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 Kastalien-Research/thoughtbox --skill claude-opus-4-6-promptinggit clone --depth 1 https://github.com/Kastalien-Research/thoughtboxWrote 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/kastalien-research/thoughtbox/claude-opus-4-6-prompting)<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.
<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>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 | $0.00132 | $0.04004 |
| Opus 5 | $0.00066 | $0.02002 |
| Sonnet 5 | $0.00026 | $0.00801 |
| Haiku 4.5 | $0.00013 | $0.00400 |
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 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."
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.
- 12d ago First seen · 490 lines · 132 tokens per session scan C 5edb4b9fd16b
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.
Other skills, from other repositories
octave-ultra-mythic
Ultra-high density compression using mythological atoms and semantic shorthand. Preserves soul and constraints at 60% compression for identity transmission, binding protocols, and extreme token scarcity. REQUIRES octave-mastery and octave-compression.
laravel-ai-sdk
Use when integrating AI agents, tool calling, embeddings, structured output, or streaming in Laravel 13 via the laravel/ai package.
prompt-library
Use when looking for a ready-made agent or task template (code review, support, data analysis, translation, extraction) instead of writing one from scratch.
prompt-testing
Use when comparing two prompt variants, defining quality/efficiency/robustness metrics, or deciding whether to adopt a challenger prompt over a baseline.
gigachat-chat
A chat command that sends a user prompt to GigaChat, an AI text-generation service, through MCP, a way for tools to connect to an agent. It can pass a model and temperature and reports the model and token counts.
prompt-creation
Use when writing a new system prompt from scratch, structuring it with Anthropic's 9-element format, or choosing emphasis levels and few-shot examples.