Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add bengous/claude-code-plugins/plugin install agents-bridgeWrote 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.
[](https://agentmods.dev/skills/bengous/claude-code-plugins/imagegen)<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/imagegen"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/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.
<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/imagegen"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/imagegen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00065 | $0.01505 |
| Opus 5.5 | $0.00026 | $0.00602 |
| Sonnet 5.5 | $0.00013 | $0.00301 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade A, and why
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 14d 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image generation via Codex
The Codex CLI ships a built-in image_gen tool (no API key needed). It is
exposed by no flag — the model calls it when the prompt asks for an image.
This skill is the thin wrapper that gets the invocation right: writable sandbox,
destination directory, output path read back reliably.
Codex already owns the image-prompting policy — its system skill covers style, sizing, text accuracy, transparency and batching. Do not duplicate or override it: pass the user's request through and let Codex augment it. Dictate size, style or quality only when the user asked for them.
Resolve the destination first
The tool writes into ~/.codex/generated_images/<thread-id>/ — outside the
workspace, under a generated filename whose shape has changed between CLI
versions, so never predict it. There is no destination argument: without an
explicit copy instruction in the prompt, the image never leaves that directory.
So before invoking, decide an absolute destination path. The user's request
may name one after a -> (a fox -> ./art/fox.png); otherwise default to a
filename in the cwd. Resolve any relative path the user wrote against your own
cwd, then pass it absolute — the prompt is read inside codex, where a bare
./x.png means something else. -C must point at a directory that contains
the resolved destination: it is the writable workspace root, and it is what
makes the copy legal. The sandbox does not govern the tool's own write, only the
copy into the project.
Invocation
Use the path each command prints literally in every later step: shell variables do not survive between Bash calls.
# 1. Create the run directory; it prints <dir>:
"${CLAUDE_PLUGIN_ROOT}/scripts/codex-run.ts" new imagegen
# 2. Write <dir>/prompt.md <- the image request + the two instructions
# below. Strip any `-> destination` off the request first: it is this
# skill's routing syntax, not part of the image description.
# 3. Run it in write mode. Add --skip-git-repo-check when -C is not inside a
# git repo.
"${CLAUDE_PLUGIN_ROOT}/scripts/codex-run.ts" start <dir> --prompt-file <dir>/prompt.md --mode write -C /absolute/path/to/project
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.
- 14d ago Changed · -25 lines 999e5dd9fc2e
- 1mo ago Changed · +18 lines ba00f789ed43
- 1mo ago First seen · 134 lines · 65 tokens per session scan A 48b28e7a3f3e
imagegen is a skill published in the GitHub repository bengous/claude-code-plugins (5 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 1,505 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 2026-08-31.
Other skills, from other repositories
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
development
An index of programming guidance for Python, Go, Rust, TypeScript, Java, C++, and shell scripting.
tencent-docs
A Tencent Docs assistant for creating, reading, editing, organizing, importing, and exporting online documents, spreadsheets, presentations, diagrams, and forms.
wechat-search
Search WeChat Official Account articles using OpenClaw's web search, Tavily API, and web fetch capabilities with compliance-focused design.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error. Also load when a live run you started for the user fails with an error from…
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.