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 commands/arielaizn/grok-plugin-cc/imagegit clone --depth 1 https://github.com/arielaizn/grok-plugin-ccWrote 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/commands/arielaizn/grok-plugin-cc/image)<a href="https://agentmods.dev/commands/arielaizn/grok-plugin-cc/image"><img src="https://agentmods.dev/badge/commands/arielaizn/grok-plugin-cc/image.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 | $0.00009 | $0.00452 |
| Opus 5 | $0.00005 | $0.00226 |
| Sonnet 5 | $0.00002 | $0.00090 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
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 5d 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.
What it actually says
Generate one or more images with Grok's image_gen tool.
Raw slash-command arguments:
$ARGUMENTS
Argument handling:
- Pass the user's arguments through unchanged. Do not rewrite, translate, expand, or "improve" the prompt — the companion sends it to
image_genverbatim on purpose, and rewriting it silently discards the user's art direction. - If the user gave no prompt at all, ask for one instead of inventing a subject.
--countabove 1 produces variations of the same subject.- If the user wants Grok to elaborate on a terse prompt, they can pass
--verbatim=false.
Execution:
- A single image takes roughly 30 seconds. Run in the foreground unless the user passed
--background, or asked for--count 4or more.
Foreground:
node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-companion.mjs" image $ARGUMENTS
Background — launch it and stop there, do not poll in the same turn:
Bash({
command: `node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-companion.mjs" image $ARGUMENTS`,
description: "Grok image generation",
run_in_background: true
})
Then tell the user it is running and that /grok:status shows progress.
Output rules:
- Relay the companion's output, which lists each saved file with its path.
- Then
Readeach saved image so the user can see it inline. This is the one place re-reading is worth it: the user asked for a picture, and a list of paths is not a picture. - Do not claim an image "looks good" or describe its quality beyond what you can actually see.
- If the run failed, relay the reason verbatim. Do not retry automatically — image generation costs money on every attempt.
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.
- 5d ago First seen · 47 lines · 9 tokens per session scan A 1d7a11ff9698
image is a command published in the GitHub repository arielaizn/grok-plugin-cc (6 stars, last pushed 21d ago), licensed MIT. It adds 9 tokens to every session and 452 once invoked, about $0.0000 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.