Codex-opus-4-6-prompting

Codex-opus-4-6-prompting is a skill for Claude Code, Codex from Kastalien-Research/thoughtbox. It costs 132 tokens per session (4,004 once invoked), scanned C, original, MIT.

A prompt-writing reference for Codex Opus 4.6 and related models. It explains how to make instructions clear, provide context, control output formats, and design tool-using workflows.

In plain words
What is it for?
Use it to write, review, or improve prompts for coding tasks, structured outputs, tool use, and agentic workflows.
Why use it?
It helps reduce ambiguity in prompts so the coding agent is more likely to produce the intended result.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions Codex.

Good fit Use it to write, review, or improve prompts for coding tasks, structured outputs, tool use, and agentic workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kastalien-research/thoughtbox/claude-opus-4-6-prompting
Install

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.

Any agent
npx skills add Kastalien-Research/thoughtbox --skill claude-opus-4-6-prompting
Clone the repo
git clone --depth 1 https://github.com/Kastalien-Research/thoughtbox

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for Codex-opus-4-6-prompting

README.md
[![agentmods](https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/claude-opus-4-6-prompting/github.svg)](https://agentmods.dev/skills/kastalien-research/thoughtbox/claude-opus-4-6-prompting)
Your own site
<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/claude-opus-4-6-prompting"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/claude-opus-4-6-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.

agentmods 80×15 button for Codex-opus-4-6-prompting

Your own site · 80×15
<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/claude-opus-4-6-prompting"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/claude-opus-4-6-prompting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,004 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00132 $0.04004
Opus 5 $0.00066 $0.02002
Sonnet 5 $0.00026 $0.00801
Haiku 4.5 $0.00013 $0.00400

Measured 12d ago against content hash 5edb4b9fd16b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

Codex-opus-4-6-prompting scanned grade C with 1 finding 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 12d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Destructive: deleting files/branches, dropping tables, rm -rf
.agents/skills/claude-opus-4-6-prompting/SKILL.md · 490 lines

How it starts

The opening of the file, as written. The whole thing — 490 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Opus 4.6 — Prompt Engineering Skill

This skill is the single reference for writing and tuning prompts targeting Codex Opus 4.6, Codex Sonnet 4.6, and Codex Haiku 4.5. Jump to the section that matches your situation.


1. General Principles

Be Clear and Direct

Codex responds well to explicit, specific instructions. Think of it as onboarding a brilliant but context-free new employee.

Golden rule: Show the prompt to a colleague with no task context. If they'd be confused, Codex will be too.

  • Specify the desired output format and constraints explicitly.
  • Use numbered lists or bullets for sequential steps where order matters.
  • Request "above and beyond" behavior explicitly — don't rely on inference.

Add Context and Motivation

Explain why an instruction matters. Codex generalizes from motivation, so brief rationale ("because our users are non-technical") often produces better calibration than exhaustive rules.

Use Examples Effectively (Few-Shot / Multishot)

Examples are the most reliable way to steer format, tone, and structure.

  • Wrap examples in <example> tags (multiple in <examples>).
  • Use 3–5 examples for best results.
  • Make examples relevant, diverse (cover edge cases), and structured.
  • Ask Codex to evaluate your examples for relevance/diversity, or to generate additional ones from your seed set.

Structure Prompts with XML Tags

XML tags help Codex parse complex prompts unambiguously when mixing instructions, context, examples, and variable inputs.

<instructions>...</instructions>
<context>...</context>
<examples>
  <example>...</example>
</examples>
<input>...</input>

Best practices:

  • Use consistent, descriptive tag names throughout a project.
  • Nest tags for natural hierarchies (e.g., <documents><document index="1">).

Give Codex a Role

A single sentence in the system prompt focusing Codex's role meaningfully changes behavior and tone:

system="You are a helpful coding assistant specializing in Python."

Read the full file on GitHub · 490 lines

Changes

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.

  1. 12d ago First seen · 490 lines · 132 tokens per session scan C 5edb4b9fd16b

Subscribe to this mod's changes

Codex-opus-4-6-prompting is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 132 tokens to every session and 4,004 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.