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 Lykhoyda/ask-llm/plugin install ask-llmWrote 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/lykhoyda/ask-llm/ask-llm-codex-image)<a href="https://agentmods.dev/skills/lykhoyda/ask-llm/ask-llm-codex-image"><img src="https://agentmods.dev/badge/skills/lykhoyda/ask-llm/ask-llm-codex-image/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/lykhoyda/ask-llm/ask-llm-codex-image"><img src="https://agentmods.dev/badge/skills/lykhoyda/ask-llm/ask-llm-codex-image.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 | $0.00098 | $0.02247 |
| Opus 5.5 | $0.00039 | $0.00899 |
| Sonnet 5.5 | $0.00020 | $0.00449 |
| Haiku 4.5 | $0.00010 | $0.00225 |
Grade A, and why
ask-llm-codex-image 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.
This is a copy
86% identical to codex-image — 124 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Portable contract
Refine the requested image prompt without changing intent, select an explicit output path, invoke Codex with sandbox: "workspace-write" so its image tool may create the file, verify the resulting file on disk, and report the path and provider response. Surface feature, policy, timeout, and filesystem failures verbatim.
Host adapters
Pi adapter
Call native ask-codex with sandbox: "workspace-write". After it returns, use Pi's read-only filesystem tools to verify the output file. Do not claim automatic inline rendering in print mode.
Other hosts adapter
Codex, Cursor Agent, Antigravity, Grok Build, Gemini CLI and OpenCode get this skill from their skills folder, not from a plugin. Use the Codex call from ../ask-llm-review/transport.md with sandbox: "workspace-write" and the exact model the user named (gpt-6-astra otherwise), then read the output file to confirm it exists.
Claude Code adapter
The existing detailed workflow below is the Claude Code adapter. Its Agent, MCP, hook, CLAUDE_PLUGIN_ROOT, and AskUserQuestion mechanics apply only on Claude Code; they do not override the Pi adapter above.
Codex Image Generation
Generate an image by delegating to the ask-codex MCP tool with a prompt-engineered template that triggers Codex's built-in image_generation tool. The result is saved to disk and the path is returned to the user.
Model capabilities (gpt-image-2)
Codex's image_generation tool selects the image model server-side; as of 2026-04-21 that is gpt-image-2. Three capabilities are worth accounting for when building prompts:
- Legible in-image text — per OpenAI's launch materials, gpt-image-2 renders text at ~99% accuracy across many scripts, so captions, labels, and UI copy are now reliable. gpt-image-1's weak text is no longer a reason to avoid asking for it.
- High resolution — up to 4K and custom dimensions; ask for it explicitly in the prompt body when you need it. Default square renders observed in testing varied (1024×1024 and 1254×1254), so don't hard-code an expected size — read it back from the file if it matters.
- Provenance + watermark — every render embeds a C2PA provenance manifest and an invisible AI-origin watermark. Flag this to the user when the image is destined for a context sensitive to AI-generated-content metadata.
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 First seen · 125 lines · 98 tokens per session scan A 8427d4efc3e8
ask-llm-codex-image is a skill published in the GitHub repository Lykhoyda/ask-llm (18 stars, last pushed 2d ago), licensed MIT. It adds 98 tokens to every session and 2,247 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to codex-image, differing in 124 lines, and is treated as a copy.
Other skills, from other repositories
skill-provenance
Version, validate, package, verify, recover, and hand off Agent Skill bundles across local folders, registries, platform uploads, and agent sessions. Use for MANIFEST.yaml, CHANGELOG.md, bundle hashes, stale evals, frontmatter portability, derived skill packages, or version identity that must survive filename changes…
bootstrap
Add version tracking to an existing unversioned skill bundle. Use when you have a skill project with SKILL.md but no MANIFEST.yaml, no version headers, and no changelog. Creates the initial manifest, adds version metadata to files, and generates the first changelog entry. Triggers on: "bootstrap this skill", "add…
close
Update version tracking when finishing work on a skill bundle. Use when you're done editing a skill project and need to bump version headers, recompute manifest hashes, update the changelog, flag stale files, or prepare a commit message. Triggers on: "close the session", "update versions", "save the bundle", "I'm done…
validate
Run a focused validation check for a skill bundle. Use when the user asks to validate, verify hashes, check MANIFEST.yaml, confirm files are present, or distinguish a canonical bundle from a derived install or registry copy without opening or closing a full editing session.
open
Verify a skill bundle's integrity when opening a project. Use when loading a skill project directory and you need to check file completeness, verify SHA-256 hashes against MANIFEST.yaml, detect stale files, review recent changes, or understand what state the bundle is in before starting work. Triggers on: "open this…
handoff
Generate a handoff note summarizing skill project state for a future session or collaborator. Use when crossing a non-persistent boundary (e.g., Chat upload), ending a session that made significant decisions, or when the user explicitly asks for a handoff note. Triggers on: "generate a handoff", "write a handoff…