visual QA and restore are confirmed, and the final completion state is reported truthfully.
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.
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.
- yesterday First seen · 272 lines · 83 tokens per session scan A ea8ca7003086
create-codex-theme is a skill published in the GitHub repository ViisOpen/get-codex-theme (1 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 3,423 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
codedrobe-theme
Create, inspect, convert, apply, replace, verify, troubleshoot, update, publish, or restore reversible CodeDrobe themes for supported Chromium/Electron AI desktop apps, including OpenAI Codex, Tencent WorkBuddy, QoderWork (CN/global), and TRAE SOLO (global/CN). Use when a user asks to turn an attached or local…
codedrobe-adapter-dev
Add, inspect, repair, or validate CodeDrobe Core adapters for Chromium/Electron AI desktop applications. Use when supporting a new app, updating Codex or WorkBuddy compatibility after an app release, discovering installation paths or CDP targets, selecting stable DOM landmarks, adding renderer profiles or…
codex-memory-trim
Manage Codex's native global memory (/.codex/memories) with three sub-procedures - trim (audit + dedupe + three-layer cleanup), compress (rewrite verbose memories into concise form), and add-global (add a custom global rule/preference). Use when the user asks to 精简/清理/整理/压缩 Codex 记忆, 去重, 简化冗长记忆, 添加/写入/修改全局记忆 or a…
CodexClaw
Install and operate a Telegram bot that exposes Codex, MCP, GitHub subagents, repo switching, and minimal frontend dev-server control.
consult
Ask a second AI model (Claude Code or Kimi Code) for an independent opinion on a hard problem in this Home Assistant config. Use when the user asks for a second opinion or another model's view, when two or more of your own attempts at a bug have failed, or before a change that is hard to undo such as editing…
eco-max
Maximum-savings variant of eco - the same frugality rules with a tighter reply budget, for routine chores (rename, small fix, quick lookup, boilerplate). Prefer plain eco for hard or high-stakes work. Works in any language.