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/walker1211/codex-imgen/imgennpx skills add walker1211/codex-imgen --skill imgengit clone --depth 1 https://github.com/walker1211/codex-imgenWrote 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/walker1211/codex-imgen/imgen)<a href="https://agentmods.dev/skills/walker1211/codex-imgen/imgen"><img src="https://agentmods.dev/badge/skills/walker1211/codex-imgen/imgen.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.00867 |
| Opus 5 | $0.00036 | $0.00434 |
| Sonnet 5 | $0.00015 | $0.00173 |
| Haiku 4.5 | $0.00007 | $0.00087 |
Grade A, and why
imgen 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 3d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
imgen
Use this skill to operate the codex-imgen CLI, service jobs, realtime mode, and OpenClaw integration.
Route the request
Read only the references needed for the request:
references/imgen-usage.md: commands, configuration, backend behavior, service/realtime selection, and the OpenClaw delivery contract.references/prompt-patterns.md: prompt wording for text-to-image or image-to-image requests.references/troubleshooting.md: failed, slow, retried, stuck, or missing-image runs.
Combine references only when the request spans those concerns.
Ask only necessary questions
If the user gave enough information, provide the command or steps directly.
Ask one question only when a required value is missing:
- Missing image prompt for generation.
- Missing local image path for image-to-image.
- Missing job id for
status,get,cancel, or job-specific troubleshooting. - Missing choice between synchronous CLI, service job, or realtime only when the goal does not determine it.
Do not ask for preferences that are not needed to produce a safe minimal command.
Command rules
- Use the shortest command that satisfies the request.
- Default one-shot generation, including normal OpenClaw requests, to synchronous
./imgen --json ...from a discovered config working directory. - Use repeated
--image <local-path>flags for references; URLs are not supported. - Use
--count Nand--concurrency Mfor quantity while keeping the prompt about one image. - Use
submitonly for job management, polling, cancellation, or recovery. Use realtime only for live WebSocket events whileimgen serveis running. - Treat success as returned image paths: text path lines, or
ok: truewith non-emptyimages[].path. Exit code 0 alone is insufficient. - For OpenClaw, follow the full contract in
references/imgen-usage.md; never substituteimage_generate, directcodex exec, or stale paths.
Safety and configuration rules
- Treat
.envas the only place for sensitive values such asEMAIL_SMTP_AUTH_CODE. - Treat
configs/config.yamlas the local structured configuration file. - Do not suggest committing
configs/config.yaml,.env, generated images, logs, or.data/imgen.db. - Do not suggest
0.0.0.0service binding unless the user explicitly asks for LAN access and understands the exposure. - Do not bypass Codex CLI login, permissions, or
$imagegenavailability checks. - Inspect
backend.modelandbackend.reasoning_effortbefore describing the active Codex agent configuration. The skill itself does not choose either value. - Do not call
backend.modelthe image-generation model; it selects the Codex agent that invokes$imagegen.
What ships with it
4 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.
- 3d ago First seen · 79 lines · 73 tokens per session scan A 3ed846158f62
imgen is a skill published in the GitHub repository walker1211/codex-imgen (2 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 867 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
mobilevc-installer
Install and start MobileVC — a Claude Code mobile workspace launcher that lets the user run Claude Code on a phone (iOS / Android) with their dev machine as the backend. Use this skill when the user asks to: "install mobilevc" / "set up mobilevc" / "装一个 mobilevc" "在手机上用 Claude Code" / "want to use Claude Code on my…
sprite-atlas-builder
Sprite atlas pipeline. Use for sprites, tilesets, textures, asset sheets, extraction, curation, and QA.
codex-studio-setup
Set up a local Codex Studio checkout end to end from the welcome-screen handoff prompt.
add
Turn a plain-language guardrail into a handrail Rule file, validate it, and relay the native permission entry handrail recommends. Use when the user wants to add, write, or create a handrail rule, or says "never let the agent ...", "block ...", "warn me when ..." and wants it enforced from now on.
analyze
Mine the current session for behaviors worth preventing and propose handrail Rules for them, with transcript evidence and per-rule approval. Use when the user wants to turn this session's corrections into guardrails, or says "analyze this session", "what should I have blocked", "make that a rule so it never happens…
codexcw
Run Codex, Claude Code, or Grok Build non-interactively from Go, Rust, Node.js, Python, or C# using the codexcw library. Use when building automation that spawns an agent, streams its JSONL events, resumes sessions, or controls sandbox, approval, and permission policy.