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 faeton/claude-grok-plugin --skill grok-promptinggit clone --depth 1 https://github.com/faeton/claude-grok-pluginWrote 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/faeton/claude-grok-plugin/grok-prompting)<a href="https://agentmods.dev/skills/faeton/claude-grok-plugin/grok-prompting"><img src="https://agentmods.dev/badge/skills/faeton/claude-grok-plugin/grok-prompting/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/faeton/claude-grok-plugin/grok-prompting"><img src="https://agentmods.dev/badge/skills/faeton/claude-grok-plugin/grok-prompting.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 | $0.00023 | $0.00389 |
| Opus 5.5 | $0.00009 | $0.00156 |
| Sonnet 5.5 | $0.00005 | $0.00078 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
grok-prompting 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 1mo 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
Grok Prompting
Use this skill when grok:grok-consult needs to tighten the user's request into a better Grok prompt before the single companion call. Prompt drafting is the only Claude-side work allowed — never solve the task yourself.
Principles:
- One clear ask per run. Split unrelated questions into separate consults.
- State what a good answer looks like (format, length, what to optimize for) instead of assuming Grok will infer it.
- Give Grok the grounding it needs as
--filecontext rather than pasting huge blobs into the question — the companion attaches files cleanly and caps their size. - For a second opinion, frame it adversarially: ask Grok to find what is wrong or risky, not to agree. Grok is most useful as an independent skeptic.
Recipe for a consult:
- Lead with the concrete question in one or two sentences.
- Add the decision or constraint that matters ("must stay zero-dependency", "targeting Node 18", "this is hot-path code").
- Name the output shape: "answer in ≤5 bullets", "give the literal flags", "rank the options".
- Attach relevant files with
--fileinstead of describing them.
Recipe for a review:
- Prefer
review(it builds the diff prompt for you). Useadversarial-review <focus>when the user wants a specific hunt (e.g. "concurrency bugs in the new pool", "auth bypass paths"). - Keep focus text specific and falsifiable.
Keep Grok requests compact. The relay can cancel very large generations — if a request is huge, narrow the scope or split it rather than sending one giant prompt.
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.
- 1mo ago First seen · 28 lines · 23 tokens per session scan A d44d55323b71
grok-prompting is a skill published in the GitHub repository faeton/claude-grok-plugin (1 stars, last pushed 4d ago), licensed MIT. It adds 23 tokens to every session and 389 once invoked, about $0.0001 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
grok-prompting
Internal guidance for composing Grok Build prompts for coding, review, diagnosis, and research tasks inside the Grok Claude Code plugin.
meta-prompting
Enhanced reasoning patterns via slash commands (/think, /verify, /adversarial, /edge, /compare, /confidence, /budget, /constrain, /json, /flip, /assumptions, /tensions, /analyze, /trade) or natural language ("argue against", "what could break", "show reasoning", "deep review", "meta-prompts", "thinking modes"…
review-prompt
Review LLM prompts against the prompt-engineering skill's principles — leading with where each line came from — and report the findings without modifying files. Use when reviewing prompt quality, auditing a prompt, evaluating a system prompt, or checking whether prompt issues are high-confidence and fixable.
refine-prompt
Transforms vague or rough prompts into precise, structured AI instructions. Use when asked to "refine prompt", "improve prompt", "make this prompt better", "promptify", "optimize prompt", "rewrite prompt", "enhance prompt", or "sharpen instructions".
gemini-prompting
Internal guidance for composing Gemini and AGY prompts for coding, review, diagnosis, and research tasks inside the Gemini Claude Code plugin.
model-sovereignty
This skill should be used when the user asks about "local models", "custom models", "fine-tuning", "self-hosting models", "model selection", "which model should I use", "data privacy and models", "LoRA", "RAG vs fine-tuning", "Ollama", "vLLM", or wants guidance on whether to build, host, or customise their own AI…