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/opus-5-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/opus-5-prompting)<a href="https://agentmods.dev/skills/dynokostya/just-works/opus-5-prompting"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/opus-5-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/opus-5-prompting"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/opus-5-prompting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 100 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Excessive Agency · line 157 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 188 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00104 | $0.06010 |
| Opus 5 | $0.00052 | $0.03005 |
| Sonnet 5 | $0.00021 | $0.01202 |
| Haiku 4.5 | $0.00010 | $0.00601 |
Grade A, and why
opus-5-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 6d 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 — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Opus 5 Prompting
When to Use
- Creating or editing system prompts targeting Opus 5
- Steering response length, deliverable length, and narration cadence
- Damping subagent spawning and self-verification
- Migrating prompt text from Opus 4.8 or older Claude models
Overview
Opus 5 is Anthropic's model for complex agentic coding and enterprise work. It performs well out of the box on existing Opus 4.8 prompts — the changes below are tuning, not repair. Most of the tuning removes instructions that earlier models needed and Opus 5 does not.
- Longer by default: Visible responses and files written to disk both run longer than on 4.8. Effort does not reliably shorten them — prompt for length explicitly.
- Narrates more: Announces what it is about to do during agentic work; per-message output in agentic sessions is longer than prior models'.
- Self-verifying: Checks and fixes its own work without being told to. Carried-over verification instructions cause over-verification.
- Delegates readily: Spawns subagents more eagerly than 4.8 — the opposite tuning direction from 4.8, which under-used them.
- Expands scope: Adds steps that weren't requested and applies its own judgment about what the task should be.
- Narrates corrections: Flags corrections to its own earlier statements more than prior models.
- Effort converts to quality: Turns additional effort into better results more reliably than any earlier Opus.
lowandmediumhold quality at a fraction of the tokens. - Completes tasks: Finishes multi-file features and refactors without leaving stubs or placeholders. Performs best given the full specification up front and left to run.
- Thinks by default: Reasoning is handled at the parameter level, so prompts should not prescribe it.
- Consistent across long context: Instruction following, tool calling, and reasoning stay consistent throughout a 1M-token window.
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.
- 6d ago First seen · 441 lines · 104 tokens per session scan A 63603fe17d69
opus-5-prompting is a skill published in the GitHub repository Dynokostya/just-works (14 stars, last pushed 2d ago), licensed Apache-2.0. It adds 104 tokens to every session and 6,010 once invoked, about $0.0005 per session on Opus 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 2026-09-04.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…