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 stdevMac/grok-in-codex --skill grok-promptinggit clone --depth 1 https://github.com/stdevMac/grok-in-codexWrote 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/stdevmac/grok-in-codex/grok-prompting)<a href="https://agentmods.dev/skills/stdevmac/grok-in-codex/grok-prompting"><img src="https://agentmods.dev/badge/skills/stdevmac/grok-in-codex/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/stdevmac/grok-in-codex/grok-prompting"><img src="https://agentmods.dev/badge/skills/stdevmac/grok-in-codex/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 | $0.00021 | $0.00186 |
| Opus 5.5 | $0.00008 | $0.00074 |
| Sonnet 5.5 | $0.00004 | $0.00037 |
| Haiku 4.5 | $0.00002 | $0.00019 |
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
Reshape a rescue request into a tighter prompt before the single task call.
Shape
- Goal — one sentence
- Context — what failed / what matters
- Constraints — no drive-by refactors, test expectations, worktree if requested
- Done when — measurable checks (
--checkhelps)
Do
- Preserve file names, errors, and commands the user mentioned
- Ask for verification via tests/build when fixing bugs
- Keep it short
Do not
- Inspect the repo yourself
- Invent stack traces
- Solve the problem in the prompt
- Embed model/effort/resume flags in the natural-language body
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 · 30 lines · 21 tokens per session scan A 7378bddb1646
grok-prompting is a skill published in the GitHub repository stdevMac/grok-in-codex (27 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 186 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 2026-08-30.
Other skills, from other repositories
grok-prompting
How to shape a good prompt before delegating to Grok via the grok-rescue subagent or /grok-cc:rescue. Use when tightening a vague user request into a crisp Grok task. Covers stating the goal, constraints, acceptance criteria, and scope so a one-shot headless Grok run succeeds.
gpt-5-4-prompting
Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Grok Codex plugin.
ima2
Use the ima2-gen CLI/server to generate, edit, inspect, and manage local AI image generation jobs.
zero-shot
Use when the user asks to "check zero-shot", "audit few-shot anchoring", "find example anchoring", or invokes /zero-shot. Read-only audit of LLM-facing prose: principle over anchoring examples.
dspy-prompt-optimizer
Tunes prompts iteratively using reflection and success metrics. Use for: optimize this prompt, dspy tune, improve prompt with reflection, self-refine-loop.
metaprompt
Generate a complete, ready-to-paste prompt engineered for a specific target model (Claude Fable 5.1 / Opus 5.5 / Sonnet 5 / Haiku 4.5, GPT-5.x) and harness (Claude Code CLAUDE.md or skill, Codex AGENTS.md, pi, Amp, eve, AI Gateway, Agent SDK, raw API, chat UI), using per-model and per-harness reference guides. Trigger…