agentmods.dev

QQ_agentshow

QQ_agentshow is a skill for Codex from tangyihang-jiayou/QQ_agentshow. It costs 37 tokens per session (377 once invoked), scanned A, original, MIT.

A macOS setup and maintenance tool for applying and managing a custom appearance for Codex, including personalization and restoration.

In plain words
What is it for?
Use it to install or update the appearance, personalize it, verify that it works, repair problems, or restore Codex's original appearance.
Why use it?
It avoids manually installing, checking, repairing, or undoing the appearance changes. It also keeps an existing theme and personalization during updates.

Skill for Codex

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

not rated 12repo 3mo ago A scan 37 tokens original MIT

Good fit Use it to install or update the appearance, personalize it, verify that it works, repair problems, or restore Codex's original appearance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tangyihang-jiayou/qq_agentshow/macos
View source ↗ tangyihang-jiayou/QQ_agentshow
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 tangyihang-jiayou/QQ_agentshow --skill macos
Clone the repo
git clone --depth 1 https://github.com/tangyihang-jiayou/QQ_agentshow

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 QQ_agentshow

README.md
[![agentmods](https://agentmods.dev/badge/skills/tangyihang-jiayou/qq_agentshow/macos/github.svg)](https://agentmods.dev/skills/tangyihang-jiayou/qq_agentshow/macos)
Your own site
<a href="https://agentmods.dev/skills/tangyihang-jiayou/qq_agentshow/macos"><img src="https://agentmods.dev/badge/skills/tangyihang-jiayou/qq_agentshow/macos/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 QQ_agentshow

Your own site · 80×15
<a href="https://agentmods.dev/skills/tangyihang-jiayou/qq_agentshow/macos"><img src="https://agentmods.dev/badge/skills/tangyihang-jiayou/qq_agentshow/macos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 377 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 $0.00037 $0.00377
Opus 5.5 $0.00015 $0.00151
Sonnet 5.5 $0.00007 $0.00075
Haiku 4.5 $0.00004 $0.00038

Measured 2mo ago against content hash 48baef49007b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

QQ_agentshow 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 2mo ago.

The scan reads SKILL.md. This mod also ships 20 executable files (assets/renderer-inject.js, menubar/codex_dream_skin.10s.sh, presets/generate-presets.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

macos/SKILL.md · 22 lines

What it actually says

QQ_agentshow macOS runtime

Use this self-contained entry when the installed runtime or standalone macOS release is opened independently. The full repository also provides a product-level Skill with public installation, privacy, and configuration guides.

Runtime workflow

  1. Resolve every relative path against the directory containing this SKILL.md, change the working directory to that standalone engine root, ask the user to open Codex once, then quit it completely.
  2. Run scripts/install-dream-skin-macos.sh --check. Stop if readiness fails.
  3. Run scripts/install-dream-skin-macos.sh --no-launch. An update preserves the active theme and existing Codex 2007 personalization.
  4. On a fresh install only, the installer selects preset-codex-1907-deep; do not switch an updating user back to it.
  5. Start with scripts/start-dream-skin-macos.sh --prompt-restart.
  6. Configure with scripts/personalize-codex-2007-macos.sh and verify with scripts/verify-dream-skin-macos.sh; the default sound setting enables both task-completion and first human-confirmation cues from the installed local payload.
  7. Restore with scripts/restore-dream-skin-macos.sh --restore-base-theme --restart-codex.

Never modify the official app bundle, move native Codex content nodes, invent right-rail data, bind CDP beyond loopback, or signal a process whose recorded identity does not match.

Files

What ships with it

60 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. 2mo ago First seen · 22 lines · 37 tokens per session scan A 48baef49007b

Subscribe to this mod's changes

QQ_agentshow is a skill published in the GitHub repository tangyihang-jiayou/QQ_agentshow (12 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 377 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

agent-uicodexcodex-skilldesktop-customizationmacosnotification-sounds
Related

QQ_agentshow compared with skills from other repositories

QQ_agentshow next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
QQ_agentshowtangyihang-jiayou/QQ_agentshowSkill123mo agoMITA37Codex
deep-clean-ai-skillmadebypan/deep-clean-ai-skillSkill222mo agoMITA123Codex
AI-UIconfig-skillvoderment/AI-UIconfig-skillSkill56mo agoMITA73Claude Code, Codex
codex-dream-skinaithink001/Codex-Dream-Skin-ThemesSkill603mo agononeB126Codex
agui-dotnet-streaming-chatag-ui-protocol/ag-uiSkill17kyesterdayMITA223Claude Code
agui-dotnet-protobufag-ui-protocol/ag-uiSkill17kyesterdayMITA162Claude Code
notificationsvellum-ai/vellum-assistantSkill1.5k2d agoMITA9Claude Code, Codex