Borrowing it
Nothing to install: this file belongs to Dynokostya/just-works. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Dynokostya/just-works/main/.claude/skills/gpt-6-prompting/SKILL.mdgit clone --depth 1 https://github.com/Dynokostya/just-worksWrote 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/dynokostya/just-works/gpt-6-prompting)<a href="https://agentmods.dev/skills/dynokostya/just-works/gpt-6-prompting"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/gpt-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/dynokostya/just-works/gpt-6-prompting"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/gpt-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 | $0.00068 | $0.03172 |
| Opus 5.5 | $0.00027 | $0.01269 |
| Sonnet 5.5 | $0.00014 | $0.00634 |
| Haiku 4.5 | $0.00007 | $0.00317 |
Grade A, and why
gpt-6-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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GPT-6 Prompt Writing Guidelines
When to Use
- Creating or editing prompts targeting GPT-6 (
gpt-6-astra,gpt-6.1-sol,gpt-6-luna) - Writing or auditing skills and AGENTS.md files that GPT-6 models will read
- Tuning persistence, approval boundaries, writing style, delegation, and testing behavior
- Migrating prompt text from GPT-5.6 or older GPT models
- Diagnosing Astra behaviors: early stops for review, unneeded questions, detailed formatted output, over-testing, under-delegation
Overview
GPT-6 is OpenAI's frontier family: gpt-6-astra (highest intelligence, the main focus of this skill), gpt-6.1-sol (near-Astra performance at lower cost), and gpt-6-luna (fast, low cost, high volume). The earlier gpt-6-sol is still an API model with different reasoning-effort support (see the table). Source: https://developers.openai.com/api/docs/guides/latest-model.
OpenAI's prompt snippets address behavior observed with Astra. Evaluate them on the model and workload you target before applying them to Sol or Luna. The reverse also holds: "Guidance that helps Sol or Luna may overconstrain GPT-6 Astra" (https://developers.openai.com/blog/rethinking-skills-and-prompts-for-gpt-6-astra).
The core discipline is lean prompting. On Astra, "what used to require a lot of handholding and scaffolding no longer does," and "overly specific guidance can now hinder results where it previously helped" (same blog post). Prompts, skills, and AGENTS.md files carried over from GPT-5.6 are the most common source of regressions because several Astra defaults reverse GPT-5.6 behavior.
- Tentative by default: asks a question when extra input could materially change the result, including non-blocking questions while it works. This can stop work where the user expected reasonable assumptions and persistence.
- Early review stops: may reach a first implementation and return for review while work remains (blog, "Persistence").
- Stronger instruction following: more sensitive to instructions in prompts, skills, and AGENTS.md. Conflicting or unclear guidance can make it pause and block work early. State each rule once.
- Detailed, formatted output: tends toward lists, tables, Markdown, and recurring phrases across sessions. Specify writing style and structure.
- Tests on its own: carried-over "always run tests" nudges produce unnecessary testing.
- Under-delegates: may use subagents less than the workflow wants. Say when delegation is expected.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago Changed · -12 tokens per session 4790a2f39f9e
- 17d ago Changed · -129 lines · +4 tokens per session 4fcc2844dc4b
- 1mo ago First seen · 308 lines · 76 tokens per session scan A d581f3a119df
gpt-6-prompting is a skill published in the GitHub repository Dynokostya/just-works (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 68 tokens to every session and 3,172 once invoked, about $0.0003 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 2026-09-24.
gpt-6-prompting compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gpt-6-promptingDynokostya/just-works | Skill | 14 | 10d ago | Apache-2.0 | A | 68 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |