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-5-5-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-5-5-prompting)<a href="https://agentmods.dev/skills/dynokostya/just-works/opus-5-5-prompting"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/opus-5-5-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-5-5-prompting"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/opus-5-5-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 | $0.00074 | $0.03175 |
| Opus 5.5 | $0.00030 | $0.01270 |
| Sonnet 5.5 | $0.00015 | $0.00635 |
| Haiku 4.5 | $0.00007 | $0.00317 |
Grade A, and why
opus-5-5-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 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Opus 5.5 Prompting
When to Use
- Creating or editing system prompts targeting Opus 5.5
- Calibrating effort, progress updates, and turn endings for agentic products
- Hardening unattended agents against early stops and pasted-content injection
- Migrating prompt text from Opus 5, Opus 4.8, or older Claude models
Overview
Opus 5.5 is Anthropic's model for complex agentic coding and enterprise work. Existing Opus 5 prompts should perform well without changes, and the Opus 5 patterns remain a reasonable starting point. The changes below are tuning: calibrating effort, restoring visible progress, keeping unattended runs going, and removing instructions the model no longer needs. Source: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5.
The 5.5 guide does not re-address several Opus 5 behaviors: long default responses, over-verification, scope expansion, correction narration, and eager subagent spawning. The mitigations are in references/opus-5-carryover.md. Keep each only where your output still shows the behavior.
- Thinks more per turn. At a given effort level it thinks more than Opus 5, especially at
xhighandmax. Atmediumit matches or beats Opus 5 athighon coding and knowledge-work evals. Thinking is always on. - Quiet between tool calls. Progress notes arrive as progress-update thinking blocks, whose text is empty at the default
thinking.display, so a client rendering only text blocks can look silent. Updates get rarer at higher effort and in long tool chains. - Can stop early when unattended. Some progress updates end the turn with text while work is still owed.
- Gets to work quickly. In multi-app workflows it starts acting before exploring broadly.
- Clear writing. It leads with the important information and uses less jargon.
- Reliable facts and review. It is much less likely to state a wrong figure or source, and finds more bugs with fewer false alarms than Opus 5.
- Vision and computer use. Better at both; at its lowest effort it reads dense charts more accurately than Opus 5 at its highest.
- Prefers the full specification up front and being left to run (Opus 5 page).
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 · -25 tokens per session 4968bb9dedc5
- 17d ago Changed · -256 lines 8fed91d390f7
- 1mo ago First seen · 432 lines · 99 tokens per session scan A b9022629f563
opus-5-5-prompting is a skill published in the GitHub repository Dynokostya/just-works (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 74 tokens to every session and 3,175 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.
opus-5-5-prompting compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| opus-5-5-promptingDynokostya/just-works | Skill | 14 | 10d ago | Apache-2.0 | A | 74 | 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 |