A workflow for generating or editing bitmap images through CodexManager's image service. Bitmap images are pixel-based files such as photos, illustrations, mockups, and textures.

Use it to generate or edit visual assets, including website graphics, game assets, product mockups, wireframes, logos, and infographics, when CodexManager mode is requested or required.

It provides the project-specific way to create images using the configured provider and credentials, without setting up a separate image client.

cm-imagegen — Skill for Codex by qxcnm/Codex-Manager

About the project

Codex-Manager is a local account management and switching tool for the Codex command-line interface, with a local gateway that forwards requests. It is for users who need to manage multiple Codex CLI accounts and choose between them.

qxcnm/Codex-Manager · 3,014 stars · on GitHub

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 qxcnm/Codex-Manager --skill cm-imagegen

Clone the repo

git clone --depth 1 https://github.com/qxcnm/Codex-Manager

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/qxcnm/codex-manager/cm-imagegen/github.svg)](https://agentmods.dev/skills/qxcnm/codex-manager/cm-imagegen)

Your own site

<a href="https://agentmods.dev/skills/qxcnm/codex-manager/cm-imagegen"><img src="https://agentmods.dev/badge/skills/qxcnm/codex-manager/cm-imagegen/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/qxcnm/codex-manager/cm-imagegen"><img src="https://agentmods.dev/badge/skills/qxcnm/codex-manager/cm-imagegen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,296 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 25
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00082	$0.03296
Opus 5.5	$0.00033	$0.01318
Sonnet 5.5	$0.00016	$0.00659
Haiku 4.5	$0.00008	$0.00330

Measured 1mo ago against content hash c8e759b7674a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cm-imagegen 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 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/cm_image_gen.py), 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.

cm-skills/cm-imagegen/SKILL.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CM Image Generation Skill

Generates or edits images for the current project (for example website assets, game assets, UI mockups, product mockups, wireframes, logo design, photorealistic images, or infographics).

This skill follows the same request semantics, prompt workflow, decision tree, and output expectations as the official imagegen skill. The only intentional difference is the execution layer: image requests are sent to CodexManager's OpenAI-compatible Images API using the current Codex provider base_url and auth.json API key.

Top-level modes and rules

This skill has one top-level mode:

CodexManager CLI mode: bundled scripts/cm_image_gen.py CLI. It uses the current Codex configuration and calls CodexManager's image endpoints.

The CLI exposes two subcommands:

generate
edit

Rules:

Use this skill only when the user explicitly asks for CodexManager image generation or when the official built-in image_gen tool is unavailable in API-key/provider mode.
Do not ask the user for a separate image API key or image base URL by default.
Do not create one-off SDK runners.
Never modify the official system imagegen skill.

CodexManager config policy:

If CODEXMANAGER_IMAGE_BASE_URL is set, use it as the image request base URL.
Otherwise, read the active model_provider from $CODEX_HOME/config.toml.
Read that provider's base_url from [model_providers.<provider>].
Read OPENAI_API_KEY from $CODEX_HOME/auth.json.
Use CODEXMANAGER_IMAGE_MODEL only for the image model override; otherwise use gpt-image-2 for OpenAI-compatible Images providers, or image-01 when the provider base URL targets the image_generation API (minimax.io / minimaxi.com hosts).
When the provider base URL targets the image_generation API, the CLI calls POST /v1/image_generation with aspect_ratio/width/height/seed/n/prompt_optimizer/response_format request fields, passes --image inputs as subject_reference, and parses data.image_urls / data.image_base64 + base_resp.status_code; otherwise it calls the OpenAI Images /images/generations and /images/edits endpoints and parses data[].b64_json.
Use CODEXMANAGER_IMAGE_OUTPUT_DIR only for the output directory override; otherwise save under the current working directory's generated-images/ folder.

Read the full file on GitHub · 276 lines

Files

What ships with it

8 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.

1mo ago First seen · 276 lines · 82 tokens per session scan A c8e759b7674a

Subscribe to this mod's changes

cm-imagegen is a skill published in the GitHub repository qxcnm/Codex-Manager (3,014 stars, last pushed 6d ago), licensed MIT. It adds 82 tokens to every session and 3,296 once invoked, about $0.0003 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.

Creative and media

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

component-fixtures

Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.