codex-image-gallery

An agent skill by daymade, from daymade/claude-code-skills. Tags: gallery, local-workflow, search, visual-art, web.

What it does

Start or reuse a self-contained local web gallery for browsing Codex-generated images. Use when the user asks to browse Codex generated images, open a local image gallery, inspect ~/.codex/generated_images, view a Codex image output folder, or browse image files produced by Codex.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add daymade/claude-code-skills --skill codex-image-gallery

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/daymade-codex/codex-image-gallery ~/.claude/skills/codex-image-gallery

Safety box score

Grade B, low risk: 11 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill runs a local Node gallery server to browse image files, by default indexing `~/.codex/generated_images` and serving those files over localhost. The main risk is filesystem exposure: it recursively reads and exposes whatever image root you point it at, and the UI shows/copies full local paths.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	It executes a shipped Node server (`node scripts/server.mjs`) and uses shell/Node checks like `node -e 'fetch(...)'`, but the code is self-contained and narrowly scoped.
Network access	0 (none)	The only network use is local-only (`http://127.0.0.1:8765/` and `fetch("http://127.0.0.1:8765/api/images")`); nothing in the skill contacts remote hosts.
Filesystem reach	2 (moderate)	It recursively reads a home dot-directory by default (`path.join(os.homedir(), ".codex/generated_images")`) and serves files from the selected image root, which is a real but bounded filesystem exposure.
Secrets & credentials	0 (none)	The files do not request, read, or export tokens, passwords, `.env` files, keychains, or browser sessions.
Privilege & persistence	0 (none)	There is no sudo, global install, service registration, or shell/OS configuration change in the skill.
Instruction hijack surface	0 (none)	There is no instruction to ignore safeguards, hide behavior, or follow remote instructions; the content is straightforward local gallery logic.
Irreversible actions	0 (none)	The skill only starts/reuses a local viewer and opens it in a browser; it does not post, deploy, pay, delete, or send messages.
Transparency	0 (none)	All shipped logic is readable source (`scripts/server.mjs` and `assets/index.html`); there are no binaries, minified blobs, or downloaded installers.

Before installing

Check `scripts/server.mjs` if you may point `GALLERY_ROOT` at a sensitive folder; it will serve whatever image tree you choose.
Verify that exposing `~/.codex/generated_images` over localhost is acceptable in your environment.
If you plan to reuse the gallery, confirm the port/bind settings stay on `127.0.0.1` and are not overridden in your shell environment.

Rated 2026-10-20 by an automated review of 4 files from the skill's repository.

Source

Repository: daymade/claude-code-skills (all skills from this repository)
Path: daymade-codex/codex-image-gallery/SKILL.md
Branch: main
Updated: 2026-09-20

aws-blocks — Guides building full-stack applications with AWS Blocks — an Infrastructure-from-Code framework.
schema — When the user wants to add, fix, or optimize schema markup and structured data on their site.
frontend-visual-qa — Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system.
read-claude-code-history — Reads, searches, and exports local Claude Code history without resuming work.
read-codex-history — Reads, searches, and exports local OpenAI Codex history without continuing the old task.
algorithmic-art — Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code.