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 skills add guihai24/openskills --skill grok-imagegit clone --depth 1 https://github.com/guihai24/openskillsWrote 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/guihai24/openskills/grok-image)<a href="https://agentmods.dev/skills/guihai24/openskills/grok-image"><img src="https://agentmods.dev/badge/skills/guihai24/openskills/grok-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/guihai24/openskills/grok-image"><img src="https://agentmods.dev/badge/skills/guihai24/openskills/grok-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 | $0.00248 | $0.01343 |
| Opus 5 | $0.00124 | $0.00672 |
| Sonnet 5 | $0.00050 | $0.00269 |
| Haiku 4.5 | $0.00025 | $0.00134 |
Grade A, and why
grok-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 8d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grok Image Generation Skill
Workflow
- Receive description — the user describes what they want in any language
- Craft prompt — translate to English, add style-appropriate quality keywords
- Pick model — choose variant based on need (see Model Selection below)
- Generate — run the script; it handles provider discovery and failover
- Display — Read the output image file to show the user
- Deliver — ALWAYS send to IM after display using
send.shwithautorouting. Only skip if the user explicitly says they don't need delivery, or if running in direct CLI mode with no IM channels configured.
Commands
Generate
bash ${CLAUDE_SKILL_DIR}/bin/generate.sh "<english_prompt>" [size] [model]
| Parameter | Required | Default | Options |
|---|---|---|---|
| prompt | yes | — | English text |
| size | no | 1024x1024 | 1024x1024, 1024x1792, 1792x1024 |
| model | no | grok-imagine-1.0 | grok-imagine-1.0, grok-imagine-1.0-fast, grok-imagine-1.0-edit |
The script:
- Reads providers from
~/clawd/proxy/config.json - Tries each matching provider, falling back to other grok-imagine variants
- Skips auth errors (401/403), retries on rate limits (429) and timeouts
- Outputs image path to stdout on success, exits 1 on failure
Send to IM
bash ${CLAUDE_SKILL_DIR}/bin/send.sh <image_path> [channel]
| Parameter | Required | Default | Options |
|---|---|---|---|
| image_path | yes | — | Local file path |
| channel | no | auto | feishu, telegram, discord, all, auto |
Source-aware routing: In auto mode (default), the script reads the claude-to-im
bridge's binding data to detect which channel sent the current request, and routes
the image back to that same channel. If the request came from Telegram, the image
goes to Telegram; if from Feishu, it goes to Feishu. If detection fails (e.g. direct
CLI usage), it falls back to the first available channel.
When delivering images, prefer using auto (omit the channel argument) so the image
goes back to wherever the request came from. Only specify a channel explicitly when
the user asks for a specific destination (e.g. "发到飞书" → feishu, "send to all" → all).
What ships with it
5 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.
- 8d ago First seen · 115 lines · 248 tokens per session scan A 362132adf98a
grok-image is a skill published in the GitHub repository guihai24/openskills (2 stars, last pushed 3d ago), licensed MIT. It adds 248 tokens to every session and 1,343 once invoked, about $0.0012 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
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.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.